Rank #1 of 5 in Meeting AI & Notetakers
vs Granola
vs Fireflies.ai
vs Otter.ai
vs FellowShowcase
Try itExperimental
See what an agent can do with Fathom before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; commands tagged live-capable can re-run against the real endpoint from our edge, right now (▶ run live — the exact same request, live and recorded lines always labeled); sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).
$curl -si https://api.fathom.ai/external/v1/meetingsrecorded session — replayed, not liveVerified integrations
Connections to other tracked products — hover a chip for the verbatim evidence quote behind it.
By theme — the product's score on each story themeBy theme
Agent access — MCP, CLI, and API access for agentsAgent accessevidence →
MCP, CLI, and API access for agents
Agenticness — how well agents can access and operate the productAgenticnessevidence →
How well agents can access and operate the product
Automation depth — how much of the product can run unattendedAutomation depthevidence →
How much of the product can run unattended
Calendar workflow — stories about calendar workflow in this arenaCalendar workflowevidence →
Stories about calendar workflow in this arena
Capture recording — stories about capture recording in this arenaCapture recordingevidence →
Stories about capture recording in this arena
Integrations crm — stories about integrations crm in this arenaIntegrations crmevidence →
Stories about integrations crm in this arena
Meeting memory search — stories about meeting memory search in this arenaMeeting memory searchevidence →
Stories about meeting memory search in this arena
Notes summaries — stories about notes summaries in this arenaNotes summariesevidence →
Stories about notes summaries in this arena
Openness — open source, data portability, and self-hosting storiesOpennessevidence →
Open source, data portability, and self-hosting stories
Pricing plans — plan structure and value — what each tier costs and what it unlocksPricing plansevidence →
Plan structure and value — what each tier costs and what it unlocks
Privacy consent — stories about privacy consent in this arenaPrivacy consentevidence →
Stories about privacy consent in this arena
Privacy posture — data-handling and privacy storiesPrivacy postureevidence →
Data-handling and privacy stories
Sharing collaboration — stories about sharing collaboration in this arenaSharing collaborationevidence →
Stories about sharing collaboration in this arena
Transcription accuracy — stories about transcription accuracy in this arenaTranscription accuracyevidence →
Stories about transcription accuracy in this arena
Story verdicts — every judged story with its evidenceStory verdicts
Follow the green: where the map greys out is where Fathom stops today. ✓ full · ~ partial · ! disputed · — none · n/a not applicable.
Agent access — MCP, CLI, and API access for agentsAgent access
MCP, CLI, and API access for agents
Agent ops
Agenticness — how well agents can access and operate the productAgenticness
How well agents can access and operate the product
API surface
Drive the product through a documented public API
✓9/10
unlocks → Scoped API keys · Versioning policy · Notes flow into the tools where work happens — Slack channels, Notion pages, and thousands of apps via Zapier
Subscribe to events via webhooks
✓9/10
Build against official SDKs
✓9/10
Issue scoped/least-privilege API credentials for an agent
—0/10
Connect an agent via an official MCP server
✓9/10
Download a machine-readable API spec (OpenAPI or equivalent)
✓8/10
Rely on versioned APIs with a documented deprecation policy
—0/10
Test against a sandbox environment without touching production data
n/an/a
Explore an interactive API reference with runnable examples
~5/10
Docs for agents
Point an agent at llms.txt or agent-oriented docs
✓9/10
Agentic features
Delegate tasks to a built-in AI assistant inside the product
~3/10
unlocks → MCP client
Operate the product with natural-language commands
~6/10
Plug MCP servers into this product so it can use their tools
—0/10
Get AI-generated insights and suggestions from my data inside the product
✓8/10
Set up automations that run autonomously in the background
~5/10
Automation depth — how much of the product can run unattendedAutomation depth
How much of the product can run unattended
Automation depth
Define rules that trigger actions automatically on events
~5/10
unlocks → I connect Google or Outlook calendar once and control per-meeting-type rules for which meetings get captured automatically · I walk into each meeting prepped — the tool surfaces past meetings with the same people and a brief of open threads before the call
Schedule recurring jobs or workflows
—0/10
Perform bulk operations across many items at once
~4/10
Version, review, and roll back my automations
n/an/a
Calendar workflow — stories about calendar workflow in this arenaCalendar workflow
Stories about calendar workflow in this arena
Capture recording — stories about capture recording in this arenaCapture recording
Stories about capture recording in this arena
Capture
Integrations crm — stories about integrations crm in this arenaIntegrations crm
Stories about integrations crm in this arena
Meeting memory search — stories about meeting memory search in this arenaMeeting memory search
Stories about meeting memory search in this arena
Notes summaries — stories about notes summaries in this arenaNotes summaries
Stories about notes summaries in this arena
Summaries
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
Pricing plans — plan structure and value — what each tier costs and what it unlocksPricing plans
Plan structure and value — what each tier costs and what it unlocks
Privacy consent — stories about privacy consent in this arenaPrivacy consent
Stories about privacy consent in this arena
Privacy
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
Sharing collaboration — stories about sharing collaboration in this arenaSharing collaboration
Stories about sharing collaboration in this arena
Transcription accuracy — stories about transcription accuracy in this arenaTranscription accuracy
Stories about transcription accuracy in this arena
Transcription
Sorted by importance (agentic first) (high → low) · 54/54 stories · click a row’s chevron for the rationale and evidence
Connect an agent via an official MCP server G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | full | 9/10 | Tprobed⚿ | |
Drive the product through a documented public API G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | full | 9/10 | Tprobed | |
Delegate tasks to a built-in AI assistant inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | partial | 3/10 | Cclaimed | |
Plug MCP servers into this product so it can use their tools G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | none | 0/10 | ⚿ | |
Build against official SDKs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 9/10 | Tprobed | |
Point an agent at llms.txt or agent-oriented docs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 9/10 | Tprobed | |
Subscribe to events via webhooks G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 9/10 | Tprobed | |
Download a machine-readable API spec (OpenAPI or equivalent) G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Tprobed | |
Get AI-generated insights and suggestions from my data inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Tprobed⚿ | |
Operate the product with natural-language commands G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 6/10 | Tprobed⚿ | |
Run the product headlessly / in CI for automation G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 6/10 | Tprobed | |
Explore an interactive API reference with runnable examples G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 5/10 | Tprobed | |
Set up automations that run autonomously in the background G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 5/10 | Tprobed⚿ | |
Issue scoped/least-privilege API credentials for an agent G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Rely on versioned APIs with a documented deprecation policy G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Use an official CLI G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | n/a | untested | none yet | |
Test against a sandbox environment without touching production data G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 1 | n/a | untested | none yet | |
An official MCP server lets Claude or any MCP client query my meetings — search, transcripts, action items — with OAuth, no glue code C Agent ops | ai-native user | Agent access — MCP, CLI, and API access for agentsAgent access | 3 | full | 9/10 | Tprobed⚿ | |
My scripts can pull transcripts, summaries, and action items from every meeting through a documented API with self-serve keys C Agent ops | ai-native user | Agent access — MCP, CLI, and API access for agentsAgent access | 3 | full | 9/10 | Tprobed | |
Action items with owners are automatically extracted from the conversation and collected somewhere I can track them C Summaries | product manager | Notes summaries — stories about notes summaries in this arenaNotes summaries | 3 | full | 8/10 | Tprobed | |
I get a structured summary right after each meeting — key points, decisions, and next steps — good enough to share without editing C Summaries | product manager | Notes summaries — stories about notes summaries in this arenaNotes summaries | 3 | full | 7/10 | Cclaimed | |
Export all of my data in open formats and leave G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | partial | 6/10 | Tprobed | |
Capture and transcribe meetings without a visible bot joining the call — audio is captured from my device so external participants see nothing extra C Capture | founder | Capture recording — stories about capture recording in this arenaCapture recording | 3 | partial | 5/10 | Cclaimed | |
Define rules that trigger actions automatically on events G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 3 | partial | 5/10 | Cclaimed | |
Meeting notes and summaries sync automatically onto the right contact and deal records in my CRM (HubSpot, Salesforce, Attio) C Integrations | sales lead | Integrations crm — stories about integrations crm in this arenaIntegrations crm | 3 | partial | 5/10 | Cclaimed | |
Search across every past meeting — transcripts, summaries, and notes — and jump to the exact moment something was said C Memory | product manager | Meeting memory search — stories about meeting memory search in this arenaMeeting memory search | 3 | partial | 5/10 | Cclaimed | |
I connect Google or Outlook calendar once and control per-meeting-type rules for which meetings get captured automatically C Calendar | product manager | Calendar workflow — stories about calendar workflow in this arenaCalendar workflow | 3 | none | untested | none yet | |
Prevent my data from being used to train AI models G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 3 | none | untested | none yet | |
Self-host the core product G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | n/a | untested | none yet | |
The product ships real consent features — participant notifications, in-meeting disclosure, or admin-enforced transparency — not just a policy PDF C Privacy | it admin | Privacy consent — stories about privacy consent in this arenaPrivacy consent | 3 | none | untested | none yet | |
The transcript attributes words to the right named speakers (diarization plus real name matching), not just "Speaker 1/2" C Transcription | product manager | Transcription accuracy — stories about transcription accuracy in this arenaTranscription accuracy | 3 | none | untested | none yet | |
The vendor documents how transcription actually works and its quality (models, accuracy claims, known limits) rather than just saying "AI-powered" C Transcription | product manager | Transcription accuracy — stories about transcription accuracy in this arenaTranscription accuracy | 3 | none | untested | none yet | |
An agent can automatically file each meeting's action items into my project tracker (Linear, Jira, Asana) using the product's API, webhooks, or native automations C Agent ops | ai-native user | Agent access — MCP, CLI, and API access for agentsAgent access | 2 | partial | 6/10 | Tprobed⚿ | |
Ask questions in natural language across my whole meeting history ("what did we decide about pricing?") and get answers with sources G Memory | product manager | Meeting memory search — stories about meeting memory search in this arenaMeeting memory search | 2 | partial | 6/10 | Tprobed⚿ | |
Do everything through the API that I can do in the UI G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | partial | 5/10 | Tprobed | |
Perform bulk operations across many items at once G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | partial | 4/10 | Tprobed | |
Sharing is controlled — private-by-default notes, granular link/folder/workspace permissions, and admin visibility into what's shared C Sharing | it admin | Sharing collaboration — stories about sharing collaboration in this arenaSharing collaboration | 2 | partial | 4/10 | Cclaimed | |
Start free and see exactly what each paid tier costs and adds — no "talk to sales" wall for basic use G Pricing | founder | Pricing plans — plan structure and value — what each tier costs and what it unlocksPricing plans | 2 | partial | 4/10 | Cclaimed | |
The notetaker reliably captures Zoom, Google Meet, and Microsoft Teams meetings, with recording where I want it C Capture | product manager | Capture recording — stories about capture recording in this arenaCapture recording | 2 | partial | 4/10 | Cclaimed | |
Record and transcribe in-person conversations from a mobile app, and those notes land in the same searchable workspace C Capture | founder | Capture recording — stories about capture recording in this arenaCapture recording | 2 | none | 0/10 | ||
Schedule recurring jobs or workflows G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | none | 0/10 | ||
Shape the notes with custom templates or saved prompts per meeting type (discovery call, 1:1, standup) instead of one generic format C Summaries | sales lead | Notes summaries — stories about notes summaries in this arenaNotes summaries | 2 | none | 0/10 | ||
Choose where my data is stored (region/residency) G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Control data retention and deletion G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Notes flow into the tools where work happens — Slack channels, Notion pages, and thousands of apps via Zapier C Integrations | product manager | Integrations crm — stories about integrations crm in this arenaIntegrations crm | 2 | none | untested | none yet | |
Opt out of telemetry and usage tracking G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Read the product's source under an open license G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | none | untested | none yet | |
Run meetings in languages other than English — transcription and summaries support many languages and handle language switching C Transcription | founder | Transcription accuracy — stories about transcription accuracy in this arenaTranscription accuracy | 2 | none | untested | none yet | |
Set retention policies — auto-delete transcripts and recordings on a schedule — and permanently erase data on demand C Privacy | it admin | Privacy consent — stories about privacy consent in this arenaPrivacy consent | 2 | none | untested | none yet | |
The vendor documents whether meeting data trains AI models and gives my org an enforceable opt-out, alongside SOC 2 / HIPAA posture C Privacy | it admin | Privacy consent — stories about privacy consent in this arenaPrivacy consent | 2 | none | untested | none yet | |
Cut a soundbite or highlight clip from a call and share that moment instead of the whole recording C Sharing | sales lead | Sharing collaboration — stories about sharing collaboration in this arenaSharing collaboration | 1 | partial | 5/10 | Cclaimed | |
I walk into each meeting prepped — the tool surfaces past meetings with the same people and a brief of open threads before the call C Calendar | founder | Calendar workflow — stories about calendar workflow in this arenaCalendar workflow | 1 | none | untested | none yet | |
The tool drafts my follow-up email from the meeting so I can review and send it in a couple of clicks C Summaries | sales lead | Notes summaries — stories about notes summaries in this arenaNotes summaries | 1 | none | untested | none yet | |
Version, review, and roll back my automations G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 1 | n/a | untested | none yet |
Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 39 stories with headroom
What would move Fathom’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.
Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools
nonemoves agent-readyimpact 45
All MCP evidence describes Fathom as an MCP *server* that other AI assistants (Claude, ChatGPT) connect to, not Fathom acting as an MCP client that plugs in external MCP servers to use their tools.
Agenticness — how well agents can access and operate the productDelegate tasks to a built-in AI assistant inside the product
partialq3/10moves Built-in AIimpact 31.5
Missing: detailed docs on the conversational assistant's task-delegation capabilities, examples of it performing actions, and independent/hands-on confirmation.
Calendar workflow — stories about calendar workflow in this arenaI connect Google or Outlook calendar once and control per-meeting-type rules for which meetings get captured automatically
nonemoves PA Scoreimpact 30
The evidence pack contains no mention of connecting a Google/Outlook calendar or configuring per-meeting-type auto-capture rules; it only covers API/webhook/SDK/MCP integration and pricing tiers (bot vs bot-free capture, custom bot) with no calendar-workflow specifics.
Privacy consent — stories about privacy consent in this arenaThe product ships real consent features — participant notifications, in-meeting disclosure, or admin-enforced transparency — not just a policy PDF
nonemoves PA Scoreimpact 30
The evidence pack covers API/SDK/webhook/MCP integration and pricing tiers (bot vs bot-free capture, SSO/SCIM) but contains no mention of participant consent notifications, in-meeting recording disclosure banners, or admin-enforced transparency controls — the core capabilities this story asks about.
Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models
nonemoves PA Scoreimpact 30
No evidence in the pack addresses AI-training data usage, opt-out settings, or data-privacy policies regarding model training; the evidence is entirely about API/SDK/MCP integration features.
Transcription accuracy — stories about transcription accuracy in this arenaThe transcript attributes words to the right named speakers (diarization plus real name matching), not just "Speaker 1/2"
nonemoves PA Scoreimpact 30
No evidence in the pack addresses diarization or speaker-name matching in transcripts; the pack only covers API access, webhooks, MCP integration, and pricing tiers.
Transcription accuracy — stories about transcription accuracy in this arenaThe vendor documents how transcription actually works and its quality (models, accuracy claims, known limits) rather than just saying "AI-powered"
nonemoves PA Scoreimpact 30
The evidence pack contains extensive docs on API access, webhooks, MCP integration, and pricing tiers, but nothing about transcription models, accuracy claims, language support, or known limitations of the transcription/AI engine itself — everything is marketed generically as 'AI summaries' or 'AI generated action items' without technical detail.
Agenticness — how well agents can access and operate the productIssue scoped/least-privilege API credentials for an agent
nonemoves agent-readyimpact 30
Fathom's docs describe generating a single account-wide API key in User Settings (fathom-docs-1, fathom-docs-7) and a separate OAuth flow for public apps (fathom-docs-5, fathom-docs-21), but nowhere do the docs describe scopes, roles, or least-privilege permission grants that an AI agent could be issued.
Showing the top 8 of 39 — every none/partial verdict in the story verdicts table is headroom.
Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.
Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map12 surfaces · 29 covered stories
Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.
API reference17 stories
- An agent can automatically file each meeting's action items into my project tracker (Linear, Jira, Asana) using the product's API, webhooks, or native automations
- My scripts can pull transcripts, summaries, and action items from every meeting through a documented API with self-serve keys
- Point an agent at llms.txt or agent-oriented docs
- Run the product headlessly / in CI for automation
- Drive the product through a documented public API
- Build against official SDKs
- Subscribe to events via webhooks
- Set up automations that run autonomously in the background
- Explore an interactive API reference with runnable examples
- Download a machine-readable API spec (OpenAPI or equivalent)
- Perform bulk operations across many items at once
- Define rules that trigger actions automatically on events
- Search across every past meeting — transcripts, summaries, and notes — and jump to the exact moment something was said
- Action items with owners are automatically extracted from the conversation and collected somewhere I can track them
- I get a structured summary right after each meeting — key points, decisions, and next steps — good enough to share without editing
- Do everything through the API that I can do in the UI
- Export all of my data in open formats and leave
Pricing docs16 stories
- An agent can automatically file each meeting's action items into my project tracker (Linear, Jira, Asana) using the product's API, webhooks, or native automations
- Get AI-generated insights and suggestions from my data inside the product
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Define rules that trigger actions automatically on events
- The notetaker reliably captures Zoom, Google Meet, and Microsoft Teams meetings, with recording where I want it
- Capture and transcribe meetings without a visible bot joining the call — audio is captured from my device so external participants see nothing extra
- Meeting notes and summaries sync automatically onto the right contact and deal records in my CRM (HubSpot, Salesforce, Attio)
- Ask questions in natural language across my whole meeting history ("what did we decide about pricing?") and get answers with sources
- Search across every past meeting — transcripts, summaries, and notes — and jump to the exact moment something was said
- Action items with owners are automatically extracted from the conversation and collected somewhere I can track them
- I get a structured summary right after each meeting — key points, decisions, and next steps — good enough to share without editing
- Do everything through the API that I can do in the UI
- Start free and see exactly what each paid tier costs and adds — no "talk to sales" wall for basic use
- Cut a soundbite or highlight clip from a call and share that moment instead of the whole recording
- Sharing is controlled — private-by-default notes, granular link/folder/workspace permissions, and admin visibility into what's shared
fathom.ai11 stories
- An official MCP server lets Claude or any MCP client query my meetings — search, transcripts, action items — with OAuth, no glue code
- Connect an agent via an official MCP server
- Get AI-generated insights and suggestions from my data inside the product
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Define rules that trigger actions automatically on events
- The notetaker reliably captures Zoom, Google Meet, and Microsoft Teams meetings, with recording where I want it
- Capture and transcribe meetings without a visible bot joining the call — audio is captured from my device so external participants see nothing extra
- Ask questions in natural language across my whole meeting history ("what did we decide about pricing?") and get answers with sources
- Search across every past meeting — transcripts, summaries, and notes — and jump to the exact moment something was said
- I get a structured summary right after each meeting — key points, decisions, and next steps — good enough to share without editing
API overview docs10 stories
- An agent can automatically file each meeting's action items into my project tracker (Linear, Jira, Asana) using the product's API, webhooks, or native automations
- My scripts can pull transcripts, summaries, and action items from every meeting through a documented API with self-serve keys
- Run the product headlessly / in CI for automation
- Drive the product through a documented public API
- Build against official SDKs
- Subscribe to events via webhooks
- Download a machine-readable API spec (OpenAPI or equivalent)
- Perform bulk operations across many items at once
- Action items with owners are automatically extracted from the conversation and collected somewhere I can track them
- Do everything through the API that I can do in the UI
Sdks docs9 stories
- My scripts can pull transcripts, summaries, and action items from every meeting through a documented API with self-serve keys
- Run the product headlessly / in CI for automation
- Drive the product through a documented public API
- Build against official SDKs
- Set up automations that run autonomously in the background
- Explore an interactive API reference with runnable examples
- Perform bulk operations across many items at once
- Do everything through the API that I can do in the UI
- Export all of my data in open formats and leave
MCP docs docs8 stories
- An agent can automatically file each meeting's action items into my project tracker (Linear, Jira, Asana) using the product's API, webhooks, or native automations
- An official MCP server lets Claude or any MCP client query my meetings — search, transcripts, action items — with OAuth, no glue code
- Point an agent at llms.txt or agent-oriented docs
- Connect an agent via an official MCP server
- Get AI-generated insights and suggestions from my data inside the product
- Set up automations that run autonomously in the background
- Operate the product with natural-language commands
- Ask questions in natural language across my whole meeting history ("what did we decide about pricing?") and get answers with sources
Webhooks docs7 stories
- An agent can automatically file each meeting's action items into my project tracker (Linear, Jira, Asana) using the product's API, webhooks, or native automations
- Build against official SDKs
- Subscribe to events via webhooks
- Set up automations that run autonomously in the background
- Define rules that trigger actions automatically on events
- Action items with owners are automatically extracted from the conversation and collected somewhere I can track them
- Do everything through the API that I can do in the UI
Quickstart docs5 stories
- My scripts can pull transcripts, summaries, and action items from every meeting through a documented API with self-serve keys
- Perform bulk operations across many items at once
- Do everything through the API that I can do in the UI
- Export all of my data in open formats and leave
- Sharing is controlled — private-by-default notes, granular link/folder/workspace permissions, and admin visibility into what's shared
developers.fathom.ai4 stories
Changelog docs3 stories
llms.txt2 stories
Probe proofs — replayable recordings from the probe harnessProbe proofs
Replayable recordings from our probe harness — see the Prove-It protocol to submit one.
$curl -si https://api.fathom.ai/external/v1/meetingsreproduced$ curl -si https://api.fathom.ai/external/v1/meetings HTTP/2 401 date: Sat, 05 Sep 2026 05:08:52 GMT content-type: text/html x-frame-options: SAMEORIGIN x-xss-protection: 0 x-content-type-options: nosniff x-download-options: noopen x-permitted-cross-domain-policies: none referrer-policy: strict-origin-when-cross-origin ratelimit-limit: 60 ratelimit-remaining: 0 ratelimit-reset: 0 cache-control: no-cache content-security-policy: base-uri 'none'; default-src blob: *.crazyegg.com opps-widget.getwarmly.com opps-api.getwarmly.com https://*.chameleon.io; connect-src https: wss: *.crazyegg.com opps-widget.getwarmly.com opps-api.getwarmly.com https://*.saltfish.ai; font-src 'self' https: data:; frame-src https: *.crazyegg.com opps-widget.getwarmly.com opps-api.getwarmly.com; img-src 'self' https: data: *.crazyegg.com opps-widget.getwarmly.com opps-api.getwarmly.com https://ct.capterra.com; media-src 'self' https: blob: data: https://*.saltfish.ai; object-src 'none'; script-src 'strict-dynamic' 'self' blob: https: 'unsafe-inline' 'wasm-unsafe-eval' 'report-sample' *.crazyegg.com opps-widget.getwarmly.com opps-api.getwarmly.com 'nonce-+DYXBZTMGW5HoqM3TPzCeg=='; style-src 'strict-dynamic' 'self' https: blob: *.crazyegg.com opps-widget.getwarmly.com opps-api.getwarmly.com assets.churn[redacted].co 'sha256-47DEQpj8HBSa+/TImW+5JCeuQeRkm5NMpJWZG3hSuFU=' 'sha256-TY3UmPzl9Yfdi4fdvwKsW7KZRglCk2NtwnpPBEnPBPk=' 'sha256-9DXMwgj0ENzPQGBkxxGWOBkPGyW4liL8lmH5T08RvtY=' 'sha256-JcO0hIPu2fx0ENUCeCUTwROltSWYsMueEikACrBGfDk=' 'sha256-gn90mc5f2qDgclfTh9qsaQikcdgVPI1Ii6jcUT+NaYk=' 'sha256-IC1KkF+eC8FPJk8dqtZorwrw5QGHgras+HbtoDZ7JWU=' 'sha256-CMKq1xo3ThFhA7djF4+5c40lf1tMSQcyMcODfZxX5HI=' 'sha256-TY3UmPzl9Yfdi4fdvwKsW7KZRglCk2NtwnpPBEnPBPk=' 'sha256-hXy/2Y+cnJu9UEsJaToZwlRtYNmEKRsYvTGGsdfh+9Q=' 'sha256-3YUjzyBn7H3n55vMQSvngvivAXHL5vVhLQ0Esowr6Jo=' 'sha256-o+rS663/A4WHzEbToTUS284eUy46Mtc80BHSmonvzeU=' 'sha256-PjJZcBl1xYrj4ZjtrQalzqr6GHesVum0yc+jX8Rh18s=' 'sha256-TY3UmPzl9Yfdi4fdvwKsW7KZRglCk2NtwnpPBEnPBPk=' 'sha256-hXy/2Y+cnJu9UEsJaToZwlRtYNmEKRsYvTGGsdfh+9Q=' 'sha256-3YUjzyBn7H3n55vMQSvngvivAXHL5vVhLQ0Esowr6Jo=' 'sha256-o+rS663/A4WHzEbToTUS284eUy46Mtc80BHSmonvzeU=' 'sha256-PjJZcBl1xYrj4ZjtrQalzqr6GHesVum0yc+jX8Rh18s=' 'sha256-EEd0EC2LfE1V2PiLy0sF6SIBhO3GHWEe9FMTdVx6ufA=' 'sha256-0CXoX0u9HyM8mVJxddTch3Qeroxo/9sncuzlm5njsqQ=' 'sha256-Ysv8g+tGHLIIu7b1GBs7pPVLGJ24YuX3NPP9WJDxfZU=' 'sha256-/tV5jumB6/X4lW94XBNnStyWzI+SeLu5YD/3pb0nKH4=' unsafe-hashes 'report-sample' 'nonce-+DYXBZTMGW5HoqM3TPzCeg=='; report-uri https://fathom.video/csp-report set-cookie: _fathom_session=71254ed717867708eaeca1d4b4de11aa; path=/; secure; HttpOnly; SameSite=Lax x-request-id: 32567f32-4656-4d2b-a62f-bb110ca5b532 x-runtime: 0.002516 strict-transport-security: max-age=31536000; includeSubDomains; preload content-security-policy-report-only: default-src 'none'; script-src 'strict-dynamic' 'wasm-unsafe-eval' 'report-sample' 'nonce-+DYXBZTMGW5HoqM3TPzCeg=='; style-src 'self' https://static.fathom.video 'report-sample' 'nonce-+DYXBZTMGW5HoqM3TPzCeg=='; connect-src 'self' wss://*.pusher.com wss://*.pusherapp.com https://*.pusher.com wss://pushkit.fathom.video https://sentry.io https://*.sentry.io https://*.amplitude.com https://*.fathom.video https://storage.googleapis.com https://*.storage.googleapis.com https://*.crazyegg.com https://opps-widget.getwarmly.com https://opps-api.getwarmly.com https://*.chameleon.io https://*.saltfish.ai https://plausible.io https://www.googletagmanager.com https://*.google-analytics.com https://*.analytics.google.com https://*.hubspot.com https://js.hs-scripts.com https://*.hs-analytics.net https://chat-assets.frontapp.com https://*.frontapp.com https://cdn-cookieyes.com https://log.cookieyes.com https://tracking.g2crowd.com https://app.revenuehero.io https://zhdqcn694sgb.statuspage.io; img-src 'self' data: https://www.gravatar.com https://ui-avatars.com https://i0.wp.com https://i1.wp.com https://i2.wp.com https://storage.googleapis.com https://static.fathom.video https://assets.brandfetch.io https://embed-ssl.wistia.com https://avatars.slack-edge.com https://zoom.us https://*.zoom.us https://*.googleusercontent.com https://graph.facebook.com https://ct.capterra.com https://www.googletagmanager.com https://*.google-analytics.com https://*.crazyegg.com; media-src 'self' blob: data: https://storage.googleapis.com https://*.storage.googleapis.com https://static.fathom.video https://embed-ssl.wistia.com; font-src 'self' data: https://static.fathom.video https://chat-assets.frontapp.com; frame-src 'self' https://assets.churn[redacted].co https://app.revenuehero.io https://chat-assets.frontapp.com https://fast.wistia.com https://embed-ssl.wistia.com https://www.googletagmanager.com https://*.crazyegg.com https://opps-widget.getwarmly.com https://opps-api.getwarmly.com https://*.chameleon.io https://zhdqcn694sgb.statuspage.io; frame-ancestors 'none'; form-action 'self'; worker-src 'none'; object-src 'none'; base-uri 'none' via: 1.1 google cf-cache-status: DYNAMIC server: cloudflare cf-ray: a362b7f1f9c3cef9-SJC
$curl -si -X POST https://api.fathom.ai/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'reproduced$ curl -si -X POST https://api.fathom.ai/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'
HTTP/2 401
date: Sat, 05 Sep 2026 05:08:52 GMT
content-type: application/json; charset=utf-8
x-frame-options: SAMEORIGIN
x-xss-protection: 0
x-content-type-options: nosniff
x-download-options: noopen
x-permitted-cross-domain-policies: none
referrer-policy: strict-origin-when-cross-origin
www-authenticate: Bearer resource_metadata="https://api.fathom.ai/.well-known/oauth-protected-resource/mcp"
vary: Accept
cache-control: no-cache
content-security-policy: base-uri 'none'; default-src blob: *.crazyegg.com opps-widget.getwarmly.com opps-api.getwarmly.com https://*.chameleon.io; connect-src https: wss: *.crazyegg.com opps-widget.getwarmly.com opps-api.getwarmly.com https://*.saltfish.ai; font-src 'self' https: data:; frame-src https: *.crazyegg.com opps-widget.getwarmly.com opps-api.getwarmly.com; img-src 'self' https: data: *.crazyegg.com opps-widget.getwarmly.com opps-api.getwarmly.com https://ct.capterra.com; media-src 'self' https: blob: data: https://*.saltfish.ai; object-src 'none'; script-src 'strict-dynamic' 'self' blob: https: 'unsafe-inline' 'wasm-unsafe-eval' 'report-sample' *.crazyegg.com opps-widget.getwarmly.com opps-api.getwarmly.com 'nonce-VuK8f4YptrxoPz3dHUx5Mw=='; style-src 'strict-dynamic' 'self' https: blob: *.crazyegg.com opps-widget.getwarmly.com opps-api.getwarmly.com assets.churn[redacted].co 'sha256-47DEQpj8HBSa+/TImW+5JCeuQeRkm5NMpJWZG3hSuFU=' 'sha256-TY3UmPzl9Yfdi4fdvwKsW7KZRglCk2NtwnpPBEnPBPk=' 'sha256-9DXMwgj0ENzPQGBkxxGWOBkPGyW4liL8lmH5T08RvtY=' 'sha256-JcO0hIPu2fx0ENUCeCUTwROltSWYsMueEikACrBGfDk=' 'sha256-gn90mc5f2qDgclfTh9qsaQikcdgVPI1Ii6jcUT+NaYk=' 'sha256-IC1KkF+eC8FPJk8dqtZorwrw5QGHgras+HbtoDZ7JWU=' 'sha256-CMKq1xo3ThFhA7djF4+5c40lf1tMSQcyMcODfZxX5HI=' 'sha256-TY3UmPzl9Yfdi4fdvwKsW7KZRglCk2NtwnpPBEnPBPk=' 'sha256-hXy/2Y+cnJu9UEsJaToZwlRtYNmEKRsYvTGGsdfh+9Q=' 'sha256-3YUjzyBn7H3n55vMQSvngvivAXHL5vVhLQ0Esowr6Jo=' 'sha256-o+rS663/A4WHzEbToTUS284eUy46Mtc80BHSmonvzeU=' 'sha256-PjJZcBl1xYrj4ZjtrQalzqr6GHesVum0yc+jX8Rh18s=' 'sha256-TY3UmPzl9Yfdi4fdvwKsW7KZRglCk2NtwnpPBEnPBPk=' 'sha256-hXy/2Y+cnJu9UEsJaToZwlRtYNmEKRsYvTGGsdfh+9Q=' 'sha256-3YUjzyBn7H3n55vMQSvngvivAXHL5vVhLQ0Esowr6Jo=' 'sha256-o+rS663/A4WHzEbToTUS284eUy46Mtc80BHSmonvzeU=' 'sha256-PjJZcBl1xYrj4ZjtrQalzqr6GHesVum0yc+jX8Rh18s=' 'sha256-EEd0EC2LfE1V2PiLy0sF6SIBhO3GHWEe9FMTdVx6ufA=' 'sha256-0CXoX0u9HyM8mVJxddTch3Qeroxo/9sncuzlm5njsqQ=' 'sha256-Ysv8g+tGHLIIu7b1GBs7pPVLGJ24YuX3NPP9WJDxfZU=' 'sha256-/tV5jumB6/X4lW94XBNnStyWzI+SeLu5YD/3pb0nKH4=' unsafe-hashes 'report-sample' 'nonce-VuK8f4YptrxoPz3dHUx5Mw=='; report-uri https://fathom.video/csp-report
x-request-id: b977cb8a-b5f5-4881-bfd3-a9a7f47c3619
x-runtime: 0.005366
strict-transport-security: max-age=31536000; includeSubDomains; preload
access-control-allow-origin: *
access-control-allow-headers: Authorization, Content-Type, mcp-protocol-version
access-control-allow-methods: GET, POST, OPTIONS
access-control-max-age: 7200
content-security-policy-report-only: default-src 'none'; script-src 'strict-dynamic' 'wasm-unsafe-eval' 'report-sample' 'nonce-VuK8f4YptrxoPz3dHUx5Mw=='; style-src 'self' https://static.fathom.video 'report-sample' 'nonce-VuK8f4YptrxoPz3dHUx5Mw=='; connect-src 'self' wss://*.pusher.com wss://*.pusherapp.com https://*.pusher.com wss://pushkit.fathom.video https://sentry.io https://*.sentry.io https://*.amplitude.com https://*.fathom.video https://storage.googleapis.com https://*.storage.googleapis.com https://*.crazyegg.com https://opps-widget.getwarmly.com https://opps-api.getwarmly.com https://*.chameleon.io https://*.saltfish.ai https://plausible.io https://www.googletagmanager.com https://*.google-analytics.com https://*.analytics.google.com https://*.hubspot.com https://js.hs-scripts.com https://*.hs-analytics.net https://chat-assets.frontapp.com https://*.frontapp.com https://cdn-cookieyes.com https://log.cookieyes.com https://tracking.g2crowd.com https://app.revenuehero.io https://zhdqcn694sgb.statuspage.io; img-src 'self' data: https://www.gravatar.com https://ui-avatars.com https://i0.wp.com https://i1.wp.com https://i2.wp.com https://storage.googleapis.com https://static.fathom.video https://assets.brandfetch.io https://embed-ssl.wistia.com https://avatars.slack-edge.com https://zoom.us https://*.zoom.us https://*.googleusercontent.com https://graph.facebook.com https://ct.capterra.com https://www.googletagmanager.com https://*.google-analytics.com https://*.crazyegg.com; media-src 'self' blob: data: https://storage.googleapis.com https://*.storage.googleapis.com https://static.fathom.video https://embed-ssl.wistia.com; font-src 'self' data: https://static.fathom.video https://chat-assets.frontapp.com; frame-src 'self' https://assets.churn[redacted].co https://app.revenuehero.io https://chat-assets.frontapp.com https://fast.wistia.com https://embed-ssl.wistia.com https://www.googletagmanager.com https://*.crazyegg.com https://opps-widget.getwarmly.com https://opps-api.getwarmly.com https://*.chameleon.io https://zhdqcn694sgb.statuspage.io; frame-ancestors 'none'; form-action 'self'; worker-src 'none'; object-src 'none'; base-uri 'none'
via: 1.1 google
cf-cache-status: DYNAMIC
server: cloudflare
cf-ray: a362b7f10f47176b-SJC
{"error":"unauthorized"}
$curl -s https://developers.fathom.ai/api-reference/openapi.yaml | head -8reproduced$ curl -s https://developers.fathom.ai/api-reference/openapi.yaml | head -8
openapi: 3.1.1
info:
title: Fathom External API
version: "1.0.0"
description: |
The Fathom External API lets you poll meetings, teams, and team members, and
optionally receive webhooks when content from a new meeting is ready.
Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence
9 of 18 testable claims verified · 1 contradicted → integrity 39/100
39 distinct capability claims found in Fathom’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.
9
Verified
8
Unverified
1
Contradicted
12
Undersold
Verified (26)
“Users can generate an API key from account settings for self-serve API access”
My scripts can pull transcripts, summaries, and action items from every meeting through a documented API with self-serve keysfullproof ↗
“Users can generate an API key from account settings for self-serve API access”
Drive the product through a documented public APIfullproof ↗
“API lets you list the most recent meetings recorded or shared with your team”
My scripts can pull transcripts, summaries, and action items from every meeting through a documented API with self-serve keysfullproof ↗
“You can set up a webhook to receive meeting events”
“Official TypeScript and Python SDKs are available for building integrations”
“SDK provides a verify_webhook helper to validate webhook signatures”
“REST API is authenticated via API keys generated in account settings”
Drive the product through a documented public APIfullproof ↗
“API includes an endpoint to download meeting recordings”
My scripts can pull transcripts, summaries, and action items from every meeting through a documented API with self-serve keysfullproof ↗
“Official MCP server lets AI assistants like ChatGPT and Claude query meeting data”
An official MCP server lets Claude or any MCP client query my meetings — search, transcripts, action items — with OAuth, no glue codefullproof ↗
“Official MCP server lets AI assistants like ChatGPT and Claude query meeting data”
“Fathom is available as an official connector inside Claude”
An official MCP server lets Claude or any MCP client query my meetings — search, transcripts, action items — with OAuth, no glue codefullproof ↗
“Coaching metrics and AI scorecards analyze call performance”
Get AI-generated insights and suggestions from my data inside the productfullproof ↗
“Meeting data can be accessed inside ChatGPT and Claude via connectors”
An official MCP server lets Claude or any MCP client query my meetings — search, transcripts, action items — with OAuth, no glue codefullproof ↗
“Webhooks deliver meeting summary, transcript, and action items to a chosen URL”
“Webhooks deliver meeting summary, transcript, and action items to a chosen URL”
My scripts can pull transcripts, summaries, and action items from every meeting through a documented API with self-serve keysfullproof ↗
“Official SDKs handle authentication, pagination, and error handling automatically”
“Claude CLI can add the Fathom MCP server directly”
An official MCP server lets Claude or any MCP client query my meetings — search, transcripts, action items — with OAuth, no glue codefullproof ↗
“Summary endpoint can return data directly or POST it asynchronously to a destination URL”
“API can fetch a call's summary directly or via destination URL callback”
My scripts can pull transcripts, summaries, and action items from every meeting through a documented API with self-serve keysfullproof ↗
“AI automatically generates action items from meetings”
Action items with owners are automatically extracted from the conversation and collected somewhere I can track themfullproof ↗
“Built-in conversational meeting assistant answers questions about calls”
Ask questions in natural language across my whole meeting history ("what did we decide about pricing?") and get answers with sourcespartialproof ↗
“Webhook payloads include a signature to verify they came from Fathom”
“Claude Code can add Fathom's MCP server directly from the command line”
An official MCP server lets Claude or any MCP client query my meetings — search, transcripts, action items — with OAuth, no glue codefullproof ↗
“Fathom can be connected to any MCP-compatible tool via its server URL and authentication”
“Fathom can be connected to any MCP-compatible tool via its server URL and authentication”
An official MCP server lets Claude or any MCP client query my meetings — search, transcripts, action items — with OAuth, no glue codefullproof ↗
“Webhook creation requires selecting at least one content type (transcript, CRM matches, summary, action items)”
Unverified (13)
“CRM field sync automatically updates records after meetings”
Meeting notes and summaries sync automatically onto the right contact and deal records in my CRM (HubSpot, Salesforce, Attio)partialproof ↗
“Users can build playlists of highlight clips from meetings”
Cut a soundbite or highlight clip from a call and share that moment instead of the whole recordingpartialproof ↗
“Collaboration features include comments, folders, and keyword alerts”
Sharing is controlled — private-by-default notes, granular link/folder/workspace permissions, and admin visibility into what's sharedpartialproof ↗
“Users can choose bot-free (beta) or traditional bot-based meeting capture”
Capture and transcribe meetings without a visible bot joining the call — audio is captured from my device so external participants see nothing extrapartialproof ↗
“Users can choose bot-free (beta) or traditional bot-based meeting capture”
The notetaker reliably captures Zoom, Google Meet, and Microsoft Teams meetings, with recording where I want itpartialproof ↗
“Built-in conversational meeting assistant answers questions about calls”
Delegate tasks to a built-in AI assistant inside the productpartialproof ↗
“Users can create clips, playlists, and search across all calls”
Cut a soundbite or highlight clip from a call and share that moment instead of the whole recordingpartialproof ↗
“Users can create clips, playlists, and search across all calls”
Search across every past meeting — transcripts, summaries, and notes — and jump to the exact moment something was saidpartialproof ↗
“Admins can view all users' shared meetings via configurable view permissions”
Sharing is controlled — private-by-default notes, granular link/folder/workspace permissions, and admin visibility into what's sharedpartialproof ↗
“Notes can be captured with or without a bot joining the call”
Capture and transcribe meetings without a visible bot joining the call — audio is captured from my device so external participants see nothing extrapartialproof ↗
“Notes can be captured with or without a bot joining the call”
The notetaker reliably captures Zoom, Google Meet, and Microsoft Teams meetings, with recording where I want itpartialproof ↗
“AI-generated summaries are available immediately after each call”
I get a structured summary right after each meeting — key points, decisions, and next steps — good enough to share without editingfullproof ↗
“Custom meeting bot can be configured for capture”
The notetaker reliably captures Zoom, Google Meet, and Microsoft Teams meetings, with recording where I want itpartialproof ↗
Contradicted (1)
“Advanced call summaries support custom summary formats”
Shape the notes with custom templates or saved prompts per meeting type (discovery call, 1:1, standup) instead of one generic formatnoneproof ↗
Undersold (12)
An agent can automatically file each meeting's action items into my project tracker (Linear, Jira, Asana) using the product's API, webhooks, or native automationspartialproof ↗
Point an agent at llms.txt or agent-oriented docsfullproof ↗
Run the product headlessly / in CI for automationpartialproof ↗
Set up automations that run autonomously in the backgroundpartialproof ↗
Operate the product with natural-language commandspartialproof ↗
Explore an interactive API reference with runnable examplespartialproof ↗
Download a machine-readable API spec (OpenAPI or equivalent)fullproof ↗
Perform bulk operations across many items at oncepartialproof ↗
Define rules that trigger actions automatically on eventspartialproof ↗
Do everything through the API that I can do in the UIpartialproof ↗
Export all of my data in open formats and leavepartialproof ↗
Start free and see exactly what each paid tier costs and adds — no "talk to sales" wall for basic usepartialproof ↗
Claims outside our story set (7)
Real capability claims found in Fathom’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.
“Developers can build a public OAuth app so other Fathom users can install it”
source ↗“API includes a users and permissions endpoint for admin management”
source ↗“Deal View feature summarizes CRM-related meeting insights”
source ↗“Keyword alerts automatically monitor meetings for key topics”
source ↗“Public apps integrating with Fathom should be built using OAuth”
source ↗“SSO and SCIM provisioning are supported for enterprise identity management”
source ↗“Unlimited recordings and transcriptions are offered”
source ↗
Business model
Free plan with unlimited recordings and transcriptions (bot-free capture in beta); Premium $20/month adds action items and advanced summaries; Team/Business per-seat tiers add CRM sync and coaching; Enterprise is custom.
pricing ↗Score trend
How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.
Try Experimental
Run it in the microterminal →Recorded agent sessions — and a live MCP handshake where the vendor ships one.
Flag
⚑ Flag a verdictThink a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.
For agents
Agent surface uptime MCP 100% · llms.txt 100% (30d, checked every 6h since Sep 8 '26)