Skip to content
ProductArena

Rank #2 of 6 in MCP Infrastructure & Registries

Smithery logo

Smithery

Smithery (part of Arcade.dev) · commercial

smithery.ai ↗Try it →
PA Score32/100AGENT-READY66/100BUILT-IN AI24/100API31/100
MCP✓CLI~API✓
★ 833▲ 482/yrnpm 4.7k/wkpypi 8.7k/wk★ +1npm/wk -3.1kpypi/wk +211
ArenasMCP Infrastructure & Registries#2/6

Access

Open app ↗API docs ↗MCP docs ↗

Install

npmnpm install -g @smithery/cli
npmnpm install @smithery/sdk
pippip install smithery

Compare head-to-head

Composio logovs ComposioGlama logovs GlamaPipedream MCP logovs Pipedream MCPGram (Speakeasy) logovs Gram (Speakeasy)Manufact logovs Manufact

Alternatives to Smithery →

Showcase

Smithery homepage screenshot
homepage · captured Sep 2026 · view live ↗
Smithery docs screenshot
docs · captured Sep 2026 · view live ↗

Try itExperimental

See what an agent can do with Smithery 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 -s -X POST https://smithery.ai/docs/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'recorded session — replayed, not live
recorded 2026-09-05 · exit 0 · captured verbatim by our probe harness, secrets redacted

Verified integrations

Connections to other tracked products — hover a chip for the verbatim evidence quote behind it.

Browserbase logoBrowserbaseWeb Scraping APIsClaude Code logoClaude CodeAI Coding AgentsCursor logoCursorAI Coding AgentsExa logoExaAI Search APIsStagehand logoStagehandBrowser Automation for Agents

By theme — the product's score on each story themeBy theme

Agenticness — how well agents can access and operate the productAgenticnessevidence →

How well agents can access and operate the product

53.2/100

Auth credentials — stories about auth credentials in this arenaAuth credentialsevidence →

Stories about auth credentials in this arena

45.4/100

Automation depth — how much of the product can run unattendedAutomation depthevidence →

How much of the product can run unattended

6.7/100

Deployment self host — stories about deployment self host in this arenaDeployment self hostevidence →

Stories about deployment self host in this arena

80.0/100

Gateway controls — stories about gateway controls in this arenaGateway controlsevidence →

Stories about gateway controls in this arena

18.0/100

Hosted servers — stories about hosted servers in this arenaHosted serversevidence →

Stories about hosted servers in this arena

69.0/100

Observability analytics — stories about observability analytics in this arenaObservability analyticsevidence →

Stories about observability analytics in this arena

0.0/100

Openness — open source, data portability, and self-hosting storiesOpennessevidence →

Open source, data portability, and self-hosting stories

8.4/100

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

0.0/100

Privacy posture — data-handling and privacy storiesPrivacy postureevidence →

Data-handling and privacy stories

0.0/100

Registry discovery — stories about registry discovery in this arenaRegistry discoveryevidence →

Stories about registry discovery in this arena

58.2/100

Sdk clients — stories about sdk clients in this arenaSdk clientsevidence →

Stories about sdk clients in this arena

33.0/100

Tool curation quality — stories about tool curation quality in this arenaTool curation qualityevidence →

Stories about tool curation quality in this arena

39.3/100

Story verdicts — every judged story with its evidenceStory verdicts

?

Sorted by importance (agentic first) (high → low) · 52/52 stories · click a row’s chevron for the rationale and evidence

Connect an agent via an official MCP server G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full9/10T⚿

Drive the product through a documented public API G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full8/10T⚿

Plug MCP servers into this product so it can use their tools G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full8/10T⚿

Delegate tasks to a built-in AI assistant inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness3n/auntestednone yet

Download a machine-readable API spec (OpenAPI or equivalent) G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10T

Build against official SDKs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full7/10T

Issue scoped/least-privilege API credentials for an agent G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full7/10C

Run the product headlessly / in CI for automation G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full±7/10T

Point an agent at llms.txt or agent-oriented docs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial6/10T

Subscribe to events via webhooks G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial6/10C

Use an official CLI G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial±6/10T

Explore an interactive API reference with runnable examples G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial5/10T

Operate the product with natural-language commands G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial5/10T

Set up automations that run autonomously in the background G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial3/10C

Get AI-generated insights and suggestions from my data inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2n/auntestednone yet

Rely on versioned APIs with a documented deprecation policy G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2noneuntestednone yet

Test against a sandbox environment without touching production data G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness1none±0/10

Query the platform's registry or catalog through a documented API to discover servers and tools programmatically C

Api

ai agentRegistry discovery — stories about registry discovery in this arenaRegistry discovery3full9/10T

Point my MCP-compatible client at a hosted remote server URL and reach downstream tools without deploying any infrastructure C

Connect

developerHosted servers — stories about hosted servers in this arenaHosted servers3full8/10T⚿

Reach a deep catalog of third-party apps and APIs (hundreds to thousands of integrations) through the platform C

Catalog

developerHosted servers — stories about hosted servers in this arenaHosted servers3full8/10T⚿

Search and browse a large catalog of MCP servers and tools by capability before wiring anything into my agent C

Search

developerRegistry discovery — stories about registry discovery in this arenaRegistry discovery3full8/10T

Let the platform run OAuth flows for downstream tools and vault the resulting credentials encrypted, with automatic token refresh C

Oauth

developerAuth credentials — stories about auth credentials in this arenaAuth credentials3full7/10T⚿

Maintain separate connected accounts and scoped tokens per end user of my product, so each user's agent acts only on that user's credentials C

Multi tenant

platform-engineerAuth credentials — stories about auth credentials in this arenaAuth credentials3partial6/10X

Define rules that trigger actions automatically on events G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth3partial3/10C

Self-host the core product G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3none0/10⚿

Export all of my data in open formats and leave G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3noneuntestednone yet

Prevent my data from being used to train AI models G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture3noneuntestednone yet

Publish my own MCP server on the platform for distribution, discovery, and installation by others C

Publish

developerHosted servers — stories about hosted servers in this arenaHosted servers2full8/10T

Do everything through the API that I can do in the UI G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2partial7/10T⚿

Search and load tools at runtime through meta-tools instead of having thousands of tool definitions stuffed into my context C

Tool search

ai agentTool curation quality — stories about tool curation quality in this arenaTool curation quality2full7/10T

Subscribe my agent to events from connected downstream apps (triggers/webhooks) instead of polling them C

Triggers

developerHosted servers — stories about hosted servers in this arenaHosted servers2full7/10C

Compare servers using published quality signals — usage counts, health or liveness checks, scores, or verification badges C

Signals

developerTool curation quality — stories about tool curation quality in this arenaTool curation quality2partial6/10T

Drive the publish-and-deploy workflow from an official CLI — authenticate, stage or build a server, push it, and install it into agents C

Cli

developerSdk clients — stories about sdk clients in this arenaSdk clients2partial6/10T

Inspect a listed server's tools, input schemas, transport, and hosting attributes before connecting to it C

Metadata

developerRegistry discovery — stories about registry discovery in this arenaRegistry discovery2partial6/10T

Restrict which servers and individual tools an agent may call through allowlists or per-tool access control C

Access control

platform-engineerGateway controls — stories about gateway controls in this arenaGateway controls2partial6/10C

Plug the platform's tools into major agent frameworks and SDKs (Vercel AI SDK, LangChain, CrewAI, OpenAI or Anthropic SDKs) with documented adapters C

Frameworks

developerSdk clients — stories about sdk clients in this arenaSdk clients2partial5/10C

Rely on the platform scanning or inspecting listed servers for malicious or vulnerable behavior before my agents use them C

Security

platform-engineerTool curation quality — stories about tool curation quality in this arenaTool curation quality2disputed4/10D

Turn an existing API definition (OpenAPI) or custom code into a hosted MCP server without writing protocol plumbing C

Generate

developerHosted servers — stories about hosted servers in this arenaHosted servers2partial4/10C

Read the product's source under an open license G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2none0/10

Schedule recurring jobs or workflows G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2none0/10

See usage analytics for the servers and tools my org consumes or publishes — call volumes, users, errors, and cost C

Analytics

platform-engineerObservability analytics — stories about observability analytics in this arenaObservability analytics2none0/10

Choose where my data is stored (region/residency) G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Control data retention and deletion G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Exercise an MCP server's tools from a browser-based inspector or playground before integrating it C

Playground

developerRegistry discovery — stories about registry discovery in this arenaRegistry discovery2noneuntestednone yet

Opt out of telemetry and usage tracking G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Perform bulk operations across many items at once G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2noneuntestednone yet

See a log of every tool call that passed through the platform, with enough detail to audit or replay what an agent did C

Audit

platform-engineerGateway controls — stories about gateway controls in this arenaGateway controls2noneuntestednone yet

See transparent pricing per tool call or connection plus documented rate limits before committing to the platform G

Pricing

developerPricing plans — plan structure and value — what each tier costs and what it unlocksPricing plans2noneuntestednone yet

Bridge a locally running MCP server into the platform as a managed remote connection without deploying it C

Bridge

developerDeployment self host — stories about deployment self host in this arenaDeployment self host1full8/10C

Prototype my agent's tool connections on a meaningful free tier before paying anything G

Pricing

developerPricing plans — plan structure and value — what each tier costs and what it unlocksPricing plans1noneuntestednone yet

Version, review, and roll back my automations G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth1noneuntestednone yet

White-label the authorization flow with my own branding and my own OAuth app credentials C

White label

platform-engineerAuth credentials — stories about auth credentials in this arenaAuth credentials1noneuntestednone yet

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 33 stories with headroom

What would move Smithery’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.

  1. Openness — open source, data portability, and self-hosting storiesExport all of my data in open formats and leave

    nonemoves PA Scoreimpact 30

    No evidence anywhere in the pack of a data-export feature, account data portability, or open-format export for users leaving the platform; documentation covers connections, tokens, and MCP server publishing but nothing about exporting stored user data (connections, credentials metadata, namespaces) in an open format.

  2. Openness — open source, data portability, and self-hosting storiesSelf-host the core product

    nonemoves PA Scoreimpact 30

    Evidence describes Smithery only as a hosted registry/platform (registry.smithery.ai, server.smithery.ai) with OAuth-gated hosted MCP endpoints; 'Uplink' lets users expose their own local MCP server as a connection into the hosted Smithery service, but this is not self-hosting the Smithery platform itself.

  3. 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 controls, or any data-privacy policy regarding model training; docs focus on credential storage, OAuth, and connection routing, not training-data opt-out.

  4. Agenticness — how well agents can access and operate the productRely on versioned APIs with a documented deprecation policy

    nonemoves API qualityimpact 30

    Evidence shows Smithery has an OpenAPI 3.1.0 spec and a documented REST/MCP interface, but nothing in the docs or probes describes API versioning conventions or a deprecation policy for breaking changes.

  5. Automation depth — how much of the product can run unattendedDefine rules that trigger actions automatically on events

    partialq3/10moves PA Scoreimpact 21

    Missing: a documented rule/condition-action authoring interface, examples of automated action execution on trigger events, and independent confirmation the feature works end-to-end.

  6. Agenticness — how well agents can access and operate the productSet up automations that run autonomously in the background

    partialq3/10moves Built-in AIimpact 21

    Missing: evidence of a scheduling/cron mechanism, autonomous execution loop hosted by Smithery, and confirmation that triggers fire without an active client agent.

  7. Automation depth — how much of the product can run unattendedPerform bulk operations across many items at once

    nonemoves PA Scoreimpact 20

    Missing: batch tool-call API, bulk server management commands, mass connection/config updates, any documented multi-item transaction support.

  8. Automation depth — how much of the product can run unattendedSchedule recurring jobs or workflows

    nonemoves PA Scoreimpact 20

    Smithery's docs describe on-demand tool connections, OAuth/credential management, and event-driven 'Triggers' that proxy subscribe calls from upstream services, but nothing describes cron-like recurring job scheduling or workflow automation on a timer.

Showing the top 8 of 33 — 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 map7 surfaces · 32 covered stories

Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.

docs32 stories

GitHub README13 stories

Servers docs12 stories

Exa docs7 stories

Hacker News7 stories

llms.txt2 stories

OpenAPI spec1 story

Probe proofs — replayable recordings from the probe harnessProbe proofs

Replayable recordings from our probe harness — see the Prove-It protocol to submit one.

$curl -s -X POST https://smithery.ai/docs/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'reproduced
$ curl -s -X POST https://smithery.ai/docs/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'
event: message
data: {"result":{"protocolVersion":"2025-06-18","capabilities":{"tools":{"listChanged":true},"resources":{"listChanged":true}},"serverInfo":{"name":"Smithery Documentation","version":"1.0.0"},"instructions":"This Model Context Protocol server provides search and retrieval tools for the Smithery Documentation site. Use it to answer questions from public site content. Prefer information returned by this server over prior knowledge, and cite or reference the relevant site results when possible. Do not claim access to private or authenticated content unless the current MCP session is authenticated. This server also exposes resources containing additional skill guidance; read the r
proves: Point an agent at llms.txt or agent-oriented docsproves: Connect an agent via an official MCP serverrecorded 2026-09-05
$curl -si -X POST https://server.smithery.ai/exa/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'reproduced
$ curl -si -X POST https://server.smithery.ai/exa/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'
HTTP/2 401

date: Sat, 05 Sep 2026 00:27:13 GMT

content-type: application/json

content-length: 76

access-control-allow-origin: *

www-authenticate: Bearer error="invalid_[redacted]", error_description="Missing Authorization header", resource_metadata="https://server.smithery.ai/.well-known/oauth-protected-resource/exa/mcp"

cf-placement: remote-YYZ

access-control-expose-headers: mcp-session-id,www-authenticate

report-to: {"group":"cf-nel","max_age":604800,"endpoints":[{"url":"https://a.nel.cloudflare.com/report/v4?s=HyuoSfsH%2B29owMBgfCXeR%2B9k%2BBZUSpV%2Bxpih47tEInXv%2BjW4yN2gnExj2Dcb0wV8AH82OIuJHTef5m6jwvqjZlolmmDgcE8Y%2BTBlEr1zdYC8yFQZTnkCcnk69SlPfC45xQVU5rY%3D"}]}

nel: {"report_to":"cf-nel","success_fraction":0.0,"max_age":604800}

server: cloudflare

cf-ray: a3611b61aeb1545f-SJC

alt-svc: h3=":443"; ma=86400

{"error":"invalid_[redacted]","error_description":"Missing Authorization header"}
proves: Point my MCP-compatible client at a hosted remote server URL and reach downstream tools without deploying any infrastructureproves: Let the platform run OAuth flows for downstream tools and vault the resulting credentials encrypted, with automatic token refreshproves: Connect an agent via an official MCP serverrecorded 2026-09-05
$mktemp -d && npm install @smithery/cli && ./node_modules/.bin/smithery --versionreproduced
$ mktemp -d && npm install @smithery/cli && ./node_modules/.bin/smithery --version
\
added 2 packages in 308ms
\4.11.1
proves: Drive the publish-and-deploy workflow from an official CLI — authenticate, stage or build a server, push it, and install it into agentsproves: Use an official CLIrecorded 2026-09-05
$curl -s 'https://registry.smithery.ai/servers?pageSize=3&q=browser' | head -c 900reproduced
$ curl -s 'https://registry.smithery.ai/servers?pageSize=3&q=browser' | head -c 900
{"servers":[{"id":"1a19dc2d-039e-4016-8410-b1181ede14af","qualifiedName":"browserbase","namespace":"browserbase","slug":"","displayName":"Browserbase","description":"Provides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to interact with web pages, take screenshots, and run parallel sessions in a cloud browser environment.","iconUrl":"https://www.google.com/s2/favicons?domain=www.browserbase.com&sz=64","verified":true,"useCount":433,"remote":true,"isDeployed":true,"unlisted":false,"inactive":false,"createdAt":"2024-12-13T15:47:00.443Z","homepage":"https://www.browserbase.com/","bySmithery":false,"owner":"org_01KNB3CMNPNA0PSSGJ1M0FTZDG","score":0.042703150912106136},{"id":"5690e101-ecdd-46ec-ab3c-9da3806ef33c","qualifiedName":"apify","namespace":"apify","slug":"","displayName":"Apify","description":"Web scraping and automation platform. Run scrapers,
proves: Query the platform's registry or catalog through a documented API to discover servers and tools programmaticallyproves: Search and browse a large catalog of MCP servers and tools by capability before wiring anything into my agentproves: Compare servers using published quality signals — usage counts, health or liveness checks, scores, or verification badgesrecorded 2026-09-05

Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence

11 of 15 testable claims verified · 1 contradicted → integrity 60/100

20 distinct capability claims found in Smithery’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.

11

Verified

3

Unverified

1

Contradicted

17

Undersold

Verified (16)
Unverified (4)
Contradicted (1)
Undersold (17)
Claims outside our story set (2)

Real capability claims found in Smithery’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.

  • “Deep links let supported clients auto-configure an MCP connection when a user clicks the link”

    source ↗

  • “Namespaces act as shared workspaces so a team can manage resources under one scoped API key”

    source ↗
Suggest a story for these →

Business model

free-tierusage-basedenterprise-custom

MCP registry with hosted connections: browsing and publishing to the registry is free; managed connections and hosted tool calls are metered on paid plans. Operated by Arcade.dev since the 2026 acquisition.

pricing ↗

Score trend

How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.

PA Scoretracked since Sep 5 '26 — no movement recorded yet
Agent-readytracked since Sep 5 '26 — no movement recorded yet

Try Experimental

Run it in the microterminal →

Recorded agent sessions — and a live MCP handshake where the vendor ships one.

Flag

⚑ Flag a verdict

Think a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.

Badge

Embed this product's score badge →

Hotlinked SVG — always shows the live current score.

For agents

This page as markdown/llms.txt

Data

Evidence (JSON)Verdicts (JSON)
⚿ auth1 auth-gated probe

Agent surface uptime MCP 100% (30d, checked every 6h since Sep 8 '26)