Try itExperimental
See what an agent can do with Skyfire 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); the live MCP handshake runs real requests from our edge, right now — including, where the server allows it, one real read-only tool call (bring your own key for auth-gated servers); sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).
$curl -s -X POST https://api.skyfire.xyz/api/v1/tokens/introspect -d '{}' # documented token API, keyless → structured challengerecorded session — replayed, not liveVerified integrations
No integration evidence found in our corpus for this product yet — that means none was found, never that it doesn’t integrate.
By theme — the product's score on each story themeBy theme
Agent checkout — stories about agent checkout in this arenaAgent checkoutevidence →
Stories about agent checkout in this arena
Agent discovery — stories about agent discovery in this arenaAgent discoveryevidence →
Stories about agent discovery in this arena
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
Fees economics — stories about fees economics in this arenaFees economicsevidence →
Stories about fees economics in this arena
Merchant enablement — stories about merchant enablement in this arenaMerchant enablementevidence →
Stories about merchant enablement in this arena
Openness — open source, data portability, and self-hosting storiesOpennessevidence →
Open source, data portability, and self-hosting stories
Order lifecycle — stories about order lifecycle in this arenaOrder lifecycleevidence →
Stories about order lifecycle in this arena
Payment credentials — stories about payment credentials in this arenaPayment credentialsevidence →
Stories about payment credentials in this arena
Privacy posture — data-handling and privacy storiesPrivacy postureevidence →
Data-handling and privacy stories
Protocol openness — stories about protocol openness in this arenaProtocol opennessevidence →
Stories about protocol openness in this arena
Refunds disputes — stories about refunds disputes in this arenaRefunds disputesevidence →
Stories about refunds disputes in this arena
Trust safety — stories about trust safety in this arenaTrust safetyevidence →
Stories about trust safety in this arena
Story verdicts — every judged story with its evidenceStory verdicts
What’s free: 0 free · 1 paid · 0 enterprise · 27 not stated in evidence
Follow the green: where the map greys out is where Skyfire stops today. ✓ full · ~ partial · ! disputed · — none · n/a not applicable.
Agent checkout — stories about agent checkout in this arenaAgent checkout
Stories about agent checkout in this arena
My agent can create and update a cart or order draft through a documented protocol call
—0/10
My agent can complete a purchase end-to-end — checkout session, delegated payment credential, confirmed order
✓8/10
Buyers can complete purchases of my products inside chat and assistant surfaces (ChatGPT, Claude, Gemini, Copilot and peers)
—0/10
Build against a versioned commerce protocol with a published schema and conformance or validation tooling
~4/10
Agent discovery — stories about agent discovery in this arenaAgent discovery
Stories about agent discovery in this arena
My agent can programmatically search products or services across merchants — keylessly or with self-service credentials, no private partnership required
~5/10
Read machine-readable offer data — price, availability, variants, checkout links — for any listed product or service
~3/10
Publish my product or service catalog into agent surfaces through a documented feed or import API so AI agents can discover what I sell
~5/10
My agent can discover payable services and APIs through a published directory or discovery index
~6/10
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
✓8/10
unlocks → Webhooks · Official SDKs · Machine-readable spec · Versioning policy · Official CLI · Full data export · My agent can create and update a cart or order draft through a documented protocol call · Buyers can complete purchases of my products inside chat and assistant surfaces (ChatGPT, Claude, Gemini, Copilot and peers)
Subscribe to events via webhooks
—–
Build against official SDKs
—0/10
Issue scoped/least-privilege API credentials for an agent
~6/10
Connect an agent via an official MCP server
✓8/10
Download a machine-readable API spec (OpenAPI or equivalent)
—0/10
Rely on versioned APIs with a documented deprecation policy
—0/10
Test against a sandbox environment without touching production data
~5/10
Explore an interactive API reference with runnable examples
—0/10
Agentic features
Delegate tasks to a built-in AI assistant inside the product
n/an/a
Operate the product with natural-language commands
~6/10
Plug MCP servers into this product so it can use their tools
n/an/a
Get AI-generated insights and suggestions from my data inside the product
n/an/a
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
Fees economics — stories about fees economics in this arenaFees economics
Stories about fees economics in this arena
Merchant enablement — stories about merchant enablement in this arenaMerchant enablement
Stories about merchant enablement in this arena
Orders are attributed to the originating agent and I can report on or filter transactions by agent
~5/10
I have a documented self-serve path to start accepting agent traffic — enable a setting, sign an agreement, or publish an endpoint
~7/10
Rate-limit, allow, or deny specific agents and agent platforms accessing my catalog and checkout
~4/10
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
Order lifecycle — stories about order lifecycle in this arenaOrder lifecycle
Stories about order lifecycle in this arena
Payment credentials — stories about payment credentials in this arenaPayment credentials
Stories about payment credentials in this arena
Hand my agent a scoped, limited-use payment credential — amount limits, expiry, merchant restrictions — instead of a raw card number
✓8/10
Monetize an API or service with HTTP 402 machine payments that agents pay per call without a checkout UI
~7/10
Settle agent-initiated payments in stablecoins over documented rails
~3/10
Provision a wallet my agent holds and spends from — funded and controlled by me, with balance visibility
✓7/10
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
Protocol openness — stories about protocol openness in this arenaProtocol openness
Stories about protocol openness in this arena
Refunds disputes — stories about refunds disputes in this arenaRefunds disputes
Stories about refunds disputes in this arena
Trust safety — stories about trust safety in this arenaTrust safety
Stories about trust safety in this arena
Agents identify themselves verifiably — registered profiles, signatures, or trust tiers — so I can tell trusted agent traffic from anonymous bots
✓8/10
Sensitive agent spending requires my documented approval — a confirmation step, signed mandate, or per-purchase consent — before money moves
~5/10
The fraud, liability, and chargeback rules for agent-initiated transactions are documented so I know who bears the risk
~6/10
Set per-agent spend caps and usage limits and revoke an agent's payment authority instantly
~4/10
Sorted by importance (agentic first) (high → low) · 56/56 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 | 8/10 | Cclaimed | |
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 | 8/10 | Tprobed | |
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 | n/a | 0/10 | ||
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 | n/a | untested | none yet | |
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 | 8/10 | 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 | partial | 6/10 | Cclaimed | |
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 | Cclaimed | |
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 | |
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 | Cclaimed | |
Build against official SDKs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
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 | none | 0/10 | ||
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 | 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 | ||
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 | n/a | untested | none yet | |
Subscribe to events via webhooks G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Use an official CLI G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 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 | partial | 5/10 | Cclaimed | |
Agents identify themselves verifiably — registered profiles, signatures, or trust tiers — so I can tell trusted agent traffic from anonymous bots C Agent identity | merchant | Trust safety — stories about trust safety in this arenaTrust safety | 3 | fullpaid | 8/10 | Cclaimed | |
Hand my agent a scoped, limited-use payment credential — amount limits, expiry, merchant restrictions — instead of a raw card number C Delegated credentials | ai-native user | Payment credentials — stories about payment credentials in this arenaPayment credentials | 3 | full | 8/10 | Cclaimed | |
My agent can complete a purchase end-to-end — checkout session, delegated payment credential, confirmed order C Checkout | ai-native user | Agent checkout — stories about agent checkout in this arenaAgent checkout | 3 | full | 8/10 | Tprobed | |
I have a documented self-serve path to start accepting agent traffic — enable a setting, sign an agreement, or publish an endpoint C Onboarding to agents | merchant | Merchant enablement — stories about merchant enablement in this arenaMerchant enablement | 3 | partial | 7/10 | Cclaimed | |
Monetize an API or service with HTTP 402 machine payments that agents pay per call without a checkout UI C Machine payments | developer | Payment credentials — stories about payment credentials in this arenaPayment credentials | 3 | partial | 7/10 | Cclaimed | |
Provision a wallet my agent holds and spends from — funded and controlled by me, with balance visibility C Wallets | ai-native user | Payment credentials — stories about payment credentials in this arenaPayment credentials | 3 | full | 7/10 | Cclaimed | |
My agent can programmatically search products or services across merchants — keylessly or with self-service credentials, no private partnership required C Agent search | ai-native user | Agent discovery — stories about agent discovery in this arenaAgent discovery | 3 | partial | 5/10 | Tprobed | |
Publish my product or service catalog into agent surfaces through a documented feed or import API so AI agents can discover what I sell C Merchant feeds | merchant | Agent discovery — stories about agent discovery in this arenaAgent discovery | 3 | partial | 5/10 | Cclaimed | |
Sensitive agent spending requires my documented approval — a confirmation step, signed mandate, or per-purchase consent — before money moves C Human oversight | ai-native user | Trust safety — stories about trust safety in this arenaTrust safety | 3 | partial | 5/10 | Cclaimed | |
The commerce protocol this product speaks is published as an open, versioned specification I can read and implement without signing anything C Spec publication | developer | Protocol openness — stories about protocol openness in this arenaProtocol openness | 3 | partial | 4/10 | Tprobed | |
My agent can create and update a cart or order draft through a documented protocol call C Cart | ai-native user | Agent checkout — stories about agent checkout in this arenaAgent checkout | 3 | none | 0/10 | ||
My agent or backend can subscribe to order lifecycle events — created, updated, fulfilled, canceled — pushed programmatically C Order events | developer | Order lifecycle — stories about order lifecycle in this arenaOrder lifecycle | 3 | none | 0/10 | ||
Self-host the core product G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | n/a | 0/10 | ||
Define rules that trigger actions automatically on events G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 3 | n/a | untested | none yet | |
Export all of my data in open formats and leave G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 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 | n/a | untested | none yet | |
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 | 6/10 | Tprobed | |
My agent can discover payable services and APIs through a published directory or discovery index C Service discovery | ai-native user | Agent discovery — stories about agent discovery in this arenaAgent discovery | 2 | partial | 6/10 | Cclaimed | |
The fraud, liability, and chargeback rules for agent-initiated transactions are documented so I know who bears the risk C Liability | merchant | Trust safety — stories about trust safety in this arenaTrust safety | 2 | partial | 6/10 | Cclaimed | |
Orders are attributed to the originating agent and I can report on or filter transactions by agent C Attribution analytics | merchant | Merchant enablement — stories about merchant enablement in this arenaMerchant enablement | 2 | partial | 5/10 | Cclaimed | |
Build against a versioned commerce protocol with a published schema and conformance or validation tooling C Protocol conformance | developer | Agent checkout — stories about agent checkout in this arenaAgent checkout | 2 | partial | 4/10 | Tprobed | |
Rate-limit, allow, or deny specific agents and agent platforms accessing my catalog and checkout C Traffic controls | merchant | Merchant enablement — stories about merchant enablement in this arenaMerchant enablement | 2 | partial | 4/10 | Cclaimed | |
Set per-agent spend caps and usage limits and revoke an agent's payment authority instantly G Spend controls | ai-native user | Trust safety — stories about trust safety in this arenaTrust safety | 2 | partial | 4/10 | Cclaimed | |
Read machine-readable offer data — price, availability, variants, checkout links — for any listed product or service C Machine readable offers | developer | Agent discovery — stories about agent discovery in this arenaAgent discovery | 2 | partial | 3/10 | Tprobed | |
Settle agent-initiated payments in stablecoins over documented rails C Settlement rails | developer | Payment credentials — stories about payment credentials in this arenaPayment credentials | 2 | partial | 3/10 | Cclaimed | |
At least two independent parties beyond the vendor implement the protocol or platform — it is an ecosystem, not a private integration C Ecosystem adoption | developer | Protocol openness — stories about protocol openness in this arenaProtocol openness | 2 | none | 0/10 | ||
Buyers can complete purchases of my products inside chat and assistant surfaces (ChatGPT, Claude, Gemini, Copilot and peers) C Embedded surfaces | merchant | Agent checkout — stories about agent checkout in this arenaAgent checkout | 2 | none | 0/10 | ||
Disputes and chargebacks on agent transactions can be handled via API — evidence submission, status, outcomes C Disputes | developer | Refunds disputes — stories about refunds disputes in this arenaRefunds disputes | 2 | none | 0/10 | ||
Perform bulk operations across many items at once G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | none | 0/10 | ||
Read the product's source under an open license G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | none | 0/10 | ||
Refunds on agent-placed orders can be initiated and tracked programmatically C Refunds | developer | Refunds disputes — stories about refunds disputes in this arenaRefunds disputes | 2 | none | 0/10 | ||
The fees for agent-originated transactions are published — I can price agentic channels without asking sales C Fees transparency | merchant | Fees economics — stories about fees economics in this arenaFees economics | 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 | n/a | 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 | |
My agent can query the status and tracking of an order it placed, after the purchase C Post purchase status | ai-native user | Order lifecycle — stories about order lifecycle in this arenaOrder lifecycle | 2 | n/a | untested | none yet | |
Opt out of telemetry and usage tracking G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | n/a | untested | none yet | |
Schedule recurring jobs or workflows G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | n/a | untested | none yet | |
Agent-originated payments settle through documented payout and reporting flows, reconcilable like any other channel C Payouts | merchant | Fees economics — stories about fees economics in this arenaFees economics | 1 | partial | 5/10 | Cclaimed | |
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 38 stories with headroom
What would move Skyfire’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.
Agent checkout — stories about agent checkout in this arenaMy agent can create and update a cart or order draft through a documented protocol call
nonemoves PA Scoreimpact 30
Skyfire's documented protocol (tokens, kya/pay/kya-pay, MCP tools like find-sellers/create-*-token) covers identity verification and payment authorization/settlement, but there is no documented call for creating or updating a cart or order draft — order/cart state is left to the seller's own system, not exposed via Skyfire's API or MCP server.
Openness — open source, data portability, and self-hosting storiesExport all of my data in open formats and leave
nonemoves PA Scoreimpact 30
Missing: any documented export/download capability, open-format (CSV/JSON) data dump, or account-closure data portability guarantee.
Order lifecycle — stories about order lifecycle in this arenaMy agent or backend can subscribe to order lifecycle events — created, updated, fulfilled, canceled — pushed programmatically
nonemoves PA Scoreimpact 30
Skyfire's docs cover token creation, charging, and introspection (pull-based checks), but there is no evidence of any webhook, event subscription, or push notification mechanism for order lifecycle events (created/updated/fulfilled/canceled).
Agenticness — how well agents can access and operate the productUse an official CLI
nonemoves agent-readyimpact 30
Missing: any documented CLI binary, npm/pip package, or command-line reference.
Agenticness — how well agents can access and operate the productBuild against official SDKs
nonemoves agent-readyimpact 30
Evidence shows Skyfire has REST API reference docs, a Playground, and an MCP server for agent integration, but nowhere does it mention or link to an official language SDK (e.g., Python/JS client library).
Agenticness — how well agents can access and operate the productSubscribe to events via webhooks
nonemoves agent-readyimpact 30
Missing: any webhook endpoint registration, event types, or push-notification documentation.
Agenticness — how well agents can access and operate the productExplore an interactive API reference with runnable examples
nonemoves API qualityimpact 30
The evidence shows Skyfire has structured reference docs (charge-token, introspect-token, etc.) but the openapi probe found no machine-readable spec (404s on all candidate paths), and there is no mention of an interactive console, 'try it' feature, or runnable code examples anywhere in the pack — only static markdown-style API reference pages.
Agenticness — how well agents can access and operate the productDownload a machine-readable API spec (OpenAPI or equivalent)
nonemoves API qualityimpact 30
The docs contain structured API reference pages (e.g., charge-token, introspect-token) suggesting an underlying spec, but a direct probe for machine-readable OpenAPI/Swagger files at all standard locations returned 404 for every candidate path, and no evidence shows a downloadable spec file or link.
Showing the top 8 of 38 — 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 map4 surfaces · 28 covered stories
Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.
docs27 stories
- My agent can complete a purchase end-to-end — checkout session, delegated payment credential, confirmed order
- Build against a versioned commerce protocol with a published schema and conformance or validation tooling
- My agent can programmatically search products or services across merchants — keylessly or with self-service credentials, no private partnership required
- Read machine-readable offer data — price, availability, variants, checkout links — for any listed product or service
- Publish my product or service catalog into agent surfaces through a documented feed or import API so AI agents can discover what I sell
- My agent can discover payable services and APIs through a published directory or discovery index
- Run the product headlessly / in CI for automation
- Connect an agent via an official MCP server
- Drive the product through a documented public API
- Issue scoped/least-privilege API credentials for an agent
- Set up automations that run autonomously in the background
- Operate the product with natural-language commands
- Test against a sandbox environment without touching production data
- Agent-originated payments settle through documented payout and reporting flows, reconcilable like any other channel
- Orders are attributed to the originating agent and I can report on or filter transactions by agent
- I have a documented self-serve path to start accepting agent traffic — enable a setting, sign an agreement, or publish an endpoint
- Rate-limit, allow, or deny specific agents and agent platforms accessing my catalog and checkout
- Do everything through the API that I can do in the UI
- Hand my agent a scoped, limited-use payment credential — amount limits, expiry, merchant restrictions — instead of a raw card number
- Monetize an API or service with HTTP 402 machine payments that agents pay per call without a checkout UI
- Settle agent-initiated payments in stablecoins over documented rails
- Provision a wallet my agent holds and spends from — funded and controlled by me, with balance visibility
- The commerce protocol this product speaks is published as an open, versioned specification I can read and implement without signing anything
- Agents identify themselves verifiably — registered profiles, signatures, or trust tiers — so I can tell trusted agent traffic from anonymous bots
- Sensitive agent spending requires my documented approval — a confirmation step, signed mandate, or per-purchase consent — before money moves
- The fraud, liability, and chargeback rules for agent-initiated transactions are documented so I know who bears the risk
- Set per-agent spend caps and usage limits and revoke an agent's payment authority instantly
API reference16 stories
- My agent can complete a purchase end-to-end — checkout session, delegated payment credential, confirmed order
- My agent can programmatically search products or services across merchants — keylessly or with self-service credentials, no private partnership required
- 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
- Agent-originated payments settle through documented payout and reporting flows, reconcilable like any other channel
- Orders are attributed to the originating agent and I can report on or filter transactions by agent
- I have a documented self-serve path to start accepting agent traffic — enable a setting, sign an agreement, or publish an endpoint
- Do everything through the API that I can do in the UI
- Hand my agent a scoped, limited-use payment credential — amount limits, expiry, merchant restrictions — instead of a raw card number
- Monetize an API or service with HTTP 402 machine payments that agents pay per call without a checkout UI
- Settle agent-initiated payments in stablecoins over documented rails
- Provision a wallet my agent holds and spends from — funded and controlled by me, with balance visibility
- The commerce protocol this product speaks is published as an open, versioned specification I can read and implement without signing anything
- The fraud, liability, and chargeback rules for agent-initiated transactions are documented so I know who bears the risk
- Set per-agent spend caps and usage limits and revoke an agent's payment authority instantly
OpenAPI spec6 stories
- Build against a versioned commerce protocol with a published schema and conformance or validation tooling
- Read machine-readable offer data — price, availability, variants, checkout links — for any listed product or service
- Point an agent at llms.txt or agent-oriented docs
- Drive the product through a documented public API
- Do everything through the API that I can do in the UI
- The commerce protocol this product speaks is published as an open, versioned specification I can read and implement without signing anything
Probe proofs — replayable recordings from the probe harnessProbe proofs
Replayable recordings from our probe harness — see the Prove-It protocol to submit one.
$curl -s -X POST https://api.skyfire.xyz/api/v1/tokens/introspect -d '{}' # documented token API, keyless → structured challengereproduced$ curl -s -X POST https://api.skyfire.xyz/api/v1/[redacted]s/introspect -d '{}' # documented [redacted] API, [redacted]less → structured challenge
{"code":"NOT_AUTHORIZED","message":"Invalid API [redacted]"}
$curl -s https://docs.skyfire.xyz/llms.txt | head -3reproduced$ curl -s https://docs.skyfire.xyz/llms.txt | head -3 # Skyfire Developer Portal Documentation > Skyfire is the open identity and payments layer for AI agents. We enable AI agents to securely create accounts, verify identity, and pay for digital services—autonomously. With Skyfire, developers can monetize APIs, tools, and content directly to agents using [redacted]-based authentication and stablecoin payments.
Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence
3 of 15 testable claims verified · 0 contradicted → integrity 20/100
21 distinct capability claims found in Skyfire’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.
3
Verified
12
Unverified
0
Contradicted
13
Undersold
Verified (3)
“Sellers can publish an MCP Server Resource documenting which token types and headers are required for each endpoint”
Point an agent at llms.txt or agent-oriented docsfullproof ↗
“Sellers can offer a guest-checkout flow to buyer agents using a combined kya-pay token”
My agent can complete a purchase end-to-end — checkout session, delegated payment credential, confirmed orderfullproof ↗
“All Skyfire tokens conform to the open, published KYAPay protocol specification for identity-linked agent payments”
The commerce protocol this product speaks is published as an open, versioned specification I can read and implement without signing anythingpartialproof ↗
Unverified (17)
“API keys are scoped to a single agent (Buyer or Seller) and managed per-agent in the dashboard”
Issue scoped/least-privilege API credentials for an agentpartialproof ↗
“Sellers onboard by creating a service (name, type, pricing, identity requirements) and submitting it for Skyfire's approval”
I have a documented self-serve path to start accepting agent traffic — enable a setting, sign an agreement, or publish an endpointpartialproof ↗
“Sellers charge a buyer-issued pay/kya-pay token via an API after delivering the service, and tokens can be charged multiple times until balance is exhausted”
Hand my agent a scoped, limited-use payment credential — amount limits, expiry, merchant restrictions — instead of a raw card numberfullproof ↗
“Buyers or sellers can check whether a token is still usable and see its remaining balance”
Provision a wallet my agent holds and spends from — funded and controlled by me, with balance visibilityfullproof ↗
“An official MCP server lets agents discover sellers, generate identity/payment tokens, and execute commerce workflows end-to-end”
“A single Know Your Agent (KYA) identity verification applies to both buyer and seller agents”
Agents identify themselves verifiably — registered profiles, signatures, or trust tiers — so I can tell trusted agent traffic from anonymous botsfullproof ↗
“Sites or bot managers can recognize a verified agent/platform and let it through instead of blocking it”
Rate-limit, allow, or deny specific agents and agent platforms accessing my catalog and checkoutpartialproof ↗
“Signing up automatically creates a Buyer Agent with a pre-funded wallet ready to spend”
Provision a wallet my agent holds and spends from — funded and controlled by me, with balance visibilityfullproof ↗
“Three token types (kya, pay, kya-pay) drive a commerce loop ending with Skyfire moving funds between buyer and seller wallets”
Agent-originated payments settle through documented payout and reporting flows, reconcilable like any other channelpartialproof ↗
“An optional paid identity tier attaches a real-world identity to agents; transactions fail if the buyer isn't verified to the required level”
Agents identify themselves verifiably — registered profiles, signatures, or trust tiers — so I can tell trusted agent traffic from anonymous botsfullproof ↗
“Pay tokens commit a specific amount against the buyer's wallet as a spending ceiling, guaranteeing the seller gets paid up to that amount”
Hand my agent a scoped, limited-use payment credential — amount limits, expiry, merchant restrictions — instead of a raw card numberfullproof ↗
“Charges can be submitted up to 24 hours after token expiry, with settlement completing within up to 51 hours”
Agent-originated payments settle through documented payout and reporting flows, reconcilable like any other channelpartialproof ↗
“Deactivation stops new tokens but already-issued tokens stay chargeable until expiry plus grace period; no per-token revocation API is documented”
Set per-agent spend caps and usage limits and revoke an agent's payment authority instantlypartialproof ↗
“Card-based agent purchases are capped by the cardholder-approved amount, which acts as a ceiling rather than a guaranteed charge”
Sensitive agent spending requires my documented approval — a confirmation step, signed mandate, or per-purchase consent — before money movespartialproof ↗
“A kya identity token is attached to every step of a purchase from search through checkout, so agentic purchases are never anonymous to the merchant”
Agents identify themselves verifiably — registered profiles, signatures, or trust tiers — so I can tell trusted agent traffic from anonymous botsfullproof ↗
“The MCP server exposes discrete tools (find-sellers, create-kya-token, create-pay-token, create-kya-payment-token) with a separate sandbox endpoint for testing”
Test against a sandbox environment without touching production datapartialproof ↗
“Agents can programmatically discover payable sellers/services via the MCP find-sellers tool”
My agent can discover payable services and APIs through a published directory or discovery indexpartialproof ↗
Undersold (13)
Build against a versioned commerce protocol with a published schema and conformance or validation toolingpartialproof ↗
My agent can programmatically search products or services across merchants — keylessly or with self-service credentials, no private partnership requiredpartialproof ↗
Read machine-readable offer data — price, availability, variants, checkout links — for any listed product or servicepartialproof ↗
Publish my product or service catalog into agent surfaces through a documented feed or import API so AI agents can discover what I sellpartialproof ↗
Run the product headlessly / in CI for automationpartialproof ↗
Drive the product through a documented public APIfullproof ↗
Set up automations that run autonomously in the backgroundpartialproof ↗
Operate the product with natural-language commandspartialproof ↗
Orders are attributed to the originating agent and I can report on or filter transactions by agentpartialproof ↗
Do everything through the API that I can do in the UIpartialproof ↗
Monetize an API or service with HTTP 402 machine payments that agents pay per call without a checkout UIpartialproof ↗
Settle agent-initiated payments in stablecoins over documented railspartialproof ↗
The fraud, liability, and chargeback rules for agent-initiated transactions are documented so I know who bears the riskpartialproof ↗
Claims outside our story set (1)
Real capability claims found in Skyfire’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 create tokens directly via the Playground or API with pre-filled parameters”
source ↗
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
