
x402 Triage MCP
io.github.TateLymanPublished by GitHub account TateLymanv0.1.1Updated Oct 24, 2026
MCP server for no-payment x402 surface triage, 402 Index health checks, and paid review handoff.
Overview
Checks public x402 and HTTP 402 payment surfaces for launch blockers and returns static paid review handoff links.
- What you can do
- Exposes three tools: triage_x402_surface inspects one public x402, MPP, Pay.sh, OpenAPI, manifest, or HTTP 402 endpoint through a public triage API and returns status, payment headers, a parsed challenge summary, attack-class checks, and findings; watch_402_index searches public 402 Index metadata for provider health, payment-validity, and domain-verification signals; x402_paid_paths returns static paid API endpoints, a service catalog, an AgentCard, and fixed-scope review links. The server is described as read-only and does not send payment headers, wallet signatures, API keys, or paid calls.
- When to use it
- Use it when you want an assistant to sanity-check a public x402 or HTTP 402 launch surface you own or are authorized to inspect, or to look up public 402 Index health and verification signals before enabling agent payments.
- Requirements
- Runs locally over stdio, typically launched with npx from the npm package x402-triage-mcp; needs Node.js and network access to the public triage and index APIs. No accounts, API keys, environment variables, or headers are declared.
Installation
In SourceWeft
- Open x402 Triage MCP in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
x402-triage-mcp
MCP server for no-payment x402 surface triage, 402 Index health checks, and paid review handoff.
It exposes three MCP tools:
triage_x402_surfacechecks one public x402, MPP, Pay.sh, OpenAPI, manifest, or HTTP 402 endpoint through the Tate Programs public triage API.watch_402_indexsearches public 402 Index metadata for provider health, payment-validity, and domain-verification signals.x402_paid_pathsreturns the paid x402 API endpoints, service catalog, AgentCard, and fixed-scope review links.
The tools do not send X-PAYMENT, wallet signatures, API keys, private credentials, or paid calls.
Tool page: https://tateprograms.com/x402-surface-check.html
Paid x402 API catalog: https://tateprograms.com/services.json
AgentCard: https://the402.tateprograms.com/.well-known/agent-card.json
Install
Run directly with npx:
MCP Config
Add this server to an MCP client that supports stdio servers:
STDIO MCP client config launches a local command. Review the command, args, and any env values before running generated configs, and pin versions when repeatability matters.
Tools
triage_x402_surface
Returns status, payment headers, parsed challenge summary, attack-class checks, findings, and paid handoff paths.
watch_402_index
Returns matching public 402 Index records, health summary, visible launch blockers, and paid handoff paths.
x402_paid_paths
Returns:
https://the402.tateprograms.com/api/x402/triagehttps://the402.tateprograms.com/api/x402/index-watchhttps://tateprograms.com/services.jsonhttps://tateprograms.com/x402-five-attack-review.htmlhttps://tateprograms.com/x402-fix-sprint.html
Payment And Safety Boundary
Use this server only on public launch surfaces that you own or are authorized to inspect. Do not submit private URLs, tokenized URLs, customer data, wallet seed phrases, or production secrets.
This MCP server is read-only. It does not initiate payments, send X-PAYMENT headers, sign wallet messages, call paid endpoints, create invoices, settle balances, or grant purchasing authority. The only paid paths it returns are static Tate Programs handoff URLs for teams that choose to buy a separate review.
For agent-commerce reviews, the server reports whether the target surface exposes the safety controls buyers expect before real spend is enabled:
- Spend limits: per-call and total budget caps should be explicit before an agent can pay.
- Approval checkpoints: payment setup and high-risk spend should require a visible user or policy approval step.
- Recipient validation: paid requests should be constrained to expected domains, merchants, wallet addresses, or signed registry entries.
- Replay protection: challenges and settlement callbacks should use nonces, expirations, idempotency keys, signed resources, or equivalent controls.
- Metadata minimization: payment metadata should avoid private user context, secrets, and unnecessary resource detail.
- Receipts and audit trails: successful payments should produce transaction IDs, recipient, amount, reason, and policy evidence.
Development
Source: README.md at commit 2d392e5
Tools
0Version history
1- v0.1.1LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts