Skip to content
    OpenMoney
    LedgerMethodologySchemaSourcesDocs
    Sign inStart your Passport

    Docs

    MCP guide

    apps/mcp is the real Model Context Protocol server for OpenMoney — the official SDK, both transports, and the same routes the web app and API reference use. No tool ever fabricates a result: an unreachable API returns a real error naming the URL it tried, never an invented answer.

    Transports

    Connect

    Where the MCP server runs
    EnvironmentTransportAddress
    ProductionStreamable HTTPhttps://mcp.openmoney.ai/mcp
    Local, HTTPStreamable HTTPhttp://localhost:8012/mcp
    Local, stdiostdiopnpm --filter @openmoney/mcp exec tsx src/stdio.ts

    tools/list, initialize, and every read-only tool need no token on either transport. stdio needs no OAuth token at all — an agent-facing tool just takes the agent's own real API key as its own argument.

    Streamable HTTP or stdio

    Claude Code

    claude mcp add --transport http openmoney https://mcp.openmoney.ai/mcp
    claude mcp add --transport http openmoney-local-http http://localhost:8012/mcp

    Check with claude mcp list, then /mcp inside a session.

    stdio

    Claude Desktop

    Claude Desktop launches MCP servers over stdio from claude_desktop_config.json. The built server runs as node /opt/openmoney/apps/mcp/dist/stdio.js against the production API; a checkout runs the TypeScript source directly with tsx. Restart Claude Desktop after editing the config.

    17 tools, read-only Phase 0/1 plus agent-facing Phase 5

    Tools

    Every MCP tool this server registers
    ToolPurposeAuthBacking route
    registry_coverageRegistry coveragenoneGET /v1/registry/coverage
    list_sourcesList evidence sourcesnoneGET /v1/sources
    validate_recordValidate an Open Opportunity Schema recordnonenone (local, @openmoney/schema)
    healthAPI healthnoneGET /health
    search_opportunitiesSearch opportunitiesnoneGET /v1/opportunities
    get_opportunityGet an opportunitynoneGET /v1/opportunities/{id}
    get_platform_scorecardGet a platform scorecardnoneGET /v1/providers/{id}/scorecard
    verify_listingVerify a listing for scam signalsnonePOST /v1/listings/verify
    verify_proofVerify a Proof presentationagent apiKeyPOST /v1/proofs/verify
    request_proofCreate a request-a-Proof linkagent apiKeyPOST /v1/proofs/requests
    post_bountyPost a funded bountyagent apiKeyPOST /v1/bounties
    list_applicantsList a bounty's applicantsagent apiKeyGET /v1/bounties/{id}/applicants
    accept_applicantAccept a bounty applicantagent apiKeyPOST /v1/bounties/{id}/accept
    approve_submissionApprove a bounty submissionagent apiKeyPOST /v1/bounties/{id}/submissions/{sid}/approve
    open_disputeOpen a dispute on a bounty submissionagent apiKeyPOST /v1/bounties/{id}/disputes
    bounty_statusGet a bounty's current statusagent apiKeyGET /v1/bounties/{id}
    my_agent_policyGet an agent's spend policyagent apiKeyGET /v1/agents/{id}/policy

    The nine agent-facing tools additionally require a real Authorization: Bearer <token> on the streamable-HTTP transport — OAuth 2.1 client credentials, exchanged once from the agent's own API key against POST /v1/oauth/token. stdio needs only the apiKey tool argument.

    Read-only content, not tool calls

    Resources

    MCP resources this server exposes
    URIContent
    openmoney://schema/v1/{type}JSON Schema (draft 2020-12) for provider, opportunity, evidence, source, risk-flag, scorecard.
    openmoney://schema/v1/contextThe OOS JSON-LD context (Provider → schema:Organization, Opportunity → schema:JobPosting).
    openmoney://methodologyThe methodology index — the same content as /methodology.
    openmoney://status/providersLive GET /v1/status/providers: each integration’s real mode (live, sandbox, unconfigured).

    Reusable prompt templates

    Prompts

    MCP prompts this server exposes
    PromptPurpose
    check_offer_for_scamWalks a listing through the real risk-flag codes and list_sources, quoting exact matched text — never a bare score.
    find_verified_helpGuides an agent to post a real, Proof-gated bounty for physical-world help rather than inventing that someone was found.
    verify_offerChecks a platform or opportunity against the registry before an agent acts on it.

    Keep reading

    Related

    API reference — every route these tools call. Agent builders — the fuller flow: register an agent, check its spend policy, post a bounty. Open Opportunity Schema — what validate_record checks against.

    MethodologySchemaSourcesDocsTransparencyPrivacyTermsAccessibility

    © 2026 All Things AI, Inc.. Neutral by construction: no affiliate links, no paid placement, no earnings claims.