{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_efv9n6u3pn84","handle":"promise","url":"https://wellknown.network/agents/promise","links":{"self":"https://wellknown.network/agents/promise/record.json","html":"https://wellknown.network/agents/promise","markdown":"https://wellknown.network/agents/promise/record.md","api":"https://wellknown.network/api/v1/agents/promise","status":"https://wellknown.network/api/v1/agents/promise/status","claim":"https://wellknown.network/agents/promise/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/promise/claim.json","badge":"https://wellknown.network/agents/promise/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/promise/history","tools":"https://wellknown.network/api/v1/agents/promise/tools"},"ard":{"identifier":"urn:air:mcp.usepromise.ai:server:promise","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"Promise","summary":"Evidence-backed follow-through memory for what you owe, await, and need to remember.","description":"Evidence-backed follow-through memory for what you owe, await, and need to remember.","publisher":{"name":"ai.usepromise","url":null},"homepage":"https://www.usepromise.ai/mcp","repository":"https://github.com/UsePromise/promise-mcp","version":"0.1.0","license":null,"protocols":["mcp"],"tags":[],"pricing":null,"endpoints":[{"url":"https://mcp.usepromise.ai/mcp","type":"mcp_streamable_http","auth":null,"probeable":true}],"skills":null,"tools":null,"extra":{"updatedAt":"2026-09-22T13:15:09.981869Z","publishedAt":"2026-09-22T13:15:09.981869Z","registryName":"ai.usepromise/promise"},"attribution":{"kind":"mcp_registry","name":"mcp_registry","repoUrl":"mcp_registry","summary":"mcp_registry","version":"mcp_registry","description":"mcp_registry","homepageUrl":"mcp_registry","publisherName":"mcp_registry"}},"derived":{"capabilities":[{"slug":"knowledge.memory","name":"Agent Memory","confidence":0.885,"provenance":"derived"},{"slug":"security.identity","name":"Identity & Access","confidence":0.583,"provenance":"derived"},{"slug":"security.secrets","name":"Secrets Management","confidence":0.569,"provenance":"derived"},{"slug":"content.writing","name":"Writing & Editing","confidence":0.54,"provenance":"derived"},{"slug":"research.academic","name":"Academic Research","confidence":0.54,"provenance":"derived"}],"categories":["content","knowledge","research","security"],"language":"en"},"observed":{"status":"live","statusReason":"Responded 5h ago.","lastOkAt":"2026-10-10T22:21:13.375Z","lastProbedAt":"2026-10-10T22:21:13.375Z","statusComputedAt":"2026-10-10T22:22:53.497Z","reliability30d":{"probes":63,"successRate":0.9683,"p50Ms":20,"basis":"service","measures":{"availability":"availability","latency":"response time","tools":"tool surface observed","summary":"Checks reached the service itself."},"checks":{"total":63,"ok":61,"authBoundaryOk":0,"serviceOk":61,"note":"Counted from the observation rows for the window, checks of the server only (HTTP, A2A card, MCP initialize). ok = authBoundaryOk + serviceOk. `probes` is the sum of daily rollups and includes registry checks, so it can differ from `total`."}},"latestObservations":[{"at":"2026-10-10T22:21:13.375Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":19,"error":null,"detail":{"tools":[{"name":"connect_promise","description":"Return a Promise signup URL for users who want agent access to follow-up memory. Safety: Never collects provider credentials in the agent. Send the user to Prom"},{"name":"get_today","description":"Return what currently deserves the user's attention. Safety: Return concise items and links back to Promise for sensitive action."},{"name":"list_commitments","description":"List what the user owes and what the user is waiting on. Safety: Do not infer more certainty than Promise returns."},{"name":"get_commitment","description":"Retrieve a structured Promise commitment or waiting-on item. Safety: Prefer structured status, due dates, people, and source links over raw mail."},{"name":"get_commitment_evidence","description":"Show why Promise believes a follow-up or memory exists. Safety: Return source summaries and citations permitted by the platform API."},{"name":"get_person_context","description":"Summarize what matters before the user speaks with someone. Safety: Avoid exposing hidden/private fields unless the platform scopes allow them."},{"name":"search_memory","description":"Search Promise's derived memory with user authorization. Safety: Search derived Promise memory, not raw provider mailboxes."},{"name":"capture_note","description":"Let a user tell Promise something to remember. Safety: Echo what Promise understood and require review when the platform requests it."},{"name":"create_follow_up","description":"Create a future follow-up from explicit user intent. Safety: Only create follow-ups from explicit user instructions."},{"name":"mark_resolved","description":"Tell Promise that a commitment or waiting-on item is complete. Safety: Confirm destructive or irreversible status changes in the agent UI."},{"name":"draft_follow_up","description":"Draft a follow-up message without sending it. Safety: Do not send email in v1. Return a draft and Promise confirmation link."}],"toolCount":11,"toolsHash":"09f7b0cfbeba446973e222a3934d155dc2bb39b8a5466f32beb2bdf65d47b6a4","serverName":"Promise MCP","capabilities":["tools"],"serverVersion":"0.1.0","protocolVersion":"2025-03-26"}},{"at":"2026-10-10T15:32:06.534Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":19,"error":null,"detail":{"tools":[{"name":"connect_promise","description":"Return a Promise signup URL for users who want agent access to follow-up memory. Safety: Never collects provider credentials in the agent. Send the user to Prom"},{"name":"get_today","description":"Return what currently deserves the user's attention. Safety: Return concise items and links back to Promise for sensitive action."},{"name":"list_commitments","description":"List what the user owes and what the user is waiting on. Safety: Do not infer more certainty than Promise returns."},{"name":"get_commitment","description":"Retrieve a structured Promise commitment or waiting-on item. Safety: Prefer structured status, due dates, people, and source links over raw mail."},{"name":"get_commitment_evidence","description":"Show why Promise believes a follow-up or memory exists. Safety: Return source summaries and citations permitted by the platform API."},{"name":"get_person_context","description":"Summarize what matters before the user speaks with someone. Safety: Avoid exposing hidden/private fields unless the platform scopes allow them."},{"name":"search_memory","description":"Search Promise's derived memory with user authorization. Safety: Search derived Promise memory, not raw provider mailboxes."},{"name":"capture_note","description":"Let a user tell Promise something to remember. Safety: Echo what Promise understood and require review when the platform requests it."},{"name":"create_follow_up","description":"Create a future follow-up from explicit user intent. Safety: Only create follow-ups from explicit user instructions."},{"name":"mark_resolved","description":"Tell Promise that a commitment or waiting-on item is complete. Safety: Confirm destructive or irreversible status changes in the agent UI."},{"name":"draft_follow_up","description":"Draft a follow-up message without sending it. Safety: Do not send email in v1. Return a draft and Promise confirmation link."}],"toolCount":11,"toolsHash":"09f7b0cfbeba446973e222a3934d155dc2bb39b8a5466f32beb2bdf65d47b6a4","serverName":"Promise MCP","capabilities":["tools"],"serverVersion":"0.1.0","protocolVersion":"2025-03-26"}},{"at":"2026-10-09T14:31:53.629Z","kind":"mcp_initialize","ok":false,"httpStatus":null,"latencyMs":null,"error":"timeout","detail":null},{"at":"2026-10-09T01:24:52.927Z","kind":"mcp_initialize","ok":false,"httpStatus":null,"latencyMs":null,"error":"timeout","detail":null},{"at":"2026-10-08T18:26:28.635Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":21,"error":null,"detail":{"tools":[{"name":"connect_promise","description":"Return a Promise signup URL for users who want agent access to follow-up memory. Safety: Never collects provider credentials in the agent. Send the user to Prom"},{"name":"get_today","description":"Return what currently deserves the user's attention. Safety: Return concise items and links back to Promise for sensitive action."},{"name":"list_commitments","description":"List what the user owes and what the user is waiting on. Safety: Do not infer more certainty than Promise returns."},{"name":"get_commitment","description":"Retrieve a structured Promise commitment or waiting-on item. Safety: Prefer structured status, due dates, people, and source links over raw mail."},{"name":"get_commitment_evidence","description":"Show why Promise believes a follow-up or memory exists. Safety: Return source summaries and citations permitted by the platform API."},{"name":"get_person_context","description":"Summarize what matters before the user speaks with someone. Safety: Avoid exposing hidden/private fields unless the platform scopes allow them."},{"name":"search_memory","description":"Search Promise's derived memory with user authorization. Safety: Search derived Promise memory, not raw provider mailboxes."},{"name":"capture_note","description":"Let a user tell Promise something to remember. Safety: Echo what Promise understood and require review when the platform requests it."},{"name":"create_follow_up","description":"Create a future follow-up from explicit user intent. Safety: Only create follow-ups from explicit user instructions."},{"name":"mark_resolved","description":"Tell Promise that a commitment or waiting-on item is complete. Safety: Confirm destructive or irreversible status changes in the agent UI."},{"name":"draft_follow_up","description":"Draft a follow-up message without sending it. Safety: Do not send email in v1. Return a draft and Promise confirmation link."}],"toolCount":11,"toolsHash":"09f7b0cfbeba446973e222a3934d155dc2bb39b8a5466f32beb2bdf65d47b6a4","serverName":"Promise MCP","capabilities":["tools"],"serverVersion":"0.1.0","protocolVersion":"2025-03-26"}},{"at":"2026-10-08T11:22:48.329Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":20,"error":null,"detail":{"tools":[{"name":"connect_promise","description":"Return a Promise signup URL for users who want agent access to follow-up memory. Safety: Never collects provider credentials in the agent. Send the user to Prom"},{"name":"get_today","description":"Return what currently deserves the user's attention. Safety: Return concise items and links back to Promise for sensitive action."},{"name":"list_commitments","description":"List what the user owes and what the user is waiting on. Safety: Do not infer more certainty than Promise returns."},{"name":"get_commitment","description":"Retrieve a structured Promise commitment or waiting-on item. Safety: Prefer structured status, due dates, people, and source links over raw mail."},{"name":"get_commitment_evidence","description":"Show why Promise believes a follow-up or memory exists. Safety: Return source summaries and citations permitted by the platform API."},{"name":"get_person_context","description":"Summarize what matters before the user speaks with someone. Safety: Avoid exposing hidden/private fields unless the platform scopes allow them."},{"name":"search_memory","description":"Search Promise's derived memory with user authorization. Safety: Search derived Promise memory, not raw provider mailboxes."},{"name":"capture_note","description":"Let a user tell Promise something to remember. Safety: Echo what Promise understood and require review when the platform requests it."},{"name":"create_follow_up","description":"Create a future follow-up from explicit user intent. Safety: Only create follow-ups from explicit user instructions."},{"name":"mark_resolved","description":"Tell Promise that a commitment or waiting-on item is complete. Safety: Confirm destructive or irreversible status changes in the agent UI."},{"name":"draft_follow_up","description":"Draft a follow-up message without sending it. Safety: Do not send email in v1. Return a draft and Promise confirmation link."}],"toolCount":11,"toolsHash":"09f7b0cfbeba446973e222a3934d155dc2bb39b8a5466f32beb2bdf65d47b6a4","serverName":"Promise MCP","capabilities":["tools"],"serverVersion":"0.1.0","protocolVersion":"2025-03-26"}},{"at":"2026-10-08T04:25:58.244Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":19,"error":null,"detail":{"tools":[{"name":"connect_promise","description":"Return a Promise signup URL for users who want agent access to follow-up memory. Safety: Never collects provider credentials in the agent. Send the user to Prom"},{"name":"get_today","description":"Return what currently deserves the user's attention. Safety: Return concise items and links back to Promise for sensitive action."},{"name":"list_commitments","description":"List what the user owes and what the user is waiting on. Safety: Do not infer more certainty than Promise returns."},{"name":"get_commitment","description":"Retrieve a structured Promise commitment or waiting-on item. Safety: Prefer structured status, due dates, people, and source links over raw mail."},{"name":"get_commitment_evidence","description":"Show why Promise believes a follow-up or memory exists. Safety: Return source summaries and citations permitted by the platform API."},{"name":"get_person_context","description":"Summarize what matters before the user speaks with someone. Safety: Avoid exposing hidden/private fields unless the platform scopes allow them."},{"name":"search_memory","description":"Search Promise's derived memory with user authorization. Safety: Search derived Promise memory, not raw provider mailboxes."},{"name":"capture_note","description":"Let a user tell Promise something to remember. Safety: Echo what Promise understood and require review when the platform requests it."},{"name":"create_follow_up","description":"Create a future follow-up from explicit user intent. Safety: Only create follow-ups from explicit user instructions."},{"name":"mark_resolved","description":"Tell Promise that a commitment or waiting-on item is complete. Safety: Confirm destructive or irreversible status changes in the agent UI."},{"name":"draft_follow_up","description":"Draft a follow-up message without sending it. Safety: Do not send email in v1. Return a draft and Promise confirmation link."}],"toolCount":11,"toolsHash":"09f7b0cfbeba446973e222a3934d155dc2bb39b8a5466f32beb2bdf65d47b6a4","serverName":"Promise MCP","capabilities":["tools"],"serverVersion":"0.1.0","protocolVersion":"2025-03-26"}},{"at":"2026-10-07T21:29:12.463Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":20,"error":null,"detail":{"tools":[{"name":"connect_promise","description":"Return a Promise signup URL for users who want agent access to follow-up memory. Safety: Never collects provider credentials in the agent. Send the user to Prom"},{"name":"get_today","description":"Return what currently deserves the user's attention. Safety: Return concise items and links back to Promise for sensitive action."},{"name":"list_commitments","description":"List what the user owes and what the user is waiting on. Safety: Do not infer more certainty than Promise returns."},{"name":"get_commitment","description":"Retrieve a structured Promise commitment or waiting-on item. Safety: Prefer structured status, due dates, people, and source links over raw mail."},{"name":"get_commitment_evidence","description":"Show why Promise believes a follow-up or memory exists. Safety: Return source summaries and citations permitted by the platform API."},{"name":"get_person_context","description":"Summarize what matters before the user speaks with someone. Safety: Avoid exposing hidden/private fields unless the platform scopes allow them."},{"name":"search_memory","description":"Search Promise's derived memory with user authorization. Safety: Search derived Promise memory, not raw provider mailboxes."},{"name":"capture_note","description":"Let a user tell Promise something to remember. Safety: Echo what Promise understood and require review when the platform requests it."},{"name":"create_follow_up","description":"Create a future follow-up from explicit user intent. Safety: Only create follow-ups from explicit user instructions."},{"name":"mark_resolved","description":"Tell Promise that a commitment or waiting-on item is complete. Safety: Confirm destructive or irreversible status changes in the agent UI."},{"name":"draft_follow_up","description":"Draft a follow-up message without sending it. Safety: Do not send email in v1. Return a draft and Promise confirmation link."}],"toolCount":11,"toolsHash":"09f7b0cfbeba446973e222a3934d155dc2bb39b8a5466f32beb2bdf65d47b6a4","serverName":"Promise MCP","capabilities":["tools"],"serverVersion":"0.1.0","protocolVersion":"2025-03-26"}},{"at":"2026-10-07T15:32:15.107Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":18,"error":null,"detail":{"tools":[{"name":"connect_promise","description":"Return a Promise signup URL for users who want agent access to follow-up memory. Safety: Never collects provider credentials in the agent. Send the user to Prom"},{"name":"get_today","description":"Return what currently deserves the user's attention. Safety: Return concise items and links back to Promise for sensitive action."},{"name":"list_commitments","description":"List what the user owes and what the user is waiting on. Safety: Do not infer more certainty than Promise returns."},{"name":"get_commitment","description":"Retrieve a structured Promise commitment or waiting-on item. Safety: Prefer structured status, due dates, people, and source links over raw mail."},{"name":"get_commitment_evidence","description":"Show why Promise believes a follow-up or memory exists. Safety: Return source summaries and citations permitted by the platform API."},{"name":"get_person_context","description":"Summarize what matters before the user speaks with someone. Safety: Avoid exposing hidden/private fields unless the platform scopes allow them."},{"name":"search_memory","description":"Search Promise's derived memory with user authorization. Safety: Search derived Promise memory, not raw provider mailboxes."},{"name":"capture_note","description":"Let a user tell Promise something to remember. Safety: Echo what Promise understood and require review when the platform requests it."},{"name":"create_follow_up","description":"Create a future follow-up from explicit user intent. Safety: Only create follow-ups from explicit user instructions."},{"name":"mark_resolved","description":"Tell Promise that a commitment or waiting-on item is complete. Safety: Confirm destructive or irreversible status changes in the agent UI."},{"name":"draft_follow_up","description":"Draft a follow-up message without sending it. Safety: Do not send email in v1. Return a draft and Promise confirmation link."}],"toolCount":11,"toolsHash":"09f7b0cfbeba446973e222a3934d155dc2bb39b8a5466f32beb2bdf65d47b6a4","serverName":"Promise MCP","capabilities":["tools"],"serverVersion":"0.1.0","protocolVersion":"2025-03-26"}},{"at":"2026-10-07T09:28:14.978Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":29,"error":null,"detail":{"tools":[{"name":"connect_promise","description":"Return a Promise signup URL for users who want agent access to follow-up memory. Safety: Never collects provider credentials in the agent. Send the user to Prom"},{"name":"get_today","description":"Return what currently deserves the user's attention. Safety: Return concise items and links back to Promise for sensitive action."},{"name":"list_commitments","description":"List what the user owes and what the user is waiting on. Safety: Do not infer more certainty than Promise returns."},{"name":"get_commitment","description":"Retrieve a structured Promise commitment or waiting-on item. Safety: Prefer structured status, due dates, people, and source links over raw mail."},{"name":"get_commitment_evidence","description":"Show why Promise believes a follow-up or memory exists. Safety: Return source summaries and citations permitted by the platform API."},{"name":"get_person_context","description":"Summarize what matters before the user speaks with someone. Safety: Avoid exposing hidden/private fields unless the platform scopes allow them."},{"name":"search_memory","description":"Search Promise's derived memory with user authorization. Safety: Search derived Promise memory, not raw provider mailboxes."},{"name":"capture_note","description":"Let a user tell Promise something to remember. Safety: Echo what Promise understood and require review when the platform requests it."},{"name":"create_follow_up","description":"Create a future follow-up from explicit user intent. Safety: Only create follow-ups from explicit user instructions."},{"name":"mark_resolved","description":"Tell Promise that a commitment or waiting-on item is complete. Safety: Confirm destructive or irreversible status changes in the agent UI."},{"name":"draft_follow_up","description":"Draft a follow-up message without sending it. Safety: Do not send email in v1. Return a draft and Promise confirmation link."}],"toolCount":11,"toolsHash":"09f7b0cfbeba446973e222a3934d155dc2bb39b8a5466f32beb2bdf65d47b6a4","serverName":"Promise MCP","capabilities":["tools"],"serverVersion":"0.1.0","protocolVersion":"2025-03-26"}}],"tools":[{"name":"connect_promise","description":"Return a Promise signup URL for users who want agent access to follow-up memory. Safety: Never collects provider credentials in the agent. Send the user to Prom"},{"name":"get_today","description":"Return what currently deserves the user's attention. Safety: Return concise items and links back to Promise for sensitive action."},{"name":"list_commitments","description":"List what the user owes and what the user is waiting on. Safety: Do not infer more certainty than Promise returns."},{"name":"get_commitment","description":"Retrieve a structured Promise commitment or waiting-on item. Safety: Prefer structured status, due dates, people, and source links over raw mail."},{"name":"get_commitment_evidence","description":"Show why Promise believes a follow-up or memory exists. Safety: Return source summaries and citations permitted by the platform API."},{"name":"get_person_context","description":"Summarize what matters before the user speaks with someone. Safety: Avoid exposing hidden/private fields unless the platform scopes allow them."},{"name":"search_memory","description":"Search Promise's derived memory with user authorization. Safety: Search derived Promise memory, not raw provider mailboxes."},{"name":"capture_note","description":"Let a user tell Promise something to remember. Safety: Echo what Promise understood and require review when the platform requests it."},{"name":"create_follow_up","description":"Create a future follow-up from explicit user intent. Safety: Only create follow-ups from explicit user instructions."},{"name":"mark_resolved","description":"Tell Promise that a commitment or waiting-on item is complete. Safety: Confirm destructive or irreversible status changes in the agent UI."},{"name":"draft_follow_up","description":"Draft a follow-up message without sending it. Safety: Do not send email in v1. Return a draft and Promise confirmation link."}],"package":null,"toolSurface":{"id":"ts_z3xy9edsvcnp","endpointId":"ep_5g2sqepytkpy","hash":"09f7b0cfbeba446973e222a3934d155dc2bb39b8a5466f32beb2bdf65d47b6a4","toolCount":11,"serverName":"Promise MCP","serverVersion":"0.1.0","protocolVersion":"2025-03-26","firstSeenAt":"2026-09-22T19:29:28.478Z","lastSeenAt":"2026-10-10T22:21:13.377Z","observations":61,"toolNames":["connect_promise","get_today","list_commitments","get_commitment","get_commitment_evidence","get_person_context","search_memory","capture_note","create_follow_up","mark_resolved","draft_follow_up"],"distinctSurfaces":1},"endpointFacts":[{"id":"ep_5g2sqepytkpy","url":"https://mcp.usepromise.ai/mcp","type":"mcp_streamable_http","factsCheckedAt":"2026-10-08T18:26:28.636Z","auth":{"observedAt":"2026-10-08T18:26:28.656Z","authRequired":false,"scheme":null,"resourceMetadata":null,"authorizationServer":null,"conformance":{"dpop":false,"rfc8414":false,"rfc9728":false,"pkceS256":false,"clientIdMetadataDocument":false,"dynamicClientRegistration":false}},"tls":{"observedAt":"2026-10-08T18:26:28.697Z","protocol":"TLSv1.3","chainValid":true,"chainError":null,"hostMatches":true,"subject":"mcp.usepromise.ai","issuer":{"commonName":"GeoTrust TLS RSA CA G1","organization":"DigiCert Inc"},"validFrom":"2026-09-22T00:00:00.000Z","validTo":"2027-03-22T23:59:59.000Z","daysToExpiry":162,"sanCount":1,"fingerprint256":"CC:84:76:0C:8B:9B:E6:7A:44:F6:17:8A:C1:6A:E3:E7:A0:BC:86:7D:EE:B3:50:47:DE:D8:85:82:7C:AE:40:FD"}}]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"mcp_registry","key":"ai.usepromise/promise","url":"https://registry.modelcontextprotocol.io/v0/servers/ai.usepromise%2Fpromise","firstSeenAt":"2026-09-22T19:21:15.295Z","fetchedAt":"2026-10-09T00:19:24.743Z","normalizedAt":"2026-10-09T00:19:24.743Z"}]},"firstSeenAt":"2026-09-22T19:21:15.295Z","updatedAt":"2026-10-10T22:23:39.420Z"}