Promise MCP

MCP serverEverything else

Evidence-backed follow-through memory for what you owe, await, and need to remember.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use Promise MCP

Install Promise MCP

The server’s own address, for the clients that take one directly. Or connect ahel onceand every client you use reads it from one address, with the account kept on ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http promise-mcp 'https://mcp.usepromise.ai/mcp'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://mcp.usepromise.ai/mcp

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=promise-mcp&config=eyJ1cmwiOiJodHRwczovL21jcC51c2Vwcm9taXNlLmFpL21jcCJ9

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://mcp.usepromise.ai/mcp

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add promise-mcp --url 'https://mcp.usepromise.ai/mcp'

    Run it once, then sign in with codex mcp login promise-mcp if the server asks for an account.

From the project's README

As published by UsePromise/promise-mcp in README.md.

Agent-facing MCP server/tools for Promise. The hosted HTTP endpoint is POST /mcp; GET /healthz is available for runtime checks.

This repository is intentionally separate from the Promise platform. It should compose the platform API into agent-friendly tools, not implement canonical backend business logic.

Boundary

  • Call the Promise platform API for data access and mutations.
  • Do not access Postgres, Redis, queues, provider tokens, or migrations directly.
  • Keep authorization, provenance, retention, provider behavior, and canonical domain rules in the platform.
  • Consume explicit platform contracts instead of duplicating procedure or capability names by hand.

Initial MCP tool surface:

  • 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

connect_promise and unauthenticated tool results are intentionally part of the product. MCP should help users discover and connect Promise when an agent needs follow-up memory that Promise can provide.

Unauthenticated tool results include a scoped authorizationUrl that sends the user to https://app.usepromise.ai/start?source=mcp..., preserves agent attribution, and uses a relative /mcp/authorize callback inside Promise before any return to an agent URL.

Development

npm install
npm run build
npm run smoke
npm run tools
npm run start

Example MCP call:

curl -sS http://localhost:3000/mcp \
  -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

Protected tools return a structured promise_auth_required result when no Bearer token is present. After the user authorizes /mcp/authorize, Promise returns a short-lived one-time code to the agent callback. The agent exchanges that code at /api/mcp/token for a scoped opaque pmcp_... bearer token. Bearer tool calls are proxied to the Promise platform API, which enforces the grant's scopes. mark_resolved and draft_follow_up intentionally deep-link to Promise for user review rather than sending or mutating mail directly.

See docs/ACQUISITION.md for signup flow guidance, docs/SECURITY.md for the MCP safety boundary, and docs/DEPLOYMENT.md for container/runtime details.

Advanced
Delivery
promise MCP server → your ahel gateway (mcp.ahel.ai) → every connected AI client.
Catalog kind
mcp-server
Gateway key
ai-usepromise-promise
Source
github.com/UsePromise/promise-mcp
Hosted endpoint
https://mcp.usepromise.ai/mcp