Promise

ai.usepromisePublished by usepromise.aiOfficial publisherv0.1.0Updated Oct 24, 2026

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

VerifiedStreamable HTTPWeb executableProductivity & WorkflowKnowledge & Memory

Overview

AI-generated overview

Promise is a hosted MCP server that gives an assistant evidence-backed memory of commitments, waiting-on items and notes, with links back to Promise.

What you can do
  • Review today's attention items and list or inspect commitments and waiting-on items
  • Show the evidence and source citations behind a follow-up or memory
  • Summarize context about a person before a conversation and search derived memory
  • Capture notes and create follow-ups from explicit user intent
  • Mark items resolved and draft follow-up messages for review in Promise
  • Return a signup link so users can connect Promise when memory is needed
When to use it
Useful when an assistant should track what the user owes or is waiting on across conversations, recall why a follow-up exists, or prepare context before meeting someone, while keeping sensitive actions in the Promise app.
Requirements
A remote MCP endpoint over streamable HTTP; no local package or environment variables are declared. Protected tools need a Promise account and a scoped bearer token obtained through the Promise authorization flow; without one, tools return an authorization link.
Before you install
Tools read and change the user's follow-up memory: notes, follow-ups and resolution status are written to the Promise platform, and mark_resolved and draft_follow_up deep-link to Promise for user review rather than acting directly. Person context and evidence may expose private fields if scopes allow. Access is granted through a bearer token, so treat it as a secret.

Installation

In SourceWeft

  1. Open Promise in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/ai.usepromise%2Fpromise/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "promise": {
      "type": "http",
      "url": "https://mcp.usepromise.ai/mcp"
    }
  }
}

README

Promise MCP

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

bash
npm installnpm run buildnpm run smokenpm run toolsnpm run start

Example MCP call:

bash
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.

Source: README.md at commit 83133d0

Tools

11

connect_promise

Connect Promise

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 Promise.

ParametersstateintentscopesreturnUrlclientName

get_today

Get Today

Return what currently deserves the user's attention. Safety: Return concise items and links back to Promise for sensitive action.

ParametershorizonDays

list_commitments

List commitments

List what the user owes and what the user is waiting on. Safety: Do not infer more certainty than Promise returns.

Parameterslimitscopecategory

get_commitment

Get commitment

Retrieve a structured Promise commitment or waiting-on item. Safety: Prefer structured status, due dates, people, and source links over raw mail.

Parametersidrequired

get_commitment_evidence

Get commitment evidence

Show why Promise believes a follow-up or memory exists. Safety: Return source summaries and citations permitted by the platform API.

Parametersidrequired

get_person_context

Get person context

Summarize what matters before the user speaks with someone. Safety: Avoid exposing hidden/private fields unless the platform scopes allow them.

ParameterslimitquerycontactId

search_memory

Search memory

Search Promise's derived memory with user authorization. Safety: Search derived Promise memory, not raw provider mailboxes.

Parameterslimitqueryrequired

capture_note

Capture note

Let a user tell Promise something to remember. Safety: Echo what Promise understood and require review when the platform requests it.

ParameterskinddueAttitlecontactIdrequestIdpersonNametranscriptrequired

create_follow_up

Create follow-up

Create a future follow-up from explicit user intent. Safety: Only create follow-ups from explicit user instructions.

ParametersdueAttitlerequiredcontactIdrequestIdpersonNametranscript

mark_resolved

Mark resolved

Tell Promise that a commitment or waiting-on item is complete. Safety: Confirm destructive or irreversible status changes in the agent UI.

Parametersidrequired

draft_follow_up

Draft follow-up

Draft a follow-up message without sending it. Safety: Do not send email in v1. Return a draft and Promise confirmation link.

ParametersgoalcontextpersonNamecommitmentId

Version history

1
  1. v0.1.0LatestSep 22, 2026

Score

90% 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 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.