# Promise (remote · mcp.usepromise.ai)

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

- Trust score: 67/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-29

## Components

- remote · `mcp.usepromise.ai`: 67/100 (this document), [markdown](https://verifymcp.io/servers/ai-usepromise-promise/mcp.md), [page](https://verifymcp.io/servers/ai-usepromise-promise/mcp)

## Channel facts

- Endpoint: `https://mcp.usepromise.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-29.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 62/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 668 tokens (~60/item across 11 items; 11 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 72/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 15% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

### How do I install the Promise MCP server?

Promise is a hosted endpoint at https://mcp.usepromise.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

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

### Cursor

```json
{
  "mcpServers": {
    "ai-usepromise-promise": {
      "url": "https://mcp.usepromise.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-usepromise-promise": {
      "type": "http",
      "url": "https://mcp.usepromise.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-usepromise-promise]
url = "https://mcp.usepromise.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-usepromise-promise": {
      "type": "remote",
      "url": "https://mcp.usepromise.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-usepromise-promise --url 'https://mcp.usepromise.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-usepromise-promise:
    url: "https://mcp.usepromise.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-usepromise-promise": {
      "Transport": "http",
      "Url": "https://mcp.usepromise.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-usepromise-promise -t streamable-http -u 'https://mcp.usepromise.ai/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-28 (score 67, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-27 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-25 (score 66, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-23 (score 65, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-09-22 (score 64)

First indexed and scored.

## MCP tools (11)

### `connect_promise` (~112 tokens)

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.

Input parameters:

- `clientName` (string): Name of the agent or MCP client requesting access.
- `intent` (string): Signup intent to preserve in Promise attribution.
- `returnUrl` (string): HTTPS URL the user can return to after Promise authorization.
- `scopes` (array)
- `state` (string): Opaque agent state returned unchanged after authorization.

### `get_today` (~38 tokens)

Get Today

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

Input parameters:

- `horizonDays` (integer)

### `list_commitments` (~54 tokens)

List commitments

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

Input parameters:

- `category` (string)
- `limit` (integer)
- `scope` (string)

### `get_commitment` (~44 tokens)

Get commitment

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

Input parameters:

- `id` (string, required)

### `get_commitment_evidence` (~42 tokens)

Get commitment evidence

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

Input parameters:

- `id` (string, required)

### `get_person_context` (~66 tokens)

Get person context

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

Input parameters:

- `contactId` (string)
- `limit` (integer)
- `query` (string): Name or email search when contactId is unknown.

### `search_memory` (~44 tokens)

Search memory

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

Input parameters:

- `limit` (integer)
- `query` (string, required)

### `capture_note` (~85 tokens)

Capture note

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

Input parameters:

- `contactId` (string)
- `dueAt` (string)
- `kind` (string)
- `personName` (string)
- `requestId` (string)
- `title` (string)
- `transcript` (string, required)

### `create_follow_up` (~76 tokens)

Create follow-up

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

Input parameters:

- `contactId` (string)
- `dueAt` (string)
- `personName` (string)
- `requestId` (string)
- `title` (string, required)
- `transcript` (string)

### `mark_resolved` (~41 tokens)

Mark resolved

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

Input parameters:

- `id` (string, required)

### `draft_follow_up` (~66 tokens)

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.

Input parameters:

- `commitmentId` (string)
- `context` (string)
- `goal` (string)
- `personName` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-usepromise-promise/mcp#diagnostics

## Score history

- 2026-09-29: 67
- 2026-09-28: 67
- 2026-09-27: 67
- 2026-09-26: 66
- 2026-09-25: 66
- 2026-09-24: 65
- 2026-09-23: 65
- 2026-09-22: 64

## Common questions

### What is the Promise MCP server?

Promise is an MCP server listed in the public MCP registry as ai.usepromise/promise. Evidence-backed follow-through memory for what you owe, await, and need to remember. This page covers its hosted endpoint (https://mcp.usepromise.ai/mcp).

### Is the Promise MCP server safe to use?

Promise scores 67 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Promise MCP server expose?

Promise exposes 11 tools: connect_promise, get_today, list_commitments, get_commitment, get_commitment_evidence, and 6 more. Their descriptions and schemas cost roughly 668 tokens of context every time the server is loaded.

### Does the Promise MCP server require authentication?

No. We connected to Promise without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Promise MCP server still maintained?

Promise is still listed as active in the MCP registry. We last reached this channel on 29 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.usepromise.ai/mcp
- Repository: https://github.com/UsePromise/promise-mcp
- Website: https://www.usepromise.ai/mcp
- Changelog RSS feed: https://verifymcp.io/servers/ai-usepromise-promise/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-usepromise-promise/mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-usepromise-promise/mcp