_ registry / mcp streamable-http · checked 1h ago

Promise MCP

https://mcp.usepromise.ai

Registry code: 2b27c1a02ea2b73e

api record

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

from a public catalogue that lists it, not from the operator

endpoint
https://mcp.usepromise.ai/mcp
protocol
streamable-http ·2025-03-26
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is Promise MCP live?
No — it has stopped answering the hub's checks (checked 1h ago). It answered 93% of checks over the last 30 days.
Is Promise MCP free to use?
Yes — the hub reached it with no key and no payment.
What tools does Promise MCP have?
11 tools: capture_note, create_follow_up, draft_follow_up, mark_resolved, search_memory, get_commitment, get_today, get_commitment_evidence, ….
Is Promise MCP safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
down
uptime, 30 days
93%

90 days 94.9%· all time 94.9%

latency
226ms

last good check

priced tools
0

of 11 tools

_ answered our checks, 90 days 433 checks · signed record
  • degraded → down· timeout after 20000ms
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
  • down → live
_ what it is for
topic
productivity & business tasks & projects
used for
  • track what the user owes and is waiting on
  • create a follow-up reminder
  • capture a note to remember
  • prepare context before meeting a person
  • draft a follow-up message
takes → gives
text → text, data
tools
8 reads3 changes data
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 11 tools
7 open 4 never probed 7 of 11 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • search_memory reads open 20h ago

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

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 20,
      "minimum": 1
    },
    "query": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 18 lines
  • get_commitment reads open 29h ago

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

    mcp-tool

    {
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "format": "uuid"
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • get_today reads open 39h ago

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

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "horizonDays": {
      "type": "integer",
      "default": 7,
      "maximum": 30,
      "minimum": 0
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • get_commitment_evidence reads open 29h ago

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

    mcp-tool

    {
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "format": "uuid"
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • list_commitments reads open 29h ago

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

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 50,
      "minimum": 1
    },
    "scope": {
      "enum": [
        "active",
        "snoozed",
        "history"
      ],
      "type": "string",
      "default": "active"
    },
    "category": {
      "enum": [
        "all",
        "waitingOnMe",
        "waitingOnThem",
        "dueSoon",
        "overdue"
      ],
      "type": "string",
      "default": "all"
    }
  },
  "additionalProperties": false
}
    arguments 33 lines
  • connect_promise reads open 39h ago

    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.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "state": {
      "type": "string",
      "description": "Opaque agent state returned unchanged after authorization."
    },
    "intent": {
      "type": "string",
      "description": "Signup intent to preserve in Promise attribution."
    },
    "scopes": {
      "type": "array",
      "items": {
        "enum": [
          "promise.memory.read",
          "promise.evidence.read",
          "promise.capture.write",
          "promise.followup.write",
          "promise.draft.write"
        ],
        "type": "string"
      }
    },
    "returnUrl": {
      "type": "string",
      "description": "HTTPS URL the user can return to after Promise authorization."
    },
    "clientName": {
      "type": "string",
      "description": "Name of the agent or MCP client requesting access."
    }
  },
  "additionalProperties": false
}
    arguments 36 lines
  • get_person_context reads open 39h ago

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

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 5,
      "maximum": 10,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "description": "Name or email search when contactId is unknown."
    },
    "contactId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "additionalProperties": false
}
    arguments 21 lines
  • capture_note changes data unknown never probed

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

    mcp-tool

    {
  "type": "object",
  "required": [
    "transcript"
  ],
  "properties": {
    "kind": {
      "enum": [
        "task",
        "follow_up",
        "remember"
      ],
      "type": "string",
      "default": "remember"
    },
    "dueAt": {
      "type": "string",
      "format": "date-time"
    },
    "title": {
      "type": "string"
    },
    "contactId": {
      "type": "string",
      "format": "uuid"
    },
    "requestId": {
      "type": "string",
      "format": "uuid"
    },
    "personName": {
      "type": "string"
    },
    "transcript": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 39 lines
  • create_follow_up changes data unknown never probed

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

    mcp-tool

    {
  "type": "object",
  "required": [
    "title"
  ],
  "properties": {
    "dueAt": {
      "type": "string",
      "format": "date-time"
    },
    "title": {
      "type": "string"
    },
    "contactId": {
      "type": "string",
      "format": "uuid"
    },
    "requestId": {
      "type": "string",
      "format": "uuid"
    },
    "personName": {
      "type": "string"
    },
    "transcript": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 30 lines
  • draft_follow_up reads unknown never probed

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

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "goal": {
      "type": "string"
    },
    "context": {
      "type": "string"
    },
    "personName": {
      "type": "string"
    },
    "commitmentId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "additionalProperties": false
}
    arguments 20 lines
  • mark_resolved changes data unknown never probed

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

    mcp-tool

    {
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "format": "uuid"
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 2b27c1a02ea2b73e.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/2b27c1a02ea2b73e/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/2b27c1a02ea2b73e/badge.svg)](https://brick.blue/agent/2b27c1a02ea2b73e?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.