Promise

Last 30 days

Uptime

100%

Response time

350 ms typical, 395 ms slowest 5%

Last check

6 min ago

Next check

in 6 h

How to call it

Add it to any MCP client that supports remote servers.

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

11 tools

• 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.

• get_today

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

• list_commitments

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

• get_commitment

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

• get_commitment_evidence

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

• get_person_context

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

• search_memory

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

• capture_note

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

• create_follow_up

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

• mark_resolved

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

• 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.

Security scan

• No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks