// SCAN REPORT

Passoff

5 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 30 Jun 2026

1 can modify or destroy data

4 read-only

5 tools total

Community server · catalogue entry verified 30/06/2026

How to control Passoff ↓

TOOL MAP

What Passoff exposes to your agents

Read (4) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Passoff tools

Write · Medium passoff_create This tool creates and stores new data (a handoff document) in a reversible manner.

1 of Passoff's 5 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Passoff

PolicyLayer is an MCP gateway — it sits between your AI agents and Passoff, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "passoff_create": {
    "limits": [
      {
        "counter": "passoff_create_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "passoff_list": {
    "limits": [
      {
        "counter": "passoff_list_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Passoff — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON PASSOFF →

Instant setup, no code required.

FULL CATALOGUE

All 5 Passoff tools

WRITE 1 tools

Write passoff_create Create a context handoff for another AI agent. Use this when the user types /passoff, asks to hand off, pass o

READ 4 tools

Read passoff_list List recent handoffs in the current project (metadata only, no body). Useful for discovery before loading a sp Read passoff_load Load a previously created handoff. Use when the user asks to load a handoff, pick up where another AI left off Read passoff_search Full-text search across handoffs in the current project. Returns ranked hits with snippets. Read passoff_thread Show the lineage chain of a handoff — ancestors, descendants, or both. Useful for tracing how a decision evolv

FAQ

Questions about Passoff

How do I prevent bulk modifications through Passoff? +

The Passoff server has 1 write tools including passoff_create. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Passoff.

How many tools does the Passoff MCP server expose? +

5 tools across 2 categories: Read, Write. 4 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Passoff? +

Register the Passoff MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Passoff tool call.

Deterministic rules across all 5 Passoff tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PASSOFF →

Instant setup, no code required.

5 Passoff tools catalogued and risk-classified — across an index of 43,000+ MCP servers.