summon_human

Part of the Mcp Human Agents MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

// WHEN AI AGENTS USE THIS TOOL

AI agents call summon_human to perform operations in Mcp Human Agents. While the risk category is not fully classified, applying a rate limit gives you visibility into how often the tool is called and prevents unexpected bursts of activity from autonomous agents.

// WHY ENFORCE A POLICY ON SUMMON_HUMAN

Applying a policy to summon_human gives you an audit trail of every call an AI agent makes. Even for low-risk tools, visibility into agent behaviour helps you debug issues, optimise workflows, and maintain compliance with your organisation's security requirements.

// RECOMMENDED POLICY

Apply a rate limit to control usage and monitor for unexpected behaviour.

mcp-human-agents.yaml

tools:
  summon_human:
    rules:
      - action: allow
        rate_limit:
          max: 60
          window: 60

See the full Mcp Human Agents policy for all 5 tools.

// DETAILS

Tool Name summon_human

Category Other

MCP Server Mcp Human Agents MCP Server

Risk Level Low

// MORE MCP HUMAN AGENTS TOOLS

Destructive dismiss_human Execute toggle_autoplans Write message_human Read list_humans

// WHAT CAN GO WRONG

Agents calling other-class tools like summon_human have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

// OTHER OTHER TOOLS ACROSS MCP SERVERS

Other tools in the Other risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.

Ai Agent Incremental mode Ai Agent Path isolation Zype Com Analytics Zype Com Categories Zype Com Monetization Zype Com Playlists

// RELATED READING

// FAQ

What does the summon_human tool do? +

BEHAVIOR (auto-plans=false): Only call this tool when the user EXPLICITLY asks to summon a human. Do NOT call it proactively — no plans, no suggestions, no 'just in case'. Summon a human contractor. pair-terminal = join your tmate session (default). pair-desktop = share your screen via WebRTC. sandbox-terminal = own terminal in a worktree. sandbox-desktop = own desktop container.. It is categorised as a Other tool in the Mcp Human Agents MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on summon_human? +

Add a rule in your Intercept YAML policy under the tools section for summon_human. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Mcp Human Agents MCP server.

What risk level is summon_human? +

summon_human is a Other tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit summon_human? +

Yes. Add a rate_limit block to the summon_human rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block summon_human completely? +

Set action: deny in the Intercept policy for summon_human. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides summon_human? +

summon_human is provided by the Mcp Human Agents MCP server (@bazaar.ai/mcp-human-agents). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

summon_human

Enforce policies on Mcp Human Agents