// MCP TOOL REFERENCE

MCP HUMAN AGENTS TOOLS

5 tools from the Mcp Human Agents MCP Server, categorised by risk level.

View the Mcp Human Agents policy → Token cost: 842 tokens →

// ALL 5 MCP HUMAN AGENTS TOOLS

READ 1 tools

Read list_humans List all currently active human contractors on this VM.

WRITE 1 tools

Write message_human Send a message to a contractor (terminal overlay or desktop notification).

DESTRUCTIVE 1 tools

Destructive dismiss_human Dismiss a human contractor, revoke their access, and optionally merge their changes.

EXECUTE 1 tools

Execute toggle_autoplans Toggle the auto-plans setting. 'on' = summon a human before writing any plan (always). 'off' = only summon ...

OTHER 1 tools

Other summon_human BEHAVIOR (auto-plans=false): Only call this tool when the user EXPLICITLY asks to summon a human. Do NOT ca...

// RUNNING THIS SERVER

The managed route: connect Mcp Human Agents through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @bazaar.ai/mcp-human-agents

// FAQ

How many tools does the Mcp Human Agents MCP server have? +

The Mcp Human Agents MCP server exposes 5 tools across 5 categories: Read, Write, Destructive, Execute, Other.

How do I enforce policies on Mcp Human Agents tools? +

Route the Mcp Human Agents server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Mcp Human Agents tools fall into? +

Mcp Human Agents tools are categorised as Read (1), Write (1), Destructive (1), Execute (1), Other (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.