// 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 →

READ TOOLS

list_humans List all currently active human contractors on this VM.

WRITE TOOLS

message_human Send a message to a contractor (terminal overlay or desktop notification). 2/5

DESTRUCTIVE TOOLS

dismiss_human Dismiss a human contractor, revoke their access, and optionally merge their changes. 4/5

EXECUTE TOOLS

toggle_autoplans Toggle the auto-plans setting. 'on' = summon a human before writing any plan (always). 'off' = only summon a human when the user explicitly asks. I... 3/5

OTHER TOOLS

summon_human 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 suggest...

// 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? +

Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Mcp Human Agents 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.

Enforce policies on Mcp Human Agents

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept

github.com/policylayer/intercept →