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. sa...
Part of the Mcp Human Agents server.
Free to start. No card required.
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.
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.
Apply a rate limit to control usage and monitor for unexpected behaviour.
{
"version": "1",
"default": "deny",
"tools": {
"summon_human": {
"limits": [
{
"counter": "summon_human_rate",
"window": "minute",
"max": 60,
"scope": "grant"
}
]
}
}
}See the full Mcp Human Agents policy for all 5 tools.
These attack patterns abuse exactly the kind of access summon_human gives an agent. Each links to the full case and the policy that stops it:
Other other tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
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.
Register the Mcp Human Agents MCP server in PolicyLayer and add a rule for summon_human: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Human Agents. Nothing to install.
summon_human is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the summon_human rule in your PolicyLayer 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.
Set action: deny in the PolicyLayer 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.
summon_human is provided by the Mcp Human Agents MCP server (@bazaar.ai/mcp-human-agents). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 Mcp Human Agents tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.