5 tools. 4 can modify or destroy data without limits.
1 destructive tool with no built-in limits. Policy required.
Last updated:
Destructive tools (dismiss_human) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (message_human) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Execute tools (toggle_autoplans) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.
Intercept sits between your agent and Mcp Human Agents. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.
npx -y @policylayer/intercept scan -- npx -y @bazaar.ai/mcp-human-agents dismiss_human:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
message_human:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
list_humans:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Mcp Human Agents server exposes 1 destructive tools including dismiss_human. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The Mcp Human Agents server has 1 write tools including message_human. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.
5 tools across 5 categories: Destructive, Execute, Other, Read, Write. 1 are read-only. 4 can modify, create, or delete data.
One line change. Instead of running the Mcp Human Agents server directly, prefix it with Intercept: intercept -c mcp-human-agents.yaml -- npx -y @@bazaar.ai/mcp-human-agents. Download a pre-built policy from policylayer.com/policies/mcp-human-agents and adjust the limits to match your use case.
Starter policies available for each. Same risk classification, same one-command setup.
Set budgets, approvals, and hard limits across MCP servers.
npx -y @policylayer/intercept init