Request human approval for a sensitive agent action. Use this when: - Policy requires human review before execution - Agent attempts a high-risk action - You want to add an extra safety check Approval requests are sent to designated approvers via: - Email notification - Slack notification (if c...
Part of the Agentos MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents use request_approval to create or modify resources in Agentos. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call request_approval repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Agentos.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
tools:
request_approval:
rules:
- action: allow
rate_limit:
max: 30
window: 60See the full Agentos policy for all 10 tools.
Agents calling write-class tools like request_approval have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
Request human approval for a sensitive agent action. Use this when: - Policy requires human review before execution - Agent attempts a high-risk action - You want to add an extra safety check Approval requests are sent to designated approvers via: - Email notification - Slack notification (if configured) - Dashboard alert Requests expire after the specified time (default: 24 hours).. It is categorised as a Write tool in the Agentos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Add a rule in your Intercept YAML policy under the tools section for request_approval. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Agentos MCP server.
request_approval is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the request_approval 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.
Set action: deny in the Intercept policy for request_approval. 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.
request_approval is provided by the Agentos MCP server (@microsoft/agentos-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.