Attach safety policies to an agent. Policies enforce rules and constraints on agent behavior. Available policy templates: - pii-protection: Protects personally identifiable information (GDPR compliant) - rate-limiting: Prevents resource abuse through rate limits - cost-control: Prevents runaway ...
Part of the Agentos MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents use attach_policy 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 attach_policy 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:
attach_policy:
rules:
- action: allow
rate_limit:
max: 30
window: 60See the full Agentos policy for all 10 tools.
Agents calling write-class tools like attach_policy 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.
Attach safety policies to an agent. Policies enforce rules and constraints on agent behavior. Available policy templates: - pii-protection: Protects personally identifiable information (GDPR compliant) - rate-limiting: Prevents resource abuse through rate limits - cost-control: Prevents runaway costs from automated operations - data-deletion: Prevents accidental data loss - secrets-protection: Prevents exposure of secrets and credentials - human-review: Requires human approval for sensitive actions Compliance frameworks: - gdpr-compliance: EU data protection compliance - soc2-security: SOC 2 Type II security controls - hipaa-healthcare: Healthcare data privacy (PHI protection) - pci-dss-payments: Payment card data security. 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 attach_policy. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Agentos MCP server.
attach_policy 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 attach_policy 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 attach_policy. 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.
attach_policy 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.