Create a reusable governance policy that guardrail_check evaluates deterministically (no LLM) on every call. Use this to define rules before calling guardrail_check — policies persist until deleted. Rules compose with and/or/not operators; applied by priority order (first match wins). Returns the...
Bulk/mass operation — affects multiple targets
Part of the Plith MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents use guardrail_create_policy to create or modify resources in Plith. 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 guardrail_create_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 Plith.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
tools:
guardrail_create_policy:
rules:
- action: allow
rate_limit:
max: 30
window: 60See the full Plith policy for all 14 tools.
Agents calling write-class tools like guardrail_create_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.
Create a reusable governance policy that guardrail_check evaluates deterministically (no LLM) on every call. Use this to define rules before calling guardrail_check — policies persist until deleted. Rules compose with and/or/not operators; applied by priority order (first match wins). Returns the created policy object with id, name, rules, and priority. Duplicate names return an error. Free — no credits charged.. It is categorised as a Write tool in the Plith 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 guardrail_create_policy. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Plith MCP server.
guardrail_create_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 guardrail_create_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 guardrail_create_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.
guardrail_create_policy is provided by the Plith MCP server (plith/plith). 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.