Run adversarial queries against a live endpoint and return per-query verdict (shape-valid / shape-invalid / confident-wrong / uncertain) vs an expected shape schema + per-query expectations. Catches responses that are shape-valid but wrong.
AI agents invoke audit_api_contract to trigger actions in Raven. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
queries | array | Yes | |
endpoint_url | string | Yes | |
expected_shape_schema | object | Yes |
Parameters from the server's own tool schema.
This tool executes adversarial queries against live endpoints, which is an active operation that depends on the arguments (target endpoint, query payload, schema). While it does not modify data (Write) or delete data (Destructive), it actively executes queries against external services.
From the tool's definition 'Run adversarial queries against a live endpoint' indicates execution of external operations against a live service. The tool performs active testing/querying of production endpoints, which triggers external side effects.
Risk signalsAccepts file system path (queries[].path) · Accepts raw HTML/template content (queries[].body) · High parameter count (13 properties)
Attacks that exploit this kind of access
Run adversarial queries against a live endpoint and return per-query verdict (shape-valid / shape-invalid / confident-wrong / uncertain) vs an expected shape schema + per-query expectations. Catches responses that are shape-valid but wrong. It is categorised as a Execute tool in the Raven MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
audit_api_contract accepts 3 parameters: queries, endpoint_url, expected_shape_schema. Required: queries, endpoint_url, expected_shape_schema. The full parameter table on this page comes from the server's own tool schema.
Register the Raven MCP server in PolicyLayer and add a rule for audit_api_contract: 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 Raven. Nothing to install.
audit_api_contract is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the audit_api_contract 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 audit_api_contract. 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.
audit_api_contract is provided by the Raven MCP server (raven-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →