3 tools from the Agentvet MCP Server, categorised by risk level.
View the Agentvet policy →lint_tool_definition Sanity-check a tool definition for common mistakes that hurt LLM tool-use accuracy: missing description, vague description, no required fields, sch... validate_tool_args Validate a tool-call args object against a small shape spec. Returns { valid, error?, retry_hint? } where retry_hint is a ready-to-send LLM feedbac... The Agentvet MCP server exposes 3 tools across 2 categories: Read, Write.
Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Agentvet server.
Agentvet tools are categorised as Read (2), Write (1). Each category has a recommended default policy.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.