3 tools from the Agentguard MCP Server, categorised by risk level.
View the Agentguard policy →check_url Check whether a URL is allowed under a network policy. Returns { allowed, reason } without making any actual request. Use this to gate tool calls b... check_urls_batch Batch-check multiple URLs against the same policy. Returns per-URL decisions plus an allowed/denied summary. Useful for vetting a list of pending t... validate_policy Sanity-check a policy spec without making any decision. Catches: empty allow list, overly broad "*" wildcards, malformed host patterns containing s... The Agentguard MCP server exposes 3 tools across 1 categories: Read.
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 Agentguard server.
Agentguard tools are categorised as Read (3). Each category has a recommended default policy.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.