3 tools from the Agentcast MCP Server, categorised by risk level.
View the Agentcast policy →extract_json Pull a JSON value out of messy LLM output. Tries the whole text, then a fenced ```json``` block, then the largest balanced {...}/[...] substring. R... validate_response Validate a parsed JSON value against an agentcast shape spec. Spec maps field name to type: 'string', 'number', 'boolean', 'array', 'object'. Suffi... The Agentcast MCP server exposes 3 tools across 2 categories: Read, Execute.
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 Agentcast server.
Agentcast tools are categorised as Read (2), Execute (1). Each category has a recommended default policy.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.