3 tools from the Agentfit MCP Server, categorised by risk level.
View the Agentfit policy →count_tokens Estimate tokens in a string or chat-message array. Fast, dependency-free, within ~10-20% of true tokenizer counts on English prose. Pass a model na... list_estimators List the built-in estimator families this server knows about. Useful for picking a model alias when the exact model name isn't recognized. The Agentfit MCP server exposes 3 tools across 2 categories: Read, Destructive.
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 Agentfit server.
Agentfit tools are categorised as Read (2), Destructive (1). Each category has a recommended default policy.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.