3 tools from the AgentIndex MCP Server, categorised by risk level.
View the AgentIndex policy →agent_index_stats Get statistics about the AgentIndex: total agents indexed, categories, protocols, sources. discover_agents Find AI agents that can perform a specific task. Returns ranked list of matching agents with quality scores and invocation details. get_agent_details Get detailed information about a specific agent including full capabilities, invocation method, scores, and metadata. The AgentIndex 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 AgentIndex server.
AgentIndex tools are categorised as Read (3). Each category has a recommended default policy.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept