API & Integration
Decision API for AI agents, supported clients, and how to integrate SpiderRating into your workflow.
Last updated: · 1 question in this topic · Based on 15,923 rated MCP servers
How can my AI agent check if an MCP tool is safe, automatically?
AI agents can query our free Decision API to get a structured safety verdict for any MCP tool: GET https://spiderrating.com/api/v1/decide/mcp-tool?slug={owner}/{repo}. No authentication required. The response returns a verdict (RECOMMENDED, CONSIDER, ALLOW_WITH_RISK, NOT_RECOMMENDED, AVOID, or UNKNOWN), a confidence score from 0 to 1, human-readable summary, specific recommendations, risk flags with severity, and reasoning factors. This is designed for agent frameworks (LangChain, Claude Code, Cursor) to make install/invoke decisions without hardcoding trust. See the llms.txt for the full API schema.