# api-governance MCP server

API governance for AI agents. Detects breaking changes, scores blast radius, blocks unsafe calls.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-coderifts-api-governance
- Repository: https://github.com/coderifts/self-hosted

## Install
- Endpoint: https://app.coderifts.com/mcp
- Auth: Auth required by registry metadata

## Setup notes
- Remote header: Authorization (required; secret)
- The upstream registry signals required auth or secrets.
- Remote endpoint: https://app.coderifts.com/mcp
- Header: Authorization

## Tools
- preflight_check - Call before merging an API spec change, or before an agent depends on an endpoint. Returns risk score, break probability, blast radius, agent impact, incident cost, and an ALLOW/WARN/REQUIRE_APPROVAL/BLOCK decision. If BLOCK, do not ship the change or make the call. Endpoint: https://app.coderifts.com/mcp
- agent_tool_check - Call when an API or tool schema changes and agents call those tools. Detects TOOL_RESULT_SHAPE_DRIFT, AGENT_PROTOCOL_DRIFT, ENDPOINT_REMOVED and REQUIRED_FIELD_ADDED, and returns per-pattern mitigation. Endpoint: https://app.coderifts.com/mcp
- agent_readiness_score - Call before wiring a new API or MCP manifest into an agent. Returns a 0-100 agent-readiness score with band and per-signal breakdown. Endpoint: https://app.coderifts.com/mcp
- registry_validate - Validate a set of OpenAPI specs together: cross-spec endpoint collisions, schema naming conflicts, auth scope consistency, and unresolved $ref targets. Endpoint: https://app.coderifts.com/mcp
- agent_preflight - Call before deploying changed agent tool schemas. Given tools before and after, returns which tools break, which workflows are affected, blast radius across the agent graph, and a deploy decision. Endpoint: https://app.coderifts.com/mcp
- mcp_diff - Call before publishing a new MCP manifest version. Compares two manifests for breaking changes in tool schemas, input/output contracts, auth, and tool availability. Endpoint: https://app.coderifts.com/mcp
- governance_health - Governance check for an API change (before/after OpenAPI specs): returns the decision (ALLOW/WARN/REQUIRE_APPROVAL/BLOCK), risk_score, breaking_changes, patterns, policy_violations, security_findings, and evidence_quality. Endpoint: https://app.coderifts.com/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.coderifts
- Version: 1.0.0
- Runtime: Sse
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Mar 20, 2026
- Source: https://registry.modelcontextprotocol.io