CodeRifts API Governance
An MCP server providing risk-aware API governance tools for AI agents. Agents call preflight checks before tool calls or merges to verify API contracts are safe. Returns risk score, blast radius, agent impact, economic cost, and a deterministic ALLOW/WARN/REQUIRE_APPROVAL/BLOCK decision. MCP endpoint: https://app.coderifts.com/mcp
README
CodeRifts — API Governance
Risk-aware API compatibility governance for AI agents and CI. Before a change merges, CodeRifts predicts whether it will cause a real production problem, who breaks, by what pattern, at what business cost, and whether blocking is justified.
The market shows you what changed. CodeRifts tells you how dangerous it is, who it affects, when deployment should be blocked, and how much it will cost.
- Hosted MCP server:
https://app.coderifts.com/mcp - Manifest:
https://coderifts.com/mcp.json - Official MCP Registry:
io.github.coderifts/api-governance - Website:
https://coderifts.com - Live demo PR:
https://github.com/coderifts/demo/pull/4
MCP server
CodeRifts runs as a hosted Streamable HTTP MCP server. Any MCP-compatible agent (Claude Desktop, Cursor, LangGraph, AutoGen, custom) can connect and run governance checks before tool calls or merges.
- Endpoint:
https://app.coderifts.com/mcp - Transport: Streamable HTTP (protocol version
2025-06-18) - Server:
CodeRifts API Governancev1.0.0 - Auth: Bearer API key from coderifts.com —
Authorization: Bearer <key>
Connect
{
"mcpServers": {
"coderifts": {
"url": "https://app.coderifts.com/mcp",
"headers": {
"Authorization": "Bearer <YOUR_CODERIFTS_API_KEY>"
}
}
}
}
Verify the connection
curl -sS https://app.coderifts.com/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"curl","version":"1.0"}}}'
Expected: a JSON-RPC result with serverInfo and capabilities.tools.
Tools
| Tool | What it does |
|---|---|
preflight_check |
Analyze an API spec diff before merge. Returns risk score, break probability, blast radius, agent impact, economic cost, and a merge decision (ALLOW / WARN / REQUIRE_APPROVAL / BLOCK). |
agent_tool_check |
Detect whether an API change breaks AI agent tool calling (TOOL_RESULT_SHAPE_DRIFT, AGENT_PROTOCOL_DRIFT, and more). Returns an agent-impact score and per-pattern mitigation templates. |
agent_readiness_score |
Score an OpenAPI spec or MCP manifest for AI agent readiness (0–100) across nine signals, with band and breakdown. |
registry_validate |
Validate an MCP tool registry or OpenAPI spec collection for governance health (schema consistency, auth coverage, deprecation, breaking-change density). |
agent_preflight |
Pre-flight governance check for agent workflows. Given tool schemas before/after, returns which tools break, which workflows are affected, blast radius across the agent graph, and a deploy decision. |
traffic_analyze |
Infer API spec drift from HTTP traffic samples — runtime behavioral drift detection without requiring spec changes. |
mcp_diff |
Compare two MCP manifests and detect breaking changes in tool schemas, input/output contracts, auth requirements, and tool availability. |
governance_health |
Governance health score for an API spec: A–F grade (0–100), policy violations, deprecation status, documentation coverage, and security findings. |
Every tool returns the same Decision Spec v1.0 envelope (decision, risk_score, safe_for_agent, breaking_changes, patterns, requires_migration, evidence_quality, coderifts_version, timestamp) so agent runtimes can branch on a stable contract.
How agents use it
- Before merging an API change (or before an agent calls a tool), send the before/after spec to
preflight_check. - Read
decision:ALLOWproceeds,WARNflags,REQUIRE_APPROVALpauses for a human,BLOCKstops the merge / aborts the agent step. - On
BLOCK, the response explains the patterns, blast radius, and estimated incident cost, and provides mitigation templates.
Decision logic is deterministic: a single breaking change is never silently allowed. Tests can pass and still ship a broken contract — CodeRifts checks the contract itself at PR time.
Also available
- GitHub App (zero-config, one-click install) on the GitHub Marketplace — posts a risk scorecard on every pull request.
- SDKs:
@coderifts/sdk(TypeScript / npm),coderifts-sdk(Python / PyPI). - CLI:
coderifts(npm) with a pre-push hook. - Integrations: Backstage plugin, VS Code extension, LangGraph / AutoGen / CrewAI.
Links
- Website: https://coderifts.com
- Decision Spec: https://coderifts.com/decision-spec/
- API reference: https://app.coderifts.com/api/docs
- Manifest: https://coderifts.com/mcp.json
- Contact: hello@coderifts.com
License
See LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.