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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。