# api-governance

**Category:** 🧬 Biology & Bioinformatics  
**Repository:** https://github.com/coderifts/self-hosted  
**GitHub Stars:** 0  
**Views:** 2  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/api-governance

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

## Tools
Capabilities this server exposes over MCP:

- **preflight_check** — Analyze an API spec diff before merge. Returns risk score, blast radius, agent impact, and a merge decision (ALLOW / WARN / REQUIRE_APPROVAL / BLOCK).
- **agent_tool_check** — Check whether an API change breaks AI agent tool calling (endpoint removal, newly required fields, result-shape drift).
- **agent_readiness_score** — Score an OpenAPI spec or MCP manifest for AI-agent readiness (0–100) with recommendations.
- **registry_validate** — Validate an MCP tool registry or OpenAPI spec collection for governance health.
- **agent_preflight** — Pre-flight governance check for agent workflows, given tool schemas before and after a change.
- **mcp_diff** — Compare two MCP manifests and detect breaking changes in tool schemas, input/output types, and descriptions.
- **governance_health** — Governance health score for an API spec (A–F grade, policy compliance, recommendations).

## Claude Desktop Quick Installation
No confirmed install details yet, so no config is published. Follow the setup steps in the repository above.

## Documentation

## What the api-governance MCP server does

The api-governance MCP server reviews API and MCP definitions with an emphasis on compatibility with AI agents. It can inspect OpenAPI specifications, MCP manifests, tool registries, and schema versions before or after a change. The results help identify changes that may disrupt existing integrations or agent tool calls.

Its governance checks cover more than endpoint compatibility. They can identify removed endpoints, newly required request fields, changes to result shapes, and other differences that affect how an agent invokes a tool. The server also produces readiness and governance assessments for specifications and registries.

## How it works

Provide the relevant specification, manifest, registry, or before-and-after tool schemas to the applicable MCP tool. A preflight review returns a risk score, estimated blast radius, agent impact, and one of four merge decisions: ALLOW, WARN, REQUIRE_APPROVAL, or BLOCK.

For agent-specific compatibility, `agent_tool_check` examines whether an API change could break tool calling. `mcp_diff` compares two MCP manifests, including tool schemas, input and output types, and descriptions. `agent_preflight` performs a similar governance check for an agent workflow using tool schemas from before and after a change.

Readiness and health checks produce scoring-based results rather than only a pass or fail. `agent_readiness_score` assigns an AI-agent readiness score from 0 to 100 and includes recommendations. `governance_health` returns an A–F grade, policy compliance information, and recommendations. `registry_validate` validates an MCP tool registry or a collection of OpenAPI specifications for governance health.

## Tools and capabilities

The api-governance MCP server exposes these capabilities:

- `preflight_check`: Assess an API specification diff before merge and return risk, blast radius, agent impact, and a merge decision.
- `agent_tool_check`: Detect API changes that can disrupt AI agent tool calling.
- `agent_readiness_score`: Rate an OpenAPI specification or MCP manifest from 0 to 100 and provide recommendations.
- `registry_validate`: Check an MCP tool registry or OpenAPI specification collection for governance health.
- `agent_preflight`: Evaluate an agent workflow from tool schemas before and after a change.
- `mcp_diff`: Find breaking changes between two MCP manifests, including schema, type, and description differences.
- `governance_health`: Generate an A–F governance grade with policy compliance and recommendations.

The api-governance MCP server is suited to pull-request checks, schema review, tool registry validation, and readiness assessments where agent compatibility is a release concern.

_Full upstream README: https://allmcps.com/mcp/api-governance/readme_