graneth-mcp
An account-free MCP server that checks AI-written changes before they are committed, detecting nonexistent packages, dependency risk shapes, and hardcoded secrets.
README
graneth-mcp
Source for @graneth/mcp-server — an account-free MCP
server that checks AI-written changes before they are committed: packages that do not
exist, dependency risk shapes, and hardcoded secrets.
npx @graneth/mcp-server
Tool documentation, install snippets for Claude Code / Cursor / Windsurf, and the exact
verdicts it returns: packages/mcp-server/README.md.
What is in this repository
packages/mcp-server |
the MCP server itself — stdio, hand-rolled JSON-RPC, no runtime dependencies |
packages/core-checks |
the detection core it bundles: registry existence across six ecosystems, manifest parsing, secret patterns + entropy, risk scoring |
What is not
The hosted scanning service is a separate, closed codebase: pull-request scanning, the second-pass LLM triage, policy enforcement, signed receipts and billing are not here and are not open source. This repository is the free tool and the checks it runs — which is the part you install on your machine, and therefore the part worth being able to read.
How it is maintained
Generated from the internal monorepo, which is the source of truth. Edits made directly here are overwritten on the next sync, so please open an issue rather than a patch — the fix lands upstream and comes back with the next release.
Three of core-checks' test files are held back: they assert that the secret rules fire,
so their fixtures are literal example credentials, and every scanner — GitHub's push
protection and this project's own — reads them as the real thing. The rules themselves
are here in full (packages/core-checks/src/secrets.ts), as are the package's other tests.
Licence
MIT. 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.