Skip to main content
SkillTotal

Is GitMCP safe?

What GitMCP does

GitMCP is an open-source remote MCP server that turns a GitHub repository or GitHub Pages site into a documentation source, with tools to fetch and search a project's documentation and code and to fetch URL content. It is published in the idosal/git-mcp repository and is used through the gitmcp.io service or self-hosted. It fetches GitHub content over the network; the README states the service needs no authentication and does not store queries. Before installing, decide between the hosted gitmcp.io endpoint and self-hosting, and connect it only to repositories whose content you are comfortable placing into the model's context.

Partially analyzed - 1 code file not read (1 minified)
Notable — review in context (a capability is not a malicious indicator):
  • Node.js network egress
  • npm prepare hook
  • MCP tool surface detected

What to do: Nothing here argues against installing it. Grant the capabilities it lists only if you expect the tool to need them.

GitMCP is an MCP server analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators. It can: install time execution, mcp tools detected and network egress — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).

git-mcp 1.0.0

GitHub repository, read as an npm package · https://github.com/idosal/git-mcp
LOW
0
/ 100 risk score
Snapshot · scanned Nov 13, 2026 · git-mcp@1.0.0 · engine 1.1.0 / ruleset 100

Get notified when this component changes

Change alerts aren't live yet. Leave your email and we'll let you know when they launch. We use it only for this and delete it on request.

Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of GitMCP's authors. Report a false positive.

Capabilities — what this component can do (not a risk score):
install time executionmcp tools detectednetwork egress

Behavioral traits

How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.

Tool surface
Tool Usage
Network egress
Interaction & Communication / Direct Communication
Supply-chain provenance risk
General Protections / Supply Chain

Findings (3)

Capabilitynpm prepare hooknot scored · severity mediumST-INSTALL-NPM-PREPARE

package.json has a 'prepare' script (runs on git/local installs and before publishing).

"prepare": "husky"

Why it matters: Usually a build step, but confirm it doesn't fetch or run remote code.

Fix: Usually a legitimate build step; confirm it only builds and does not fetch or execute remote code.

CapabilityNode.js network egressnot scored · severity mediumST-NET-NODE

The component makes outbound network requests.

import { IncomingMessage, ServerResponse } from "http";
const response = await fetch(url);
const response = await fetch(searchUrl, {
const response = await fetch(url, {
const response = await fetch(url, {
const response = await fetch(url);
const response = await fetch(robotsTxtUrl);
async fetch(request: Request, env: any, ctx: any) {
return await MyMCP.serve("/*").fetch(request, env, ctx);
const res = await env.ASSETS.fetch(`${origin}/README.md`);
fetch(input: RequestInfo | URL, init?: RequestInit<RequestInitCfProperties>): Promise<Response>;
declare function fetch(input: RequestInfo | URL, init?: RequestInit<RequestInitCfProperties>): Promise<Response>;
fetch(request: Request): Response | Promise<Response>;
fetch(input: RequestInfo | URL, init?: RequestInit): Promise<Response>;

Why it matters: Usually legitimate, but confirm the destinations are expected and no sensitive data leaves.

Fix: Confirm the destination hosts are expected and that no sensitive data is sent off-host.

CapabilityMCP tool surface detectednot scored · severity lowST-MCP-DETECTED

An MCP tool surface (manifest or tool definitions) was found.

const mcp = new McpServer({
const transport = new SSEServerTransport(endpoint, res);
mcp.tool("fetch_documentation", "Fetch documentation for a repository (URL will be provided when called).", {
mcp.tool("search_documentation", "Search documentation for a repository (URL will be provided when called).", {
server = new McpServer({

Why it matters: Just context — review which tools it offers and their permissions.

Fix: Review the declared MCP tools and their permissions.

How attackers abuse these capabilities

Interactive labs on the attack class behind the rules above. They show the technique, not anything found in GitMCP.

Maintain GitMCP?

Check the next package before your agent installs it

The free Claude Code plugin scans each npm, PyPI or MCP package with this report's open-source engine before the install command runs. It runs on your machine and needs no account.

Check your own component

Run the same evidence-backed scan on any MCP server, agent skill, or package.

Scan your own component

How we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →