Is Git MCP server safe?
What Git MCP server does
mcp-server-git lets an MCP client read and change Git repositories: status, diffs, log, show, listing and creating branches, checkout, add, commit and reset. PyPI lists Anthropic, PBC. as author, with source in the modelcontextprotocol/servers repository, and the README says the server is in early development. It works on local repositories on disk, chosen with --repository or a repo_path argument per tool, and the Docker setup mounts host directories into the container. Before installing, start it with --repository set to a single repository and, under Docker, mount only that path, because tools such as git_reset and git_checkout change the working tree.
- Python shell/command execution
- Python filesystem read
- 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.
Git MCP server is an MCP server analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators. It can: filesystem read, mcp tools detected and shell execution — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).
mcp-server-git 2026.11.11
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 Git MCP server's authors. Report a false positive.
Behavioral traits
How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.
Findings (3)
The component can run operating-system commands or spawn processes.
import git
from git.exc import BadName
Why it matters: Powerful and often legitimate — confirm the commands aren't built from untrusted input.
Fix: Confirm the command and its arguments are fully controlled and not derived from untrusted input; avoid shell=True.
The component reads files from disk.
repo.commit(sha) for sha in merge_head.read_text().split()
stash_oid = autostash.read_text().strip()
lines = alternates.read_text(encoding="utf-8", errors="replace")
Why it matters: Usually legitimate, but worth confirming it can't be steered into reading sensitive files.
Fix: Confirm which files are read and that paths cannot be influenced by untrusted input to reach sensitive locations.
An MCP tool surface (manifest or tool definitions) was found.
@server.tool(
@server.tool(
@server.tool(
@server.tool(
@server.tool(
@server.tool(
@server.tool(
@server.tool(
@server.tool(
@server.tool(
@server.tool(
@server.tool(
@server.tool(
@server.tool(
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 Git MCP server.
Maintain Git MCP server?
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 componentHow we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →