Fs Git MCP Server
fs-git-mcp
PyPI
v0.1.0
Published by wojons — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
MCP Git-enforced filesystem with direct and staged modes
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 12
high Shell/command execution in server code (debug_mcp_methods.py)MTC-SRC-002
In the server's implementation (`debug_mcp_methods.py:17`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rver process proc = subprocess.Popen( [sys.executable, "mcp_server/server_fastmcp_new.py"], stdin=su
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server debug_mcp_methods.py
high Shell/command execution in server code (mcp_server/cli/main.py)MTC-SRC-002
In the server's implementation (`mcp_server/cli/main.py:42`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: Initialize git repo subprocess.run(["git", "init", repo_root], check=True) # Set safe.directory subprocess.
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server mcp_server/cli/main.py
high Shell/command execution in server code (mcp_server/git_backend/commits.py)MTC-SRC-002
In the server's implementation (`mcp_server/git_backend/commits.py:22`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: result = subprocess.run( ["git", "-C", repo.root, "log", f"--oneline", f"-{window}", "--forma
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server mcp_server/git_backend/commits.py
high Shell/command execution in server code (mcp_server/git_backend/history.py)MTC-SRC-002
In the server's implementation (`mcp_server/git_backend/history.py:7`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: result = subprocess.run( ["git", "-C", repo.root, "log", f"--oneline", f"-{limit}", "--", pat
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server mcp_server/git_backend/history.py
high Shell/command execution in server code (mcp_server/git_backend/repo.py)MTC-SRC-002
In the server's implementation (`mcp_server/git_backend/repo.py:17`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: safe.directory subprocess.run(["git", "config", "--global", "--add", "safe.directory", self.root], check=True)
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server mcp_server/git_backend/repo.py
high Shell/command execution in server code (mcp_server/git_backend/safety.py)MTC-SRC-002
In the server's implementation (`mcp_server/git_backend/safety.py:85`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: result = subprocess.run(["git", "-C", repo.root, "status", "--porcelain"], capture_output=True, text=True
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server mcp_server/git_backend/safety.py
high Shell/command execution in server code (mcp_server/git_backend/staging.py)MTC-SRC-002
In the server's implementation (`mcp_server/git_backend/staging.py:21`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: log_result = subprocess.run( ["git", "-C", self.repo.root, "log", "--oneline", f"{self.base_b
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server mcp_server/git_backend/staging.py
high Shell/command execution in server code (mcp_server/git_backend/templates.py)MTC-SRC-002
In the server's implementation (`mcp_server/git_backend/templates.py:41`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: result = subprocess.run( ['git', 'log', f'--oneline', f'-{window}', '--format=%s'],
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server mcp_server/git_backend/templates.py
low Unconstrained path parameter "path" on "read_with_history"MTC-CAP-008
Tool "read_with_history" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool read_with_history · inputSchema.properties.path
low Unconstrained path parameter "path" on "read_file"MTC-CAP-008
Tool "read_file" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool read_file · inputSchema.properties.path
low Shell/command execution in packaging/dev tooling (basic_mcp_test.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`basic_mcp_test.py:15`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: h): self.proc = subprocess.Popen( [sys.executable, server_path], stdin=subprocess.PIPE,
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server basic_mcp_test.py
low Shell/command execution in packaging/dev tooling (comprehensive_mcp_test.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`comprehensive_mcp_test.py:16`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: h): self.proc = subprocess.Popen( [sys.executable, server_path], stdin=subprocess.PIPE,
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server comprehensive_mcp_test.py
Tools 28
Each tool and what it can reach — statically extracted from the published source.
read_filereads sensitive dataread_file_funcreads sensitive dataread_with_historyreads sensitive dataabort_stagedno sensitive capabilityaddno sensitive capabilityanswer_about_fileno sensitive capabilityapply_patch_and_commitno sensitive capabilityapply_patch_and_commit_funcno sensitive capabilitybatch_replace_and_commitno sensitive capabilitybatch_replace_and_commit_funcno sensitive capability
Show 18 more tools ↓
extractno sensitive capabilityfinalize_stagedno sensitive capabilitylint_commit_messageno sensitive capabilitylist_dirno sensitive capabilitylist_dir_funcno sensitive capabilitymake_dirno sensitive capabilitymake_dir_funcno sensitive capabilitypreview_diffno sensitive capabilitypreview_diff_funcno sensitive capabilityreplace_and_commitno sensitive capabilityreplace_and_commit_funcno sensitive capabilitystaged_previewno sensitive capabilitystaged_writeno sensitive capabilitystart_stagedno sensitive capabilitystat_fileno sensitive capabilitystat_file_funcno sensitive capabilitytest_addno sensitive capabilitywrite_and_commitno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (28 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.1.0 latest |
A 93/100 | 12 | 1.13.0 | 2026-08-25 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan fs-git-mcp --online --registry pypiMore in Developer Tools
Hotel booking MCP server — 300K+ properties, real confirmation numbers, loyalty programs. Builders monetize every booking via Stripe Connect. The first MCP server that completes real hotel reservations inside AI conversations.
Manage AdGuard Home through AI assistants
Read-only Azure DevOps for MCP clients using only your existing browser session — no PAT, no Azure CLI. Browse work items, pull requests, comments, attachments and Artifacts feeds across every project, repo and feed you can access.
MCP server for Adobe Experience Manager Assets integration development
Servidor MCP para el tiempo oficial de España (API pública OpenData de AEMET). Predicción, observación y avisos como herramientas MCP tipadas.
A standalone MCP stdio bridge for Affinity by Canva's local MCP SSE server.