Codebrain MCP Server
codebrain
PyPI
v0.4.4
Published by monk0062006 — 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.
Know what breaks before you break it. Structural knowledge graph for codebases — impact analysis, dead code detection, health scores. No LLM required.
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 Dynamic code execution in server code (codebrain/graph/query.py)MTC-SRC-001
In the server's implementation (`codebrain/graph/query.py:832`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: "eval(", "Function(", "[key]", "require(", "import(", "dynamic import", "d
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 codebrain/graph/query.py
high Shell/command execution in server code (codebrain/actions/reviewer.py)MTC-SRC-002
In the server's implementation (`codebrain/actions/reviewer.py:280`): 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: y: result = subprocess.run( ["git", "diff", "--name-only", base], capture_ou
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 codebrain/actions/reviewer.py
high Shell/command execution in server code (codebrain/actions/test_gen.py)MTC-SRC-002
In the server's implementation (`codebrain/actions/test_gen.py:276`): 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: y: result = subprocess.run( [sys.executable, "-m", "pytest", test_file, "-x", "-q"],
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 codebrain/actions/test_gen.py
high Shell/command execution in server code (codebrain/cli.py)MTC-SRC-002
In the server's implementation (`codebrain/cli.py:1495`): 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: diff_output = subprocess.check_output( ["git", "diff", "--name-only", diff_spec],
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 codebrain/cli.py
high Shell/command execution in server code (codebrain/diff_impact.py)MTC-SRC-002
In the server's implementation (`codebrain/diff_impact.py:144`): 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: ] result = subprocess.run( cmd, cwd=str(self.repo_root), ca
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 codebrain/diff_impact.py
high Shell/command execution in server code (codebrain/equivalence.py)MTC-SRC-002
In the server's implementation (`codebrain/equivalence.py:143`): 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: proc = subprocess.run( ["python", "-m", "pytest", str(test_dir), "-v", "--tb=short"],
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 codebrain/equivalence.py
high Shell/command execution in server code (codebrain/graph/query.py)MTC-SRC-002
In the server's implementation (`codebrain/graph/query.py:797`): 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: "vars()[", "exec(", "eval(", "type(", "__subclasses__", "register(", "registry", "plugin", "
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 codebrain/graph/query.py
high Shell/command execution in server code (codebrain/hooks.py)MTC-SRC-002
In the server's implementation (`codebrain/hooks.py:24`): 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: aged files result = subprocess.run( ["git", "diff", "--cached", "--name-only", "--diff-filter=ACMR"],
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 codebrain/hooks.py
high Shell/command execution in server code (codebrain/indexer.py)MTC-SRC-002
In the server's implementation (`codebrain/indexer.py:117`): 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( [sys.executable, "-c", _PARSE_SCRIPT, str(file_path), str(repo_root)
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 codebrain/indexer.py
high Shell/command execution in server code (codebrain/rewriter.py)MTC-SRC-002
In the server's implementation (`codebrain/rewriter.py:1483`): 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: proc = subprocess.run( build_cmd, cwd=str(output_dir), capture_outp
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 codebrain/rewriter.py
high Shell/command execution in server code (codebrain/test_runner.py)MTC-SRC-002
In the server's implementation (`codebrain/test_runner.py:255`): 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: proc = subprocess.run( cmd, capture_output=True, text=True, timeout=tim
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 codebrain/test_runner.py
low Dynamic code execution in packaging/dev tooling (tests/test_vscode_extension.py)MTC-SRC-001
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_vscode_extension.py:243`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: """Should never use eval().""" assert "eval(" not in source def test_no_shell_true(self, source):
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 tests/test_vscode_extension.py
Tools 2
Each tool and what it can reach — statically extracted from the published source.
get_projectno sensitive capabilityset_projectno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (2 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 |
|---|---|---|---|---|
v0.4.4 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 codebrain --online --registry pypiMore in AI, Memory & Reasoning
FDA device & vehicle recall risk for AI agents: recall history, MAUDE trend, risk score.
Open-source MCP server exposing Agent402.Tools' catalog — 500+ strong: 400+ self-hostable tools + 100 multi-tool skill packs (security-audit, trend-analysis, structured-scrape, decode-blob, forecasting-bake-off) for AI agents — browser, web search & answe
Zero-dependency MCP server that gives AI agents a self-updating project memory in AGENTS.md. Returns merge instructions instead of mutating state, so every change is a reviewable diff.
MCP Apps UI resources and server helpers for n8n
MCP server providing comprehensive access to BookStack knowledge management system
MCP server for tracking achievements with STAR methodology