Code Graph (npm) MCP Server
code-graph-mcp
npm
v0.2.7
Published by an unidentified publisher — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
A code indexing system accessible via MCP (Model Context Protocol)
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 − 8 = 92. 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 |
| −2 | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read |
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 9
high Reads a sensitive credential path or dumps the environment (dist/core/repository/GitOperations.js)MTC-SRC-006
In the server's implementation (`dist/core/repository/GitOperations.js:299`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. 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.join(this.workingDir, ".git-credentials-temp"); const credContent = `https://${token}:[email protected]
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 dist/core/repository/GitOperations.js
high Dynamic code execution in server code (dist/core/performance/ParallelProcessor.js)MTC-SRC-001
In the server's implementation (`dist/core/performance/ParallelProcessor.js:265`): 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: const result = vm.runInNewContext(script, context); // Handle async results cons
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 dist/core/performance/ParallelProcessor.js
high Shell/command execution in server code (dist/cli/commands/server.js)MTC-SRC-002
In the server's implementation (`dist/cli/commands/server.js: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: equire("chalk")); const child_process_1 = require("child_process"); const fs = __importStar(require("fs-extra")); const
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 dist/cli/commands/server.js
high Shell/command execution in server code (dist/cli/npx.js)MTC-SRC-002
In the server's implementation (`dist/cli/npx.js:48`): 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: = getSystemInfo; const child_process_1 = require("child_process"); const path = __importStar(require("path")); const fs
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 dist/cli/npx.js
high Shell/command execution in server code (dist/core/database/Database.js)MTC-SRC-002
In the server's implementation (`dist/core/database/Database.js:335`): 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: prepare(sql); } exec(sql) { this.db.exec(sql); } } exports.CodeGraphDatabase = CodeGraphDatabase; //
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 dist/core/database/Database.js
high Shell/command execution in server code (dist/core/repository/GitOperations.js)MTC-SRC-002
In the server's implementation (`dist/core/repository/GitOperations.js:40`): 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: ire("fs-extra")); const child_process_1 = require("child_process"); const utils_1 = require("./utils"); class GitOperati
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 dist/core/repository/GitOperations.js
medium Dynamic module load from a non-literal (bin/code-graph-mcp-demo.js)MTC-SRC-005
In the server's implementation (`bin/code-graph-mcp-demo.js:56`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: Sync(demoPath)) { require(demoPath); } else { console.error('Error: NPX demo files not found. Please run
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 bin/code-graph-mcp-demo.js
medium Dynamic module load from a non-literal (bin/code-graph-mcp.js)MTC-SRC-005
In the server's implementation (`bin/code-graph-mcp.js:71`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const npxModule = require(npxPath); if (npxModule.setupNPXEnvironment) { const setupSuccess = aw
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 bin/code-graph-mcp.js
low Shell/command execution in packaging/dev tooling (scripts/postinstall.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/postinstall.js:5`): 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: st { spawn } = require('child_process'); /** * Post-installation setup script for code-graph-mcp * Handles NPX compat
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 scripts/postinstall.js
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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 |
|---|---|---|---|---|
v0.2.7 latest |
A 92/100 | 9 | 1.13.0 | 2026-09-07 |
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 code-graph-mcp --onlineOther implementations of Code Graph 4
Independent packages implementing the same tool, scanned with the same engine. Compare all 5 side by side →
Code Graph MCP Server
Local code-intelligence MCP server: index a mono-repo into a knowledge graph (routes, components, API calls, backend handlers) and answer structural questions in a fraction of the tokens.
MCP server for multi-language code graph intelligence and analysis across 25+ programming languages
MCP server that indexes codebases into an AST knowledge graph with semantic search, call graph traversal, and HTTP route tracing
More 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.