Codeseeker MCP Server
codeseeker
npm
v2.0.1
Published by jghiringhelli — 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.
Graph-powered code intelligence for Claude Code. Semantic search + knowledge graph for better AI code understanding.
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 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 99 − 7 = 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 |
| −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 25
high Reads a sensitive credential path or dumps the environment (dist/mcp/indexing-service.js)MTC-SRC-006
In the server's implementation (`dist/mcp/indexing-service.js:115`): 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: pfx', '*.jks', 'id_rsa', 'id_dsa', 'id_ecdsa', 'id_ed25519', '*.keystore', // Auth tokens
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/mcp/indexing-service.js
high Dynamic evaluation of a non-literal value (dist/cli/quality/services/compilation-service.js)MTC-SRC-010
In the server's implementation (`dist/cli/quality/services/compilation-service.js:122`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate 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: new Function(content); } catch (syntaxError) {
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/quality/services/compilation-service.js
high Dynamic code execution in server code (dist/cli/quality/services/compilation-service.js)MTC-SRC-001
In the server's implementation (`dist/cli/quality/services/compilation-service.js:122`): 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: new Function(content); } catch (syntaxError) {
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/quality/services/compilation-service.js
high Dynamic code execution in server code (dist/cli/quality/services/security-service.js)MTC-SRC-001
In the server's implementation (`dist/cli/quality/services/security-service.js:154`): 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: description: 'Use of eval() can lead to code injection vulnerabilities' }); }
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/quality/services/security-service.js
high Dynamic code execution in server code (dist/cli/services/data/embedding/providers/xenova-provider.js)MTC-SRC-001
In the server's implementation (`dist/cli/services/data/embedding/providers/xenova-provider.js:25`): 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: nsformersModule = await eval('import("@xenova/transformers")'); const { pipeline: pipelineFunc } = trans
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/services/data/embedding/providers/xenova-provider.js
high Dynamic code execution in server code (dist/shared/intelligent-cycle/services/security-scanning-service.js)MTC-SRC-001
In the server's implementation (`dist/shared/intelligent-cycle/services/security-scanning-service.js:41`): 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: description: 'Use of eval() can lead to code injection vulnerabilities' }, {
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/shared/intelligent-cycle/services/security-scanning-service.js
high Dynamic code execution in server code (dist/shared/validation-cycle/services/core-safety-service.js)MTC-SRC-001
In the server's implementation (`dist/shared/validation-cycle/services/core-safety-service.js:277`): 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: s*\(/, message: 'Use of eval() function detected' }, { pattern: /exec\s*\(/, message: 'Use of exec() fun
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/shared/validation-cycle/services/core-safety-service.js
high Shell/command execution in server code (dist/cli/analyzers/change-analyzer.js)MTC-SRC-002
In the server's implementation (`dist/cli/analyzers/change-analyzer.js: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: nalyzer = void 0; const child_process_1 = require("child_process"); const util_1 = require("util"); const execAsync = (0
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/analyzers/change-analyzer.js
high Shell/command execution in server code (dist/cli/commands/command-router.js)MTC-SRC-002
In the server's implementation (`dist/cli/commands/command-router.js:431`): 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'); return new Promise((resolve) => { // Extract the claude com
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/command-router.js
high Shell/command execution in server code (dist/cli/commands/services/user-interaction-service.js)MTC-SRC-002
In the server's implementation (`dist/cli/commands/services/user-interaction-service.js:13`): 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: platform-utils"); const child_process_1 = require("child_process"); const inquirer_1 = __importDefault(require("inquirer
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/services/user-interaction-service.js
high Shell/command execution in server code (dist/cli/commands/services/workflow-orchestrator.js)MTC-SRC-002
In the server's implementation (`dist/cli/commands/services/workflow-orchestrator.js:60`): 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: ../../ui/theme"); const child_process_1 = require("child_process"); const util_1 = require("util"); const path = __impor
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/services/workflow-orchestrator.js
high Shell/command execution in server code (dist/cli/features/compilation/verifier.js)MTC-SRC-002
In the server's implementation (`dist/cli/features/compilation/verifier.js:44`): 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: require("path")); const child_process_1 = require("child_process"); class CompilationVerifier { logger = logger_1.Lo
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/features/compilation/verifier.js
high Shell/command execution in server code (dist/cli/git/git-commit-utils.js)MTC-SRC-002
In the server's implementation (`dist/cli/git/git-commit-utils.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: require("util"); const child_process_1 = require("child_process"); const fs = __importStar(require("fs/promises")); con
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/git/git-commit-utils.js
high Shell/command execution in server code (dist/cli/git/services/git-analysis-service.js)MTC-SRC-002
In the server's implementation (`dist/cli/git/services/git-analysis-service.js:8`): 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: Service = void 0; const child_process_1 = require("child_process"); const util_1 = require("util"); const logger_1 = req
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/git/services/git-analysis-service.js
high Shell/command execution in server code (dist/cli/git/services/git-autocommit-service.js)MTC-SRC-002
In the server's implementation (`dist/cli/git/services/git-autocommit-service.js: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: Service = void 0; const child_process_1 = require("child_process"); const util_1 = require("util"); const chokidar = __i
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/git/services/git-autocommit-service.js
high Shell/command execution in server code (dist/cli/git/services/git-operations-service.js)MTC-SRC-002
In the server's implementation (`dist/cli/git/services/git-operations-service.js:8`): 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: Service = void 0; const child_process_1 = require("child_process"); const util_1 = require("util"); const logger_1 = req
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/git/services/git-operations-service.js
high Shell/command execution in server code (dist/cli/managers/claude-code-forwarder.js)MTC-SRC-002
In the server's implementation (`dist/cli/managers/claude-code-forwarder.js:11`): 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: e("../ui/theme"); const child_process_1 = require("child_process"); class ClaudeCodeForwarder extends events_1.EventEmit
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/managers/claude-code-forwarder.js
medium Hardcoded egress to an external endpoint (dist/cli/services/data/content-processing/content-processor.js)MTC-SRC-003
In the server's implementation (`dist/cli/services/data/content-processing/content-processor.js:58`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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 response = await fetch('https://api.openai.com/v1/embeddings', { method: 'POST',
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/services/data/content-processing/content-processor.js
medium Hardcoded egress to an external endpoint (dist/shared/hybrid-file-discovery.js)MTC-SRC-003
In the server's implementation (`dist/shared/hybrid-file-discovery.js:248`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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 response = await fetch('https://api.openai.com/v1/embeddings', { method: 'POST', headers:
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/shared/hybrid-file-discovery.js
medium Dynamic module load from a non-literal (bin/codeseeker.js)MTC-SRC-005
In the server's implementation (`bin/codeseeker.js:137`): 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: ng const cliModule = require(cliPath); if (!cliModule || typeof cliModule.main !== 'function') { throw new
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/codeseeker.js
medium Dynamic module load from a non-literal (dist/cli/services/data/semantic-graph/parsers/tree-sitter-java-parser.js)MTC-SRC-005
In the server's implementation (`dist/cli/services/data/semantic-graph/parsers/tree-sitter-java-parser.js:74`): 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: .then(s => __importStar(require(s))); const javaModule = await Promise.resolve(`${'tree-sitter-java'}`).
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/cli/services/data/semantic-graph/parsers/tree-sitter-java-parser.js
medium Dynamic module load from a non-literal (dist/cli/services/data/semantic-graph/parsers/tree-sitter-python-parser.js)MTC-SRC-005
In the server's implementation (`dist/cli/services/data/semantic-graph/parsers/tree-sitter-python-parser.js:76`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: .then(s => __importStar(require(s))); const pythonModule = await Promise.resolve(`${'tree-sitter-python'
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/services/data/semantic-graph/parsers/tree-sitter-python-parser.js
medium Dynamic module load from a non-literal (dist/cli/services/data/semantic-graph/tree-sitter-semantic-builder.js)MTC-SRC-005
In the server's implementation (`dist/cli/services/data/semantic-graph/tree-sitter-semantic-builder.js:69`): 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 Language = require(packageName); // Handle TypeScript which has multiple grammars
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/services/data/semantic-graph/tree-sitter-semantic-builder.js
medium Dynamic module load from a non-literal (dist/shared/tool-registry-initializer.js)MTC-SRC-005
In the server's implementation (`dist/shared/tool-registry-initializer.js:87`): 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: toolModule = require(tryPath); loadedPath = tryPath; break;
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/shared/tool-registry-initializer.js
low Package runs install-time scripts (postinstall)MTC-SUP-010
"codeseeker" executes postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.
Evidence: node scripts/postinstall.js
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package codeseeker
Tools 1
Each tool and what it can reach — statically extracted from the published source.
codeseekerno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (1 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 |
|---|---|---|---|---|
v2.0.1 latest |
A 92/100 | 25 | 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 codeseeker --onlineMore in Web, Search & Scraping
Agent IP: MCP server with patents search tools
MCP server for searching the Agent Almanac — the public catalog of 9,000+ Model Context Protocol servers. Find, install, and discover MCP servers from inside Claude Desktop, Cursor, Continue, Zed, or any MCP-aware agent.
Search agents & MCP servers by capability, with daily-observed pricing, liveness and market data.
Verified merchants accepting agentic payments on Lightning/L402/BOLT12/USDT — search, verify, pay.
Airframe MCP Client - Connect agents to Airframe's product intelligence
Amazon product search demand over time, with growth for any keyword. Free key at trendsmcp.ai