codesift-mcp
npm
v0.17.0
Published by greglas75 — 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 server for code intelligence — 146 tools for symbol search, call graph, semantic search, route tracing, community detection, LSP bridge, secret detection, conversation search, and Hono framework intelligence
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 − 7.5 = 93. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −6.3 | Untrusted input concatenated into a command sink MTC-SRC-009 | injection |
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 93 − 7 = 86. 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.
In the server's implementation (`dist/cli/auto-prune.js:1`): 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: rt { spawn } from "node:child_process"; import { readFile, writeFile } from "node:fs/promises"; import { join } from "no
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/auto-prune.js
In the server's implementation (`dist/cli/commands-index.js:27`): 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: } = await import("node:child_process"); const { fileURLToPath } = await import("node:url"); const { dirname, jo
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-index.js
In the server's implementation (`dist/cli/commands-maintenance.js:1`): 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: ecFileSync } from "node:child_process"; import { getBoolFlag, output, die } from "./args.js"; /** * Delete orphaned per
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-maintenance.js
In the server's implementation (`dist/cli/git-hooks-installer.js: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: { execSync } from "node:child_process"; import { existsSync, realpathSync } from "node:fs"; import { copyFile, mkdir, re
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-hooks-installer.js
In the server's implementation (`dist/cli/hooks/post-tool-use.js:4`): 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: rt { spawn } from "node:child_process"; import { randomUUID } from "node:crypto"; import { CODE_EXTENSIONS } from "./sha
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/hooks/post-tool-use.js
In the server's implementation (`dist/cli/setup/mcp.js:1`): 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: { execSync } from "node:child_process"; import { existsSync } from "node:fs"; import { homedir } from "node:os"; import
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/setup/mcp.js
In the server's implementation (`dist/install-check.js:115`): 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: } = await import("node:child_process"); /** * Verify in a FRESH process, not with `transformersResolvable()`.
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/install-check.js
In the server's implementation (`dist/lsp/lsp-manager.js:1`): 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: rt { spawn } from "node:child_process"; import { pathToFileURL } from "node:url"; import { LspClient } from "./lsp-clien
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/lsp/lsp-manager.js
In the server's implementation (`dist/lsp/lsp-servers.js:1`): 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: ecFileSync } from "node:child_process"; export const LSP_SERVERS = { typescript: { command: "typescript-lang
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/lsp/lsp-servers.js
In the server's implementation (`dist/tools/dependency-audit-freshness-tools.js:1`): 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: { execFile } from "node:child_process"; import { promisify } from "node:util"; import { CHECK_TIMEOUT_MS, MAX_BUFFER, pa
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/tools/dependency-audit-freshness-tools.js
In the server's implementation (`dist/cli/git-hooks-installer.js:171`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: } else { execSync(`git config --global core.hooksPath ${JSON.stringify(hooksDir)}`, { stdio:
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-hooks-installer.js
In the server's implementation (`dist/install-check.js:131`): 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: ut-type=module", "-e", "import(process.env.CS_PROBE_SPEC).then(()=>process.exit(0),()=>process.exit(1))"], { cwd: packag
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/install-check.js
In the server's implementation (`dist/register-tool-groups/core/meta.js:68`): 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: matched files may ONLY import (allowlist)"), })), zJsonArray(z.object({
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/register-tool-groups/core/meta.js
In the server's implementation (`dist/search/optional-transformers.js:41`): 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: IFIER; return await import(spec); } /** * How to actually get the package back, phrased for the platform the caller
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/search/optional-transformers.js
In the server's implementation (`dist/tools/astro-audit.js:89`): 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 mod = (await import(resolvedPath)); const fn = mod[exportName]; if (typeof fn === "function")
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/tools/astro-audit.js
"codesift-mcp" 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 ./dist/cli.js setup all 2>/dev/null && echo '
✨ CodeSift MCP installed and configured for all platforms.
⚠️ Restart your AI client (Cmd+Q for Claude C
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package codesift-mcp
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 |
|---|---|---|---|---|
v0.17.0 latest |
B 86/100 | 16 | 1.13.0 | 2026-09-07 |
v0.15.5 |
B 86/100 | 17 | 1.13.0 | 2026-09-06 |
v0.15.3 |
B 86/100 | 17 | 1.13.0 | 2026-08-25 |
v0.15.2 |
B 86/100 | 17 | 1.12.1 | 2026-08-16 |
v0.15.1 |
B 86/100 | 15 | 1.12.1 | 2026-08-12 |
v0.14.0 |
B 86/100 | 15 | 1.12.1 | 2026-08-10 |
v0.13.1 |
B 86/100 | 15 | 1.12.1 | 2026-08-06 |
v0.12.0 |
B 86/100 | 15 | 1.12.1 | 2026-08-03 |
v0.11.0 |
B 86/100 | 15 | 1.12.1 | 2026-08-02 |
v0.10.2 |
B 86/100 | 15 | 1.12.1 | 2026-07-31 |
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.
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 codesift-mcp --online
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.