Codex Dev Mcp Suite MCP Server
codex-dev-mcp-suite
npm
v3.5.0
Published by verrysimatupang99 — 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.
Four local, file-based MCP servers for solo devs/vibecoders: persistent project memory, session handoff/resume, git-independent file checkpoints, and token-efficient project briefings. Works with any MCP client.
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 − 9.5 = 91. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −9.5 | Untrusted input concatenated into a command sink ×2 MTC-SRC-009 | injection |
2. Client adoption risk — 91 − 11 = 80. 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 |
|---|---|
| −10 | capability blast radius (critical) — 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 7
high Reads a sensitive credential path or dumps the environment (context-pack/server.js)MTC-SRC-006
In the server's implementation (`context-pack/server.js:40`): 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: \.p12$/i, /\.pfx$/i, /id_rsa/i, /id_ed25519/i, /id_ecdsa/i, /id_dsa/i, /known_hosts/i, /authorized_keys/i, /creden
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 context-pack/server.js
high Shell/command execution in server code (checkpoint/server.js)MTC-SRC-002
In the server's implementation (`checkpoint/server.js: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: port { execSync } from "child_process"; const ROOT = process.env.CHECKPOINT_DIR || path.join(os.homedir(), ".ai-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 checkpoint/server.js
high Shell/command execution in server code (context-pack/server.js)MTC-SRC-002
In the server's implementation (`context-pack/server.js: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: port { execSync } from "child_process"; const IGNORE = new Set([ "node_modules", ".git", ".next", "dist", "build", "t
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 context-pack/server.js
high Shell/command execution in server code (project-memory/auto-indexer.js)MTC-SRC-002
In the server's implementation (`project-memory/auto-indexer.js:10`): 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: port { execSync } from "child_process"; async function scanSessionLogs(root, customSessionDir) { const decisions = []
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 project-memory/auto-indexer.js
high Shell/command execution in server code (run-tests.mjs)MTC-SRC-002
In the server's implementation (`run-tests.mjs:6`): 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: import { spawn } from "child_process"; import path from "path"; import { fileURLToPath } from "url"; import fs from "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 run-tests.mjs
medium Untrusted input concatenated into a command sink (checkpoint/server.js)MTC-SRC-009
In the server's implementation (`checkpoint/server.js:260`): 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: const diffOut = execSync(`diff -u "${oldPath}" "${newPath}" || true`).toString(); // Remove the abs
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 checkpoint/server.js
medium Untrusted input concatenated into a command sink (context-pack/server.js)MTC-SRC-009
In the server's implementation (`context-pack/server.js:460`): 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: > { try { execSync(`git check-ignore -q -- "${rel}"`, { cwd: root, timeout: 2000 }); return 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 context-pack/server.js
Tools 42
Each tool and what it can reach — statically extracted from the published source.
memory_getingests untrusted inputcheckpoint_createno sensitive capabilitycheckpoint_deleteno sensitive capabilitycheckpoint_diffno sensitive capabilitycheckpoint_listno sensitive capabilitycheckpoint_restoreno sensitive capabilityinitialize_agent_sessionno sensitive capabilityjournal_clear_handoffno sensitive capabilityjournal_compressno sensitive capabilityjournal_dailyno sensitive capability
Show 32 more tools ↓
journal_handoffno sensitive capabilityjournal_logno sensitive capabilityjournal_resumeno sensitive capabilityjournal_searchno sensitive capabilityjournal_standupno sensitive capabilityjournal_timelineno sensitive capabilitymemory_auto_indexno sensitive capabilitymemory_broadcastno sensitive capabilitymemory_dedupno sensitive capabilitymemory_deleteno sensitive capabilitymemory_global_recallno sensitive capabilitymemory_graphno sensitive capabilitymemory_import_sessionno sensitive capabilitymemory_linkno sensitive capabilitymemory_listno sensitive capabilitymemory_mocno sensitive capabilitymemory_recallno sensitive capabilitymemory_reindexno sensitive capabilitymemory_saveno sensitive capabilitymemory_statsno sensitive capabilitymemory_swarm_timelineno sensitive capabilitypack_auditno sensitive capabilitypack_dense_briefno sensitive capabilitypack_find_todosno sensitive capabilitypack_guardno sensitive capabilitypack_impactno sensitive capabilitypack_outlineno sensitive capabilitypack_overviewno sensitive capabilitypack_predictive_diffno sensitive capabilitypack_searchno sensitive capabilitypack_telemetryno sensitive capabilitypack_treeno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (42 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 3
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 |
|---|---|---|---|---|
v3.5.0 latest |
B 80/100 | 7 | 1.13.0 | 2026-09-07 |
v3.2.0 |
B 83/100 | 5 | 1.13.0 | 2026-09-01 |
v3.1.1 |
B 83/100 | 5 | 1.10.0 | 2026-07-25 |
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 codex-dev-mcp-suite --onlineMore 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.