Context (prom.codes) MCP Server
@prom.codes/context-mcp
npm
v0.26.0
Published by @prom.codes — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
prom.codes Context — local-first codebase indexing & retrieval as an MCP server.
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 − 15.4 = 85. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −15.4 | Near-miss of @upstash/context7-mcp MTC-SUP-005 | supply-chain |
2. Client adoption risk — 85 − 8 = 77. 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 3
high Reads a sensitive credential path or dumps the environment (dist/bin.js)MTC-SRC-006
In the server's implementation (`dist/bin.js:4076`): 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: __PURE__ */ new Set([ ".npmrc", ".pypirc", ".netrc", ".pgpass", "known_hosts", // Project-specific: CLAUDE.m
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/bin.js
high Shell/command execution in server code (dist/bin.js)MTC-SRC-002
In the server's implementation (`dist/bin.js:4137`): 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: ort { exec } from "node:child_process"; import { mkdir, readFile as readFile2, rm, writeFile } from "node:fs/promises";
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/bin.js
high Near-miss of @upstash/context7-mcp (edit distance 1)MTC-SUP-005
"@prom.codes/context-mcp" is edit-distance 1 from the high-traffic package "@upstash/context7-mcp". Verify this is the intended package.
Fix: Confirm you meant "@upstash/context7-mcp". Install packages only from their documented, official name.
Location: package @prom.codes/context-mcp
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 7
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 |
|---|---|---|---|---|
v0.26.0 latest |
C 77/100 | 3 | 1.13.0 | 2026-09-07 |
v0.24.2 |
C 77/100 | 3 | 1.13.0 | 2026-09-01 |
v0.24.1 |
C 77/100 | 3 | 1.12.1 | 2026-08-05 |
v0.23.0 |
C 77/100 | 3 | 1.12.1 | 2026-08-03 |
v0.22.0 |
C 77/100 | 3 | 1.12.1 | 2026-08-01 |
Show 2 more versions ↓
v0.21.0 |
C 70/100 | 2 | 1.8.0 | 2026-07-23 |
v0.20.0 |
B 83/100 | 2 | 1.5.0 | 2026-07-22 |
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 @prom.codes/context-mcp --onlineOther implementations of Context 11
Independent packages implementing the same tool, scanned with the same engine. Compare all 12 side by side →
An agnostic Model Context Protocol (MCP) engine that exposes task-driven frontend documentation to AI agents via distributed UI library providers.
Lightweight MCP server for semantic search over organizational markdown
MCP Context Server — a FastMCP-based server providing persistent multimodal context storage for LLM agents.
A Model Context Protocol server providing intelligent context management and web content fetching capabilities for AI assistants
Design system context for AI coding agents — MCP server + CLI + live preview
Persistent AI memory + codebase knowledge graph MCP server. Works across Claude Code, VS Code Copilot, Google Antigravity, Codex CLI, Hermes Agent, Claude.ai, and ChatGPT.
More in Analytics & Monitoring
Public-safe MCP admin discovery contract descriptors and response builders.
Pokemon Champions battle advisor MCP server
Airflow MCP server — DAG list, runs, task instances, log tails, trigger and clear over the Airflow REST API
MCP analytics wrapper SDK that instruments MCP tool declarations with telemetry.
AI-ready GIS, geofencing, DataSynch, CRM, inventory, routing, APIs, telemetry and workflows.
AI-native social listening. Monitor buying signals and run GTM workflows via natural language.