augments-mcp-server@2.0.2
CAUTION· not startedPublisher claims: "Augments MCP Server - A comprehensive framework documentation provider for Claude Code" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
GITHUB_TOKENMASTER_API_KEYConfiguration, not credentials: AUGMENTS_CACHE_DIR, BLOCK_DIRECT_ACCESS, ENFORCE_CLOUDFLARE, ENV, REDIS_URL, WORKERS- Where it talks to
- augments.dev (its own)Also nextjs.org, react.dev, tailwindcss.com, tiangolo.com, cloudflare.com, mongodb-api.com — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names nextjs.org, react.dev, tailwindcss.com, tiangolo.com, cloudflare.com, mongodb-api.com as well as its own vendor. The guard injects GITHUB_TOKEN, MASTER_API_KEY only into requests to augments.dev (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-19 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Auto-update or dynamic fetch configuration; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
npx create-react-app my-appFix: Pin versions and sources; vendor anything fetched at install time.npm install next@latest react@latest react-dom@latestFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed."""File system event handler for hot-reloading framework configs."""Fix: Pin versions and sources; vendor anything fetched at install time.npx tailwindcss initFix: Pin versions and sources; vendor anything fetched at install time.assert validate_file_path("../../../etc/passwd") is FalseFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.".env", ".git", ".config", # Sensitive filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."eval(", "exec(", # Code executionFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.# Load environment variables from .env fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.urls = {Homepage = "https://augments.dev", Repository = "https://github.com/augmnt/augments-mcp-server", Issues = "https://github.com/augmnt/augments-mcp-server/issues"}Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for augments-mcp-server@2.0.2 as of 6 h ago. This is the package itself, not its dependencies.
What would make this Verified
1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim augmnt: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
- Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Python exec or eval of computed code≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.