mcp-langfuse@0.2.0
VERIFIED· install onlyPublisher claims: "Read-only Model Context Protocol server that enables querying Langfuse v4 events-only deployments for traces rebuilt as trees, sessions, searchable observations, scores, server-side metrics aggregates and managed prompts. Supports many projects from one server, taking a project argument per data tool and verifying each key against the project it is filed under before any data is read." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What this means for the label: Verified 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
LANGFUSE_SECRET_KEYConfiguration, not credentials: GIT_COMMIT, GIT_COMMIT_DATE, LANGFUSE_ALLOW_WRITES, LANGFUSE_BASE_URL, LANGFUSE_DB_URL, LANGFUSE_DEBUG, LANGFUSE_HOST, LANGFUSE_KEYS_FILE, LANGFUSE_MAX_RETRIES, LANGFUSE_PROJECT, LANGFUSE_PROJECTS, LANGFUSE_PUBLIC_KEY, LANGFUSE_SALT- Where it talks to
- no vendor host named in the codeAlso langfuse.com — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names langfuse.com as well as its own vendor. The guard injects LANGFUSE_SECRET_KEY only into requests to the host you bind (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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-11 and scored it 85/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
# and npx picks the bin by name: it only forgives a mismatch while theFix: Pin versions and sources; vendor anything fetched at install time.# picked up. For any server that reads one (~/.npmrc, ~/.aws/credentials),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- name: npx can resolve a bin 🔒Fix: Pin versions and sources; vendor anything fetched at install time.# picked up. For any server that reads one (~/.npmrc, ~/.aws/credentials),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Every client config in the wild spells this server `npx -y <package>`,Fix: Pin versions and sources; vendor anything fetched at install time.`${path} holds secret keys and is readable by other users. Run: chmod 600 ${path}`,Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.console.error('npx cannot pick a bin for ' + pkg.name + ': none of [' +Fix: Pin versions and sources; vendor anything fetched at install time.# picked up. For any server that reads one (~/.npmrc, ~/.aws/credentials),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.expect(config.problems.join(" ")).toContain("chmod 600");Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.run: npm install -g npm@latestFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.