tracehub-mcp@0.13.2
CAUTION· not startedPublisher claims: "MCP server for querying OpenTelemetry traces across multiple observability backends (Jaeger, Tempo, Traceloop, Datadog, and more) for LLM application debugging" 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
MCP_HTTP_BEARER_TOKENSENTRY_DSNor--http-bearer-token/--allow-unauthenticated-httpConfiguration, not credentials: CZ_PRE_NEW_VERSION, MAX_TRACES_PER_QUERY, OTEL_EXPORTER_OTLP_ENDPOINT, OTEL_SERVICE_NAME, OTEL_TRACES_SAMPLER, QUERY_CACHE_MAX_ENTRIES, QUERY_CACHE_TTL_SECONDS, SLOW_REQUEST_THRESHOLD_MS- Where it talks to
- no vendor host named in the codeAlso sentry.io, traceloop.com, githubusercontent.com, backend.test, datadoghq.com, datadoghq.eu, honeycomb.io, newrelic.com, tempo.internal, h.test — 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 sentry.io, traceloop.com, githubusercontent.com, backend.test, datadoghq.com, datadoghq.eu, honeycomb.io, newrelic.com, tempo.internal, h.test as well as its own vendor. The guard injects MCP_HTTP_BEARER_TOKEN, SENTRY_DSN 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 (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-20 and scored it 60/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Collapsed <details> block carrying instructions; Collapsed <details> block carrying instructions. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
**Environment Variables** (see [.env.example](.env.example)):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.<summary><b>Grafana Tempo</b></summary> ```bash BACKEND_TYPE=tempo BACKEND_URL=http://localhost:3200 ``` No API key required for a local/self-hosted install. SeFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.<summary><b>Traceloop</b></summary> ```bash BACKEND_TYPE=traceloop BACKEND_URL=https://api.traceloop.com BACKEND_API_KEY=your_api_key_here ``` The API key encodFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…s own `RichHandler`s at import), and neither do uvicorn's, so records they emit bypass the filter - which is why `server._handle_tool_error` judges the whole exception chain (`_…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.…h `FASTMCP_CHECK_FOR_UPDATES=stable` or `prerelease` (process environment or a `.env` in the working directory; their own value is never overridden - an `os.environ…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.<summary><b>Jaeger</b></summary> ```bash BACKEND_TYPE=jaeger BACKEND_URL=http://localhost:16686 ``` No API key required. **`search_traces` and `search_spans_tooFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.unset because .env.example ships `SECONDARY_BACKEND_TYPE=` with noFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.<summary><b>Datadog</b></summary> ```bash BACKEND_TYPE=datadog # US site (default): https://api.datadoghq.com # EU site: https://api.datadoghq.eu BACKEND_URL=htFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.chown -R mcpuser:mcpuser /appFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.environment variable or a .env file), so an operator's own "stable",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# `MCP_HTTP_BEARER_TOKEN=` in a compose file or .env started aFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# literal "@" inside the password (`https://u:p@[email protected]/` is host h.test,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.BackendConfig(type="jaeger", url=HttpUrl(f"https://u:{VFY_MARKER}@h.test"))Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# - .env files mounted at runtimeFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.BackendConfig(type="jaeger", url=HttpUrl("http://100.100.100.200/latest/meta-data/"))Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.BackendConfig(type="jaeger", url=HttpUrl("http://168.63.129.16/machine?comp=goalstate"))Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.BackendConfig(type="jaeger", url=HttpUrl("http://169.254.169.254/latest/meta-data/"))Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.config = BackendConfig(type="jaeger", url=HttpUrl("http://10.0.0.5:16686"))Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.BackendConfig(type="jaeger", url=HttpUrl("http://168.63.129.16/machine?comp=goalstate"))Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.monkeypatch.setenv("SECONDARY_BACKEND_URL", f"https://u:{VFY_MARKER}@h.test")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.BackendConfig(type="jaeger", url=HttpUrl("http://169.254.170.2/v2/metadata"))Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.config.apply_cli_overrides(backend_url=f"https://u:{VFY_MARKER}@h.test")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.monkeypatch.setenv("BACKEND_URL", f"https://{LONG_USER}:{LONG_PASSWORD}@{tail}")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.BackendConfig(type="jaeger", url=HttpUrl("http://100.100.100.200/latest/meta-data/"))Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.BackendConfig(type="jaeger", url=HttpUrl(f"http://u:{VFY_MARKER}@169.254.169.254/"))Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
20 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
- Unclaimed publisher≈ +8 on the totalClaim mcpsmiths: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- URL with embedded credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.