unicefstats-mcp@1.5.5
VERIFIED· not startedPublisher claims: "MCP server for UNICEF child development statistics — 790+ child-focused indicators, 200+ countries, disaggregations by sex/age/wealth/residence. No API key required." 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: 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
BRAVE_API_KEYFRED_API_KEYGITHUB_PERSONAL_ACCESS_TOKENGOOGLE_API_KEYHF_TOKENLINKEDIN_CLIENT_SECRETTWITTER_ACCESS_SECRETTWITTER_ACCESS_TOKENTWITTER_API_KEYTWITTER_API_SECRETZOTERO_API_KEY- Where it talks to
- no vendor host named in the codeAlso nodejs.org, python.org, gitmcp.io, unicef.org — 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 nodejs.org, python.org, gitmcp.io, unicef.org as well as its own vendor. The guard injects BRAVE_API_KEY, FRED_API_KEY, GITHUB_PERSONAL_ACCESS_TOKEN, GOOGLE_API_KEY, HF_TOKEN, LINKEDIN_CLIENT_SECRET, TWITTER_ACCESS_SECRET, TWITTER_ACCESS_TOKEN, TWITTER_API_KEY, TWITTER_API_SECRET, ZOTERO_API_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 (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-20 and scored it 84/100 (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 · 2 scenarios · 0 deviationsStatic findings
# markdownlint-cli2 is fast, no install step needed (npx fetches it).Fix: Pin versions and sources; vendor anything fetched at install time.ΔEQAFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.mcp_figures = importlib.util.module_from_spec(_spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.ΔwavesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.log "npx available"Fix: Pin versions and sources; vendor anything fetched at install time.ΔwavesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.run: npx --yes [email protected] "**/*.md" "#internal/**"Fix: Pin versions and sources; vendor anything fetched at install time.if ! command -v npx &>/dev/null; thenFix: Pin versions and sources; vendor anything fetched at install time.sudo mv /tmp/mcp-publisher /usr/local/bin/mcp-publisherFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell._spec.loader.exec_module(mcp_figures)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# Environment variables needed (set in your shell profile or .env):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.err "npx not found."Fix: Pin versions and sources; vendor anything fetched at install time.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.