provellm-mcp@2.1.2
VERIFIED· not startedPublisher claims: "ProveLLM MCP Gateway — every MCP tool call checked against an agent passport, and signed into a receipt." 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
PROVELLM_API_KEYConfiguration, not credentials: PROVELLM_AGENT, PROVELLM_API, PROVELLM_ATTEST_OUTPUT, PROVELLM_CHAIN_ID, PROVELLM_MCP_HEADERS, PROVELLM_MCP_TIMEOUT, PROVELLM_MCP_URL, PROVELLM_NO_TOOL_MANIFEST, PROVELLM_PARENT_RUN_ID, PROVELLM_PURPOSE, PROVELLM_TEAM, PROVELLM_USER- Where it talks to
- no vendor host named in the codeAlso linear.app, provingx.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
- 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 linear.app, provingx.com as well as its own vendor. The guard injects PROVELLM_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 2026-11-15 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 · 2 scenarios · 0 deviationsStatic findings
# kill signal interrupts Python mid-call, which is common — many processFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.provellm-mcp --agent fs-agent -- npx -y @modelcontextprotocol/server-filesystem /pathFix: Pin versions and sources; vendor anything fetched at install time.own. A kill signal is different: it lands mid-call, and the receiptFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# kill landing in that gap silently drops the one receipt for the call thatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# chmod is never the wide one.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.self._child = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.pins the INSTRUCTION rather than the code: `npx -y @some/server` isFix: 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
No advisories in OSV for provellm-mcp@2.1.2 as of 22 min ago. This is the package itself, not its dependencies.