riveter-mcp-server@0.3.7
VERIFIEDPublisher claims: "MCP server for the Riveter API — connects Claude to Riveter's enrichment, scraping, and monitoring tools" Observed in sandbox: calls docs.riveterhq.com only, touches nothing outside the project, writes no memory.
Coverage
Started with a decoy RIVETER_API_KEY; tool list observed. Tool calls with a real credential not tested.- Tested
- server startup with a tagged decoy in RIVETER_API_KEY · MCP initialize and tools/list · every tool description, for hidden instructions · where the decoy credential went · every file read, file written and host contacted by what ran
- Not tested
- what the tools do when called with a real credential
- Needs
- RIVETER_API_KEY — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.
Before you give it your token
- It will ask for
OAUTH_ISSUER_URLRIVETER_API_KEYConfiguration, not credentials: MCP_PATH, MCP_PUBLIC_URL, OPENAI_APPS_CHALLENGE, PROTECTED_RESOURCE_METADATA_PATH, RIVETER_API_BASE_URL, RIVETER_OPENAPI_URL, SPEC_REFRESH_INTERVAL_MS, TOOL_PROPERTY_NAME_PATTERN- Where it talks to
- riveterhq.com (its own)
- What we saw when it ran
- no credential files read · reached only docs.riveterhq.com (its own)
- What we could not test
- what the tools do when called with a real credential
Connect it with a scoped credential, under the guard. It asks for OAUTH_ISSUER_URL, RIVETER_API_KEY and talks to riveterhq.com. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 0.3.6
vet-skills diff riveter-mcp-server 0.3.6 0.3.7This version reaches for something 0.3.6 did not: 1 new tool (submit_feedback) · 1 rewritten tool descriptor (get_extraction). Compared from the two recorded runs, not from source.
- New tools
- submit_feedback
- Rewritten tool descriptors
- get_extraction
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-19 and scored it 95/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: calls docs.riveterhq.com only, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 45 s · 2 scenarios · 0 deviationsStatic findings
No findings across 1,084 lines in 14 files.
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 riveter-mcp-server@0.3.7 as of 14 h ago. This is the package itself, not its dependencies.