roost-mcp@0.2.2
VERIFIED· not startedPublisher claims: "Model Context Protocol server for Roost — credit underwriting and per-spend decisioning for AI agents." 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
ROOST_CORPUS_TOKENROOST_CORPUS_TOKEN_FILEROOST_SDK_OPERATOR_API_KEYSENTRY_DSNor--operator-api-keyConfiguration, not credentials: ROOST_20X_DB_PATH, ROOST_CORPUS_API_BASE, ROOST_CORPUS_SOURCE, ROOST_MCP_PYTHON, ROOST_SDK_ACTOR_LABEL, ROOST_SDK_AGENT_ID, ROOST_SDK_API_BASE, SENTRY_ENVIRONMENT, SENTRY_RELEASE, SENTRY_TRACES_SAMPLE_RATE, SERVICE_NAME- Where it talks to
- roostcapital.ai (its own)Also fly.dev — 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 fly.dev as well as its own vendor. The guard injects ROOST_CORPUS_TOKEN, ROOST_CORPUS_TOKEN_FILE, ROOST_SDK_OPERATOR_API_KEY, SENTRY_DSN only into requests to roostcapital.ai (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 2026-11-16 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
``backend/app/eval/cert_corpus/<version>.json`` — computed purely from thisFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.# explicit mode and chmod defensively afterward.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.server_proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# umask-masked and a pre-existing dir keeps its old mode, so chmodFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.as a bare PYTHONPATH addition: ``mcp-server/.venv`` has ``httpx``,Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.bootstrap = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# umask-masked and a pre-existing dir keeps its old mode, so chmodFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.# explicit mode and chmod defensively afterward.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.``mcp-server/.venv`` (``mcp/server/streamable_http.py``,Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.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.