Skills/PyPI/roost-mcp

roost-mcp@0.2.2

VERIFIED· not started

Publisher 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.

Registry PyPI (MCP server)Publisher roostcapital · publishing for 14 daysInstalls 347Last detonated 1 h ago
$claude mcp add roost-mcp -- uvx roost-mcp
WatchReport an issue

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_DSN or --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.

$vet-skills run --secrets ROOST_CORPUS_TOKEN=roostcapital.ai,ROOST_CORPUS_TOKEN_FILE=roostcapital.ai,ROOST_SDK_OPERATOR_API_KEY=roostcapital.ai,SENTRY_DSN=roostcapital.ai -- uvx roost-mcp

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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionintegrations/20x/eval/run_certification.py:82 · File type combined with upload action — agent may exfiltrate local data files``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.
AST07
MEDIUM
File permission modification commandsrc/roost_mcp_common/anon_token.py:36 · File permission modification command — agent changes file ownership/permissions# explicit mode and chmod defensively afterward.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedtests/test_qa_integration.py:199 · Python subprocess execution detectedserver_proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandsrc/roost_mcp_common/anon_token.py:34 · File permission modification command — agent changes file ownership/permissions# 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.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_qa_integration.py:19 · MCP server using network transport (SSE/HTTP) — data sent over networkas 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.
AST04
MEDIUM
Python subprocess execution detectedtests/test_qa_integration.py:184 · Python subprocess execution detectedbootstrap = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandpublish/src/roost_mcp_common/anon_token.py:34 · File permission modification command — agent changes file ownership/permissions# 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.
AST05
MEDIUM
File permission modification commandpublish/src/roost_mcp_common/anon_token.py:36 · File permission modification command — agent changes file ownership/permissions# explicit mode and chmod defensively afterward.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)src/roost_remote_mcp/server.py:12 · MCP server using network transport (SSE/HTTP) — data sent over network``mcp-server/.venv`` (``mcp/server/streamable_http.py``,Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04

Cost to the agent

Instructions loaded
≈60 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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.