Skills/PyPI/vecten-mcp

vecten-mcp@0.1.1

VERIFIED· install only

Publisher claims: "The MCP server of Vecten Open" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher vecten · publishing for 1 daysInstalls 225Last detonated 18 min ago
$claude mcp add vecten-mcp -- uvx vecten-mcp
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 43 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

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
VECTEN_MCP_SECRET_DIRConfiguration, not credentials: VECTEN_BUNDLE_COMMIT, VECTEN_ENV, VECTEN_FEEDBACK_MANIFEST, VECTEN_MCP_POOL_CAP, VECTEN_MCP_PUBLIC_URL, VECTEN_PROJECT_ROOT, VECTEN_PROVIDER
Where it talks to
no vendor host named in the codeAlso mcp.localhost — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names mcp.localhost as well as its own vendor. The guard injects VECTEN_MCP_SECRET_DIR only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx vecten-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; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 88/100 (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 · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.0sprocessexited 1: ModuleNotFoundError: No module named 'uvicorn'
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessexited 1: ModuleNotFoundError: No module named 'sqlalchemy'
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessexited 1: SyntaxError: multiple exception types must be parenthesized
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2sprocessexited 1: ModuleNotFoundError: No module named 'sqlalchemy'
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2sprocessexited 1: ModuleNotFoundError: No module named 'sqlalchemy'
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocessexited 1: ModuleNotFoundError: No module named 'sqlglot'
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sprocessexited 1: ModuleNotFoundError: No module named 'starlette'
0.4sprocess8 of 43 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.4sprocessscript backend runs setup only
0.4sprocessscript backend runs setup only
0.4sprocessno install scripts to re-run

Static findings

LOW
Dynamic module loadingtests/test_usage_tools.py:13 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(fixture)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/served.py:81 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/served.py:74 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Dynamic module loadingtests/test_apps_page.py:17 · Dynamic module loadingsession = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/test_usage_tools.py:12 · Dynamic module loadingfixture = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/test_app_listing.py:15 · Dynamic module loadingsurfaces_module = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/test_apps_page.py:18 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(session)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/served.py:33 · Dynamic module loadingdocker_util = importlib.util.module_from_spec(_spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/test_app_listing.py:16 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(surfaces_module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_app_sql.py:148 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"SELECT pg_read_file('/etc/passwd')",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Dynamic module loadingtests/served.py:35 · Dynamic module loading (importlib.loader.exec_module via provenance)_spec.loader.exec_module(docker_util)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈43 tok
1 file · 81 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.