Skills/PyPI/kestrel-feature-mcp

kestrel-feature-mcp@0.17.0

VERIFIED· not started

Publisher claims: "Model Context Protocol (MCP) server management for Kestrel Sovereign agents" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher pypi · publishing for 723 daysInstalls 31Last detonated 2d ago
$claude mcp add kestrel-feature-mcp -- uvx kestrel-feature-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
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso docker.com, sandbox.invalid — 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 under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx kestrel-feature-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 2026-11-12 and scored it 87/100 (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
MCP server using network transport (SSE/HTTP)kestrel_feature_mcp/catalog.toml:52 · MCP server using network transport (SSE/HTTP) — data sent over network# Use: docker run -p 8000:8000 supercorp/supergateway --stdio "mcp-server-xxx" --outputTransport streamableHttpFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
URL to the cloud instance metadata addresstests/unit/test_remote_mcp.py:174 · URL to the cloud instance metadata address — reads the VM's credentials"http://remote.example/mcp", "https://127.0.0.1/mcp", "https://169.254.169.254/mcp",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
File type combined with upload actiontests/unit/test_oauth_grants.py:72 · File type combined with upload action — agent may exfiltrate local data filesfrom kestrel_sovereign.storage.db.postgres import PostgresBackendFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedtests/browser/conftest.py:45 · Python subprocess execution detectedresult = subprocess.run(["node", "web/test-support/parent-browser-build.mjs"], cwd=REPOSITORY,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/unit/test_remote_mcp.py:176 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"file:///etc/passwd", "https:relative", "https://remote.example/mcp#fragment",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedkestrel_feature_mcp/registry.py:263 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedkestrel_feature_mcp/gateway.py:202 · Python subprocess execution detectedresult = 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/browser/run_native.py:84 · Python subprocess execution detectednames = subprocess.check_output(['git', 'ls-files', '-z'], cwd=repository).decode().split('\0')Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedkestrel_feature_mcp/gateway.py:278 · Python subprocess execution detectedself.process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedkestrel_feature_mcp/gateway.py:189 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL with embedded credentialstests/unit/test_remote_mcp.py:175 · URL with embedded credentials — may be phishing or credential leaking"https://user:[email protected]/mcp", "https://[not-ipv6]/mcp",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07

Cost to the agent

Instructions loaded
≈399 tok
2 files · 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 kestrel-feature-mcp@0.17.0 as of 2d ago. This is the package itself, not its dependencies.