Skills/PyPI/mcpm

mcpm@2.15.0

VERIFIED· not started

Publisher claims: "MCPM - Model Context Protocol Manager" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher pathintegral-institute · publishing for 593 daysInstalls 8,675Last detonated 4d ago
$claude mcp add mcpm -- uvx mcpm
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
ANYON_API_KEYGITHUB_TOKENOPENROUTER_API_KEY or --no-authConfiguration, not credentials: MCPM_DEBUG, MCPM_FORCE, MCPM_JSON_OUTPUT, MCPM_LOG_LEVEL, MCPM_NON_INTERACTIVE, SITE_URL
Where it talks to
mcpm.sh (its own)Also visualstudio.com, nodejs.org, openrouter.ai, chatxiv.org, docker.com, cursor.sh, 5ire.app, opencode.ai, trae.ai, codeium.com, huggingface.co — 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 visualstudio.com, nodejs.org, openrouter.ai, chatxiv.org, docker.com, cursor.sh, 5ire.app, opencode.ai, trae.ai, codeium.com, huggingface.co as well as its own vendor. The guard injects ANYON_API_KEY, GITHUB_TOKEN, OPENROUTER_API_KEY only into requests to mcpm.sh (and its subdomains) and refuses the rest.

$vet-skills run --secrets ANYON_API_KEY=mcpm.sh,GITHUB_TOKEN=mcpm.sh,OPENROUTER_API_KEY=mcpm.sh -- uvx mcpm

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 2026-11-11 and scored it 81/100 (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
npx invocation of non-well-known packagescripts/get_manifest.py:105 · npx invocation of non-well-known package — may execute untrusted code# npm type should use npx command with -y flagFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationsrc/mcpm/commands/update.py:55 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeNPX/UVX servers auto-update at runtime and are shown for informational purposes.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionscripts/generate_llm_txt.py:394 · File type combined with upload action — agent may exfiltrate local data filesprint(f"✅ Generated llm.txt at: {output_path}")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedsrc/mcpm/utils/git.py:47 · 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 detectedsrc/mcpm/core/tunnel.py:146 · Python subprocess execution detectedself.proc = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, start_new_session=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/mcpm/migration/v1_migrator.py:384 · npx invocation of non-well-known package — may execute untrusted code# URL-based server (SSE) - convert to npx command for typical MCP serversFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/mcpm/commands/inspect.py:175 · Python subprocess execution detectedreturncode = subprocess.call(cmd_parts)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/mcpm/commands/config.py:43 · npx invocation of non-well-known package — may execute untrusted codemcpm config set --key node_executable --value npx # Non-interactive modeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/mcpm/commands/client.py:783 · Python subprocess execution detectedsubprocess.run(["open", config_path] if os.uname().sysname == "Darwin" else ["xdg-open", config_path])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagescripts/get_manifest.py:228 · npx invocation of non-well-known package — may execute untrusted code- If README shows "npx package-name" → create npm entry with npx commandFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/mcpm/commands/inspect.py:81 · Python subprocess execution detectedreturncode = subprocess.call(cmd_parts)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/mcpm/commands/config.py:81 · npx invocation of non-well-known package — may execute untrusted code"description": "Default node executable for npx servers"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/mcpm/commands/config.py:65 · npx invocation of non-well-known package — may execute untrusted code"Select default node executable, it will be automatically applied when adding npx server with mcpm add",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/get_manifest.py:176 · npx invocation of non-well-known package — may execute untrusted codeNPXFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/mcpm/commands/doctor.py:71 · npx invocation of non-well-known package — may execute untrusted codeissues_found += _check_cli_tool("node", "Node.js", "Node.js not found - npx servers will not work")Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/mcpm/commands/doctor.py:190 · npx invocation of non-well-known package — may execute untrusted codeconsole.print(" • Install Node.js for npx server support")Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/mcpm/commands/update.py:244 · npx invocation of non-well-known package — may execute untrusted codeconsole.print(f" [cyan]{name:<22}[/] [blue]npx[/] auto-updates via npx ({source.package})")Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/mcpm/commands/update.py:382 · 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
npx invocation of non-well-known packagesrc/mcpm/core/source.py:95 · npx invocation of non-well-known package — may execute untrusted code"""Extract the npm package name from npx args, stripping flags like -y and @version suffixes."""Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/mcpm/commands/doctor.py:68 · npx invocation of non-well-known package — may execute untrusted code# 3. Check Node.js (for npx servers)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/mcpm/commands/edit.py:503 · Python subprocess execution detectedsubprocess.run(["open", config_path] if os.uname().sysname == "Darwin" else ["xdg-open", config_path])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcpm/commands/profile/inspect.py:130 · Python subprocess execution detectedreturncode = subprocess.call(cmd_parts)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcpm/commands/doctor.py:58 · Python subprocess execution detectedversion = subprocess.check_output([tool_path, "--version"], stderr=subprocess.DEVNULL).decode().strip()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/mcpm/core/source.py:132 · npx invocation of non-well-known package — may execute untrusted codereturn UnknownSource(reason="npx server but could not determine package name")Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈42 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 mcpm@2.15.0 as of 4d ago. This is the package itself, not its dependencies.