muscle-memory-mcp@0.1.1
VERIFIED· not startedPublisher claims: "MCP server that gives your agent a library of its own tested, reusable scripts." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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 code
- 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.
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 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 deviationsStatic findings
subprocess.run(["git", "-C", str(root), "config", "--local", PUSH_KEY, "true" if push else "false"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run(["git", "-C", str(project), "rev-parse", "--git-path", "info/exclude"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "-C", str(self.d), "config", "user.email", "t@t"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run(argv, cwd=str(cwd), env=child_env, capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "init", "-q", str(self.d)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.g = lambda *a: subprocess.run(["git", "-C", str(self.personal), *a], check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."assert subprocess.check_output([sys.executable, os.environ['MM_SCRIPT']]).decode().strip() == 'ok'\n")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."assert subprocess.check_output([shutil.which('bash'), os.environ['MM_SCRIPT']]).decode().strip() == 'hi'\n")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."r = subprocess.run([sys.executable, os.environ['MM_SCRIPT'], 'Jo'], capture_output=True, text=True)\n"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out." out = subprocess.run([sys.executable, os.environ['MM_SCRIPT']], capture_output=True, encoding='utf-8').stdout\n"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "init", str(root)], check=True, capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.for bad in ["../etc/passwd", "missing.py", "INDEX.md", "../mm.py"]:Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.subprocess.run(["git", "-C", str(self.d), "commit", "-q", "--allow-empty", "-m", "init"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "clone", "--", remote, str(root)], check=True, capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "-C", str(self.d), "config", "user.name", "t"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run(["git", "-C", str(cwd), "rev-parse", "--show-toplevel"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out." out = subprocess.run([sys.executable, os.environ['MM_SCRIPT']], capture_output=True, encoding='utf-8').stdout\n"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, str(Path(__file__).resolve().parents[1] / 'scripts' / 'double.py'), '21'],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run([sys.executable, "-m", "muscle_memory_mcp"], input="\n".join(lines) + "\n",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out." out = subprocess.run([sys.executable, os.environ['MM_SCRIPT']], capture_output=True, encoding='utf-8').stdout\n"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "-C", str(project), "config", "user.name", "Task Test"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "init", "--bare", str(bare)], check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."assert subprocess.check_output([sys.executable, os.environ['MM_SCRIPT']]).decode().strip() "Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "init", "-q", str(project)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.f" def test_run(self): self.assertEqual(subprocess.check_output([{bash_path!r}, os.environ['MM_SCRIPT'], 'Jo'], encoding='utf-8').strip(), 'hi Jo')\n"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, script, '21'], capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "-C", str(self.d), "config", "user.name", "t"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "-C", str(self.d), "config", "user.name", "t"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.## Add to your AGENTS.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.out = subprocess.run([sys.executable, "-m", "muscle_memory_mcp"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "-C", str(project), "config", "user.email", "[email protected]"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([UV, "build", *extra_args, "--out-dir", str(self.dist)],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "-C", str(self.d), "config", "user.email", "t@t"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.self.branch = subprocess.check_output(["git", "-C", str(self.personal), "branch", "--show-current"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "init", "-q", str(self.d)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Add this standing rule to your `AGENTS.md`, `CLAUDE.md`, `SOUL.md` or equivalent agent instructions:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.## Add to your AGENTS.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.subprocess.run(["git", "-C", str(self.d), "config", "user.email", "t@t"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.self.assertLess(self.text.index("## Install"), self.text.index("## Add to your AGENTS.md"))Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."assert subprocess.check_output([sys.executable, os.environ['MM_SCRIPT']]).decode().strip() == 'safe'\n")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "-C", str(self.personal), *args], check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.GOOD_TEST = "import os, subprocess, sys\nassert subprocess.check_output([sys.executable, os.environ['MM_SCRIPT']]).decode().strip() == 'ok'\n"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.remote_head = subprocess.check_output(["git", "--git-dir", str(self.remote), "rev-parse", self.branch],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "init", "-q", str(self.d)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."## Add to your AGENTS.md"):Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.subprocess.run(["git", "-C", str(self.d), "commit", "-q", "--allow-empty", "-m", "init"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run(["git", "-C", str(cwd), *args], capture_output=True, encoding="utf-8",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "init", "--bare", str(self.remote)], check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Add this standing rule to your `AGENTS.md`, `CLAUDE.md`, `SOUL.md` or equivalent agent instructions:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."## Install", "## Add to your AGENTS.md", "## First run and storage",Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
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 muscle-memory-mcp@0.1.1 as of 39 h ago. This is the package itself, not its dependencies.