Skills/PyPI/agentic-mcp-solver

agentic-mcp-solver@4.5.0

VERIFIED· not started

Publisher claims: "LLM-driven constraint solving (SAT, MaxSAT, SMT, CP, ASP) on top of agentic-python-coder" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher stefan-szeider-stefan · publishing for 369 daysInstalls 533Last detonated 15 min ago
$claude mcp add agentic-mcp-solver -- uvx agentic-mcp-solver
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
OPENROUTER_API_KEYConfiguration, not credentials: MCP_SOLVER_DEV, MCP_SOLVER_STATS
Where it talks to
no vendor host named in the codeAlso astral.sh, openrouter.ai — 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
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 astral.sh, openrouter.ai as well as its own vendor. The guard injects OPENROUTER_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx agentic-mcp-solver

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 4.2.0

vet-skills diff agentic-mcp-solver 4.2.0 4.5.0

In the sandbox, this version reached for nothing 4.2.0 did not. Compared from the two recorded runs, not from source.

4.2.0 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 2026-11-22 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
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsminion/src/mcp_minion/cli.py:459 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Environment first, then FOLDER/.env, then ~/.mcp-minion.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsminion/src/mcp_minion/cli.py:411 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesotherwise it is loaded from FOLDER/.env (run folder),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_solver/agent/harness.py:78 · Python subprocess execution detected"""``subprocess.run(cmd, capture_output=True, text=True, ...)`` whoseFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_solver/agent/cli.py:491 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python exec or eval of computed codesrc/mcp_solver/agent/harness.py:352 · Python exec or eval of computed codeprint("\nsolver valid/run tokens(avg) exec(avg) wall(avg)", file=sys.stderr)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
HIGH
Access to sensitive file pathssrc/mcp_solver/agent/cli.py:224 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesextra_dotenv=(Path.home() / ".config" / "coder" / ".env",),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandsrc/mcp_solver/agent/harness.py:40 · Process kill command — agent can terminate processes# Seconds a CLI gets after SIGTERM (to kill its re-executed program) beforeFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/mcp_solver/agent/mcp_server.py:271 · Process kill command — agent can terminate processesHosts often kill the server without a clean shutdown (claude -p does),Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/unit/test_harness.py:264 · Process kill command — agent can terminate processes# --- timeouts kill the whole process tree ----------------------------------Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/unit/test_problems.py:28 · Python subprocess execution detectedproc = subprocess.run(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_engine.py:196 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesmonkeypatch.setenv("UV_ENV_FILE", "/home/u/.env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathsminion/tests/test_cli.py:724 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""find_api_key: environment, folder/.env, extra files, ~/.mcp-minion."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsminion/src/mcp_minion/env.py:19 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesOrder: the process environment, then ``folder/.env`` (if ``folder`` isFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/unit/test_cli.py:316 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesengine_env = tmp_path / ".config" / "coder" / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_solver/agent/cli.py:217 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesorder are the environment, ``~/.config/coder/.env`` (engine) andFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)tests/unit/test_mcp_server.py:1138 · MCP server using network transport (SSE/HTTP) — data sent over networkassert mcp_server._episode["self_check"] == "passed"Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Access to sensitive file pathsminion/tests/test_cli.py:753 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(folder / ".env").write_text("OPENROUTER_API_KEY=from-folder\n")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_solver/agent/harness.py:89 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathsminion/tests/test_cli.py:736 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(tmp_path / ".env").write_text("OPENROUTER_API_KEY=from-folder\n")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathspyproject.toml:69 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"**/.env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_solver/agent/cli.py:706 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Set OPENROUTER_API_KEY or put it in ~/.config/coder/.env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/unit/test_harness.py:269 · Python subprocess execution detectedchild = subprocess.Popen([sys.executable, "-c", "import time; time.sleep(600)"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsminion/src/mcp_minion/env.py:29 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filescandidates.append(Path(folder) / ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/unit/test_cli.py:800 · Python subprocess execution detected"child = subprocess.Popen("Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Coercive compliance languagesrc/mcp_solver/templates/clingo.md:37 · Coercive compliance language · informational: not an instruction file**FUNDAMENTAL RULE**: You must follow these basic syntax rules. Errors here are the most common cause of failures.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedtests/unit/test_mcp_server.py:1733 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathsminion/tests/test_cli.py:762 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(tmp_path / ".env").write_text("OTHER_KEY=x\n")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_solver/agent/cli.py:701 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesf"Set {model.api_key_env} or put it in ~/.config/coder/.env."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Dynamic module loadingsrc/mcp_solver/agent/mcp_server.py:213 · Dynamic module loading_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/unit/test_cli.py:835 · Dynamic module loading" 'found': [m for m in mods if importlib.util.find_spec(m)]}))\n"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/unit/test_harness.py:369 · Process kill command — agent can terminate processes# harness's SIGTERM makes the CLI kill the program's session before theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathsminion/tests/test_cli.py:780 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(folder / ".env").write_text("OPENROUTER_API_KEY=sk-folder\n")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathsminion/e2e_tests/test_problems_e2e.py:11 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesminute per problem. Requires OPENROUTER_API_KEY (env, cwd .env, orFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandsrc/mcp_solver/agent/cli.py:620 · Process kill command — agent can terminate processes"""Send *sig* to *proc*'s process group (POSIX); elsewhere kill *proc*.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/unit/test_cli.py:707 · Process kill command — agent can terminate processes# Done is no real process: record the group kill after its exit.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/unit/test_cli.py:762 · Python subprocess execution detected"child = subprocess.Popen("Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Dynamic module loadingsrc/mcp_solver/agent/mcp_server.py:215 · Dynamic module loading (importlib.loader.exec_module via provenance)_spec.loader.exec_module(_module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_solver/agent/harness.py:303 · Python subprocess execution detectedcheck = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedminion/e2e_tests/test_problems_e2e.py:75 · Python subprocess execution detectedproc = 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/unit/test_cli.py:948 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/mcp_solver/agent/cli.py:473 · Process kill command — agent can terminate processesthread), so a caller can kill the run from elsewhere. RaisesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/unit/test_cli.py:838 · Dynamic module loadingassert importlib.util.find_spec("mcp_minion") and importlib.util.find_spec("pytest")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈61 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

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