Skills/PyPI/agent-host-mcp

agent-host-mcp@0.2.2

VERIFIED· install only

Publisher claims: "Connect Codex sessions, remote execution, and project knowledge to MCP clients." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher pypi · publishing for 731 daysInstalls 1,194Last detonated 25 min ago
$claude mcp add agent-host-mcp -- uvx agent-host-mcp
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 58 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
MCP_TOKENConfiguration, not credentials: AGENT_HOST_MCP_HOME, AGENT_MCP_CODEX_BIN, AGENT_MCP_DB, AGENT_MCP_PROJECT_DIR, AGENT_MCP_TEST_INLINE, CODEX_HOME
Where it talks to
no vendor host named in the code
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. It asks for MCP_TOKEN and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --net declared -- uvx agent-host-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 2026-11-22 and scored it 84/100 (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
0.2sprocessexited 1: ModuleNotFoundError: No module named 'mcp'
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocessexited 1: ModuleNotFoundError: No module named 'mcp'
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sprocessexited 1: ModuleNotFoundError: No module named 'dotenv'
0.4sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.6sprocessexited 1: ModuleNotFoundError: No module named 'agent_mcp'
0.6sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.7sprocessexited 1: RuntimeError: Notebook supervisor requires an isolated process group
0.7sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.8sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.9sprocessexited 1: ModuleNotFoundError: No module named 'agent_mcp'
0.9sprocessbundled script run in the sandbox with no arguments · not named in the instructions
1.0sprocess8 of 58 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
1.1sprocessscript backend runs setup only
1.1sprocessscript backend runs setup only
1.1sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedagent_mcp/openwiki_runtime.py:60 · Python subprocess execution detectedsubprocess.run(['npm', 'ci', '--omit=dev', '--ignore-scripts', '--no-audit', '--no-fund'],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedagent_mcp/cell_worker.py:46 · Python subprocess execution detectedprocess = subprocess.run(source.lstrip()[1:], shell=True, executable='/bin/sh', stdin=subprocess.DEVNULL)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedagent_mcp/wiki_ingest.py:94 · Python subprocess execution detectedresult = subprocess.run(['node', str(Path(__file__).with_name('openwiki_ingest.mjs')),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsagent_mcp/auth.py:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesraise ValueError("Set a valid --api_key, config api_key, or MCP_TOKEN in .env/the environment before starting agent-host-mcp.")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedagent_mcp/wiki.py:147 · Python subprocess execution detectedsubprocess.run(["node", str(Path(__file__).with_name("openwiki_export.mjs")),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedagent_mcp/screen_runtime.py:154 · Python subprocess execution detectedsubprocess.run([self.executable(), "-S", screen_id, "-X", "quit"], env=self.environment(),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 codeagent_mcp/cell_worker.py:55 · Python exec or eval of computed codevalue = eval(compile(ast.Expression(expression.value), '<execute>', 'eval'), namespace)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedagent_mcp/process_guard.py:16 · Python subprocess execution detectedos.execvpe(sys.argv[2], sys.argv[2:], os.environ)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedagent_mcp/wiki_ingest.py:20 · Python subprocess execution detectedreturn subprocess.run(['git', '-c', 'core.hooksPath=/dev/null', *arguments], cwd=workspace,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedagent_mcp/make_job.py:14 · Python subprocess execution detectedprocess = subprocess.run([binary, "-C", directory, action], stdin=subprocess.DEVNULL,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedagent_mcp/screen_runtime.py:142 · 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 detectedagent_mcp/screen_runtime.py:117 · Python subprocess execution detectedresult = subprocess.run([self.executable(), "-S", screen_id, "-Q", "select", "."],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedagent_mcp/screen_runtime.py:131 · Python subprocess execution detectedresult = subprocess.run(command, env=self.environment(), stdin=subprocess.DEVNULL,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 codeagent_mcp/cell_worker.py:53 · Python exec or eval of computed codeexec(compile(tree, '<execute>', 'exec'), namespace)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedagent_mcp/skills/upload-files/SKILL.md:52 · Python subprocess execution detectedsubprocess.run(command, input="Authorization: Bearer " + os.environ["MCP_TOKEN"] + "\n",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsagent_mcp/auth.py:16 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Explicit API key wins, then exported MCP_TOKEN, then working-directory .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 pathsagent_mcp/auth.py:19 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filestoken = dotenv_values(env_file or Path.cwd() / ".env", interpolate=False).get("MCP_TOKEN")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈4,342 tok
5 files · 70 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.