opencode-hermes-mcp@0.5.1
CAUTION· not startedPublisher claims: "Deterministic MCP controller between Hermes (supervisor LLM) and the permanent OpenCode server. OpenCode pin defined in opencode_hermes_mcp/pin.txt (currently 1.18.31)." 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: Caution 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
OPENCODE_API_KEYOPENCODE_SERVER_CREDENTIALSUNSLOTH_API_KEYConfiguration, not credentials: OPENCODE_MCP_HOME, OPENCODE_MCP_PID_FILE, OPENCODE_MCP_REPO, OPENCODE_MCP_STATE_DIR, OPENCODE_MCP_TEST_DIR, OPENCODE_SERVER_URL, OPENCODE_SERVER_USERNAME- Where it talks to
- no vendor host named in the codeAlso opencode.ai — 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 opencode.ai as well as its own vendor. The guard injects OPENCODE_API_KEY, OPENCODE_SERVER_CREDENTIALS, UNSLOTH_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.
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 2026-11-13 and scored it 76/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe-to-shell pattern. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
cmd = f"curl -fsSL https://opencode.ai/install | bash -s -- --version {version}"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.cmd = f"curl -fsSL https://opencode.ai/install | bash -s -- --version {version}"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.state.installed.append("server credentials (generated, chmod 600)")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.subprocess.run(cmd, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["uv", "pip", "install", "--python", venv_py, *args], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.state.console.print(f"[dim]would write {cred_file} (generated token, chmod 600)[/dim]")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.# PID file (used by tests to kill the controller process mid-turn to simulateFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.subprocess.run([sys.executable, "-m", "venv", str(venv_dir)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([venv_py, "-m", "pip", "install", *args], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.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 opencode-hermes-mcp@0.5.1 as of 16 h ago. This is the package itself, not its dependencies.
What would make this Verified
4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Unclaimed publisher≈ +8 on the totalClaim arthurhtr: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.