ha-mcp-dev@9.3.0.dev3663
CAUTION· not startedPublisher claims: "Configure and automate Home Assistant with Claude, ChatGPT, and other AI assistants." 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
HOMEASSISTANT_TOKENMCP_SECRET_PATHMCP_SETTINGS_SECRET_PATHOIDC_CLIENT_SECRETOIDC_JWT_SIGNING_KEYOIDC_VERIFY_ID_TOKENSUPERVISOR_TOKENConfiguration, not credentials: FLAG, FORWARDED_ALLOW_IPS, HA_MCP_BUILD_VERSION, HA_MCP_CONFIG_DIR, HA_MCP_DISABLE_SETTINGS_UI, HA_MCP_EMBEDDED, HAMCP_DEV_SECURITY_POLICY_ACCESS, HAMCP_ENV_FILE, HOMEASSISTANT_URL, MCP_BASE_URL, MCP_HEALTHZ, MCP_HOST, MCP_PORT, OIDC_ALLOWED_CLIENT_REDIRECT_URIS, OIDC_AUDIENCE, OIDC_CLIENT_ID, OIDC_CONFIG_URL, SUPERVISOR_BASE_URL- Where it talks to
- no vendor host named in the codeAlso homeassistant.local, your-tunnel.com, trycloudflare.com, home-assistant.io, claude.com, cloudflare.com, qc-h.net — 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 homeassistant.local, your-tunnel.com, trycloudflare.com, home-assistant.io, claude.com, cloudflare.com, qc-h.net as well as its own vendor. The guard injects HOMEASSISTANT_TOKEN, MCP_SECRET_PATH, MCP_SETTINGS_SECRET_PATH, OIDC_CLIENT_SECRET, OIDC_JWT_SIGNING_KEY, OIDC_VERIFY_ID_TOKEN, SUPERVISOR_TOKEN 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.
What changed since 9.3.0.dev3541
vet-skills diff ha-mcp-dev 9.3.0.dev3541 9.3.0.dev3663In the sandbox, this version reached for nothing 9.3.0.dev3541 did not. Compared from the two recorded runs, not from source.
9.3.0.dev3541 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 2026-11-21 and scored it 73/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Collapsed <details> block carrying instructions. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
env_path = project_root / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Fallback to default .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.<summary><b>🐧 Linux</b></summary> Anthropic doesn't ship Claude Desktop for Linux, so pick one path: **Claude Desktop** — free, via the community build: 1. InsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.(includes values loaded from ``.env`` via ``load_dotenv`` atFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- Or create a .env file in the project directory (copy from .env.example)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# a warning, since this is a security kill switch and failing open on a typoFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.missing.append(" - MCP_BASE_URL (e.g., https://your-tunnel.trycloudflare.com)")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.security kill switch it fails **closed**: any value thatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.env_file = os.getenv("HAMCP_ENV_FILE", ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Load environment variables from .env file with HAMCP_ENV_FILE supportFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Use absolute path to ensure .env is found regardless of cwdFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.<summary><b>🍎 macOS</b></summary> 1. Go to [claude.ai](https://claude.ai) and sign in (or create a free account) 2. Open **Terminal** and run: ```sh curl -LsSfFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.<summary><b>🪟 Windows</b></summary> 1. Go to [claude.ai](https://claude.ai) and sign in (or create a free account) 2. Open **Windows PowerShell** (from Start mFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.(includes values loaded from ``.env`` via ``load_dotenv`` atFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."sudo apt install python3.14 (Linux)\n"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.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
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
7 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim homeassistant-ai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Tunneling service URL≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.