hanary-mcp@0.47.0
CAUTION· not startedPublisher claims: "Hanary MCP Server - Task management for Claude Code, OpenCode & OpenAI Codex" 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
HANARY_API_TOKENConfiguration, not credentials: HANARY_API_URL- Where it talks to
- no vendor host named in the codeAlso hanary.org, 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 hanary.org, opencode.ai as well as its own vendor. The guard injects HANARY_API_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.
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 2026-11-11 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Agent configured for autonomous execution without human approval; Agent configured for autonomous execution without human approval; Agent configured for autonomous execution without human approval. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
…guide mode instead of only asking for explicit AI delegation and stopping. safe autonomous advisory support is allowed and should continue. This includes reading task context and related local documents, read-only inspection commands, prov…Fix: Declare and request only the permissions the task needs.…guide mode instead of only asking for explicit AI delegation and stopping. safe autonomous advisory support is allowed and should continue. This includes reading task context and related local documents, read-only inspection commands, prov…Fix: Declare and request only the permissions the task needs.…guide mode instead of only asking for explicit AI delegation and stopping. safe autonomous advisory support is allowed and should continue. This includes reading task context and related local documents, read-only inspection commands, prov…Fix: Declare and request only the permissions the task needs.…guide mode instead of only asking for explicit AI delegation and stopping. safe autonomous advisory support is allowed and should continue. This includes reading task context and related local documents, read-only inspection commands, prov…Fix: Declare and request only the permissions the task needs.…tion ID, version, and reason. Cancellation records that decision; Hanary cannot kill an external host process. - finish_delegated_execution records succeeded/failed,…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."squad:%ED%95%9C%EA%B8%80-%EC%8A%A4%EC%BF%BC%EB%93%9C",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.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 hanary-mcp@0.47.0 as of 3d ago. This is the package itself, not its dependencies.
What would make this Verified
1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Agent configured for autonomous execution without human approval≈ +9 on the totalDeclare and request only the permissions the task needs.
- Unclaimed publisher≈ +8 on the totalClaim hanary: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Dense URL-encoded content≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.