resq-mcp@1.2.2
BLOCKED· not startedPublisher claims: "FastMCP server exposing ResQ platform capabilities to AI clients" Observed in sandbox: sends data to nixos.org.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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: Blocked 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
- no credential variables read in the code
- Where it talks to
- no vendor host named in the codeAlso nixos.org, docker.com, bun.sh — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · contacted nixos.org (undeclared)
- What we could not test
- server startup · the tool list · tool behavior
Do not connect it. The honeypot or a critical finding blocked this version; the evidence is below.
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 (3 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-16 and scored it 39/100 (Blocked). Do not install it: the sandbox observed behaviour consistent with credential theft, exfiltration or persistence. Notable findings: Collapsed <details> block carrying instructions; Collapsed <details> block carrying instructions; Pipe-to-shell pattern. Summary: sends data to nixos.org.
Behavior trace
Honeypot run · 0 s · 3 scenariosStatic findings
<summary>Local development</summary> ```bash git clone https://github.com/resq-software/pypi.git cd mcp uv sync uv run resq-mcp ```Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.<summary>Claude Desktop</summary> Add to your `claude_desktop_config.json` ([MCP install guide](https://modelcontextprotocol.io/quickstart/user)): ```json { "mcFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.if curl -L https://nixos.org/nix/install | sh -s -- --daemon --yes; thenFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.curl -fsSL https://bun.sh/install | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.<summary>VS Code</summary> A pre-configured [`.vscode/mcp.json`](.vscode/mcp.json) is included in this repo — just open the project and the server is available.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.# 1 if sudo is not available and not running as root.Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# Ensures the user has sudo privileges.Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.<summary>Docker</summary> Run the server as a container in SSE mode: ```json { "mcpServers": { "resq": { "command": "docker", "args": [ "run", "-i", "--rm", "--Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.# Root/sudo privileges.Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.sudo apt-get update -yFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Use a .env file or export environment variables to override.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.documentation including README, AGENTS.md, and CLAUDE.md - Add environment variable validation onFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.if curl -L https://nixos.org/nix/install | sh -s -- --daemon --yes; thenFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.agent guide - Add agent-sync.sh to keep AGENTS.md and CLAUDE.md in syncFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Settings loaded from environment variables (RESQ_*) or .env file.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.curl -fsSL https://bun.sh/install | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.env_file=".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.sudo apt-get install -y apt-transport-https ca-certificates curl software-properties-common lsb-releaseFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.- Update .github/workflows/ci.yml with pytest --cov and Codecov upload - Add CLAUDE.md + AGENTS.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.chmod +x "$PROJECT_ROOT"/.git-hooks/* 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.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
41 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
- 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 resq-software: 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.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- 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.