mcp.science@0.1.7
CAUTION· not startedPublisher claims: "Open Source MCP Servers for Scientific Research" 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
NEMAD_API_KEYSSH_PASSWORDSSH_PRIVATE_KEY_FILEConfiguration, not credentials: SSH_ALLOWED_COMMANDS, SSH_ALLOWED_PATHS, SSH_ARGUMENTS_BLACKLIST, SSH_COMMANDS_BLACKLIST, SSH_CONFIG_FILE, SSH_HOST, SSH_PORT, SSH_USERNAME- Where it talks to
- no vendor host named in the codeAlso nemad.org — 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 nemad.org as well as its own vendor. The guard injects NEMAD_API_KEY, SSH_PASSWORD, SSH_PRIVATE_KEY_FILE 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 2026-11-10 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Collapsed <details> block carrying instructions; HTML comment carrying imperative instructions to the agent; Collapsed <details> block carrying instructions. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
<summary>How to install uv?</summary> For macOS and Linux: ```bash curl -LsSf https://astral.sh/uv/install.sh | sh ``` For Windows: ```powershell powershell -ExFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.prettier-ignore-startFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.result = subprocess.run(uvx_cmd, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.<summary>👈 Click to see more conventions about directory and naming</summary> Please create your new server in the `servers` folder. For creating a new server Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.prettier-ignore-startFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.prettier-ignore-endFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.prettier-ignore-endFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.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 mcp.science@0.1.7 as of 4d ago. This is the package itself, not its dependencies.
What would make this Verified
2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
- Unclaimed publisher≈ +8 on the totalClaim pypi: 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.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.