perseus-mcp@1.1.0
VERIFIED· not startedPublisher claims: "MCP server for Perseus Greek and Latin text 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: Verified 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
- perseus.org (its own)Also tufts.edu, tei-c.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 under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable and talks to perseus.org, its own; the guard pins the network to what the honeypot saw and logs every call.
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 2026-11-14 and scored it 85/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
2. Enable **Developer mode**.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.<summary><strong>Cursor configuration</strong></summary> ### Cursor Open or create `mcp.json`: - Windows: `%APPDATA%\Cursor\mcp.json` - macOS: `~/Library/ApplicFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.<!ENTITY lol2 "&lol;&lol;&lol;&lol;&lol;&lol;&lol;&lol;&lol;&lol;">Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.<summary><strong>Claude Desktop configuration</strong></summary> ### Claude Desktop In Claude Desktop, open **Settings → Developer → Edit Config**, or edit: - WFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.<summary><strong>OpenRouter notebook workflow</strong></summary> ### OpenRouter OpenRouter is not a native local MCP host. The project notebooks instead use a sFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.<summary><strong>Other local MCP clients</strong></summary> ### Other local MCP clients Use these values when a client asks for separate fields: | Field | ValueFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.2. Enable **Developer mode**.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.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 perseus-mcp@1.1.0 as of 57 min ago. This is the package itself, not its dependencies.