Skills/npm/seegeo-mcp

seegeo-mcp@1.0.4

VERIFIED

Publisher claims: "Audit any website for AI visibility: graded report, findings with fixes, AI crawler access check." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher see-geo · publishing for 68 daysInstalls 0Last detonated 33 h ago
$claude mcp add seegeo-mcp -- npx -y seegeo-mcp
WatchReport an issue

Coverage

Started with a decoy SEEGEO_API_KEY; tool list observed. Tool calls with a real credential not tested.
Tested
server startup with a tagged decoy in SEEGEO_API_KEY · MCP initialize and tools/list · every tool description, for hidden instructions · where the decoy credential went · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with a real credential
Needs
SEEGEO_API_KEY — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.

Before you give it your token

It will ask for
SEEGEO_API_KEYConfiguration, not credentials: SEEGEO_API_URL
Where it talks to
see-geo.com (its own)
What the honeypot saw
no credential files read · no network
What we could not test
what the tools do when called with a real credential

Connect it with a scoped credential, under the guard. It asks for SEEGEO_API_KEY and talks to see-geo.com. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind.

$vet-skills run --secrets SEEGEO_API_KEY=see-geo.com -- npx -y seegeo-mcp

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) on 2026-11-14 and scored it 90/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 48 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
7.8sprocessdependency install exit 0
28sprocessrelaunched with a decoy SEEGEO_API_KEY (tagged; nothing real)
48sclaimed5 tools with a decoy SEEGEO_API_KEY: audit_site, get_audit, crawler_check, list_audits, usage
48stools9507676f690b478d
48stoolsaba599b1caed72df
48stools6423b2dc5fb04f1e
48stools0405e5864e857931
48stools8218b1b8bb13c03e
48sprocessscript backend runs setup only
48sprocessno install scripts to re-run

Static findings

MEDIUM
File permission modification commandpackage.json:16 · File permission modification command — agent changes file ownership/permissions"build": "tsc -p tsconfig.json && chmod +x dist/index.js",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packagedist/index.js:8 · npx invocation of non-well-known package — may execute untrusted code* MCP client at `npx seegeo-mcp`.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈74 tok
1 file · 6 in bundle
Tool list per prompt
≈755 tok
5 tools · 151 per tool
Handshake
489 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 193

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 seegeo-mcp@1.0.4 as of 32 h ago. This is the package itself, not its dependencies.