Skills/PyPI/vector-mcp

vector-mcp@3.4.0

VERIFIED· not started

Publisher claims: "Governed vector retrieval over native medulla and secure opt-in providers." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher repository-maintainers-maintainers · publishing for 442 daysInstalls 1,624Last detonated 16 min ago
$claude mcp add vector-mcp -- uvx vector-mcp
WatchReport an issue

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
LLM_API_KEYConfiguration, not credentials: A2A_URL, VECTOR_MCP_DATA_DIR
Where it talks to
no vendor host named in the codeAlso example.invalid — not the publisher's domain; check what for before connecting.
What we saw when it ran
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 example.invalid as well as its own vendor. The guard injects LLM_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx vector-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 3.3.4

vet-skills diff vector-mcp 3.3.4 3.4.0

In the sandbox, this version reached for nothing 3.3.4 did not. Compared from the two recorded runs, not from source.

No longer contacted
knuckles.team, llamaindex.ai

3.3.4 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 2026-11-20 and scored it 92/100 (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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_mcp_server.py:242 · MCP server using network transport (SSE/HTTP) — data sent over network"FASTMCP_SERVER_AUTH_JWT_ISSUER": "https://issuer.example.test",Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
LOW
Dynamic module loadingvector_mcp/vectordb/db_utils.py:63 · Dynamic module loadingavailable = importlib.util.find_spec(package) is not NoneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_mcp_server.py:241 · MCP server using network transport (SSE/HTTP) — data sent over network"FASTMCP_SERVER_AUTH_JWT_JWKS_URI": "https://issuer.example.test/jwks",Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04

Cost to the agent

Instructions loaded
≈54 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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.