MCP, MCP server
Llm Search
Llm Search, an MCP server listed in the PlugVet directory.
Compatibility: Not stated.
Grade C
One Medium finding. Read the report before installing.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
NETWORK_HOST_FROM_INPUT
Why this grade
- NETWORK_HOST_FROM_INPUT Medium
A file takes a URL or endpoint as input and has no fixed host list.
chat-client/static/app.js, line 155
const resp = await fetch('/v1/models');
Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.
Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.
What was checked
Plain notes from the hygiene checks.
Permissions
Pass
No shell or command execution found, and no extra permission was declared.
Install and update
Concern
dependencies are not pinned.
INSTALL_UNPINNED
requirements.txt, line 2
fastapi>=0.110.0
Network
Serious
accepts a host from input, with no fixed list in this file.
NETWORK_HOST_FROM_INPUT
chat-client/static/app.js, line 155
const resp = await fetch('/v1/models');
chat-client/static/app.js, line 272
const resp = await fetch('/v1/chat/completions', {
chat-client/static/app.js, line 692
const resp = await fetch('/v1/config');
Show more
chat-client/static/app.js, line 746
const resp = await fetch('/v1/config', {
chat-client/static/app.js, line 802
const resp = await fetch('/stats');
chat-client/static/sw.js, line 60
const fetchPromise = fetch(event.request)
scripts/probes/tool_selection.py, line 96
"description": "The full URL of the page to fetch (must start with http:// or https://)",
src/llm_search/fetch_page.py, line 140
url: The URL to fetch (http/https only).
src/llm_search/tool_registry.py, line 67
"description": "The full URL of the page to fetch (must start with http:// or https://)",
Secrets
Concern
reads a credential or environment file.
SECRETS_PATH_DOTENV
src/llm_search/__main__.py, line 4
variables or .env file. SearXNG should be running separately
src/llm_search/config.py, line 16
env_file=".env",
src/llm_search/tool_loop.py, line 84
"Set LM_STUDIO_API_KEY (env or .env) or PUT /v1/config."
Show more
.dockerignore, line 4
venv
.env.example, line 2
# Copy to .env and edit if you want to override defaults:
.env.example, line 3
# cp .env.example .env
.gitignore, line 10
# Environment
CHANGELOG.md, line 13
- **Backend API key support (`LM_STUDIO_API_KEY`)** - the middleware can now authenticate to its LLM backend. It previously sent no auth header at all, so an OpenAI-compatible serv
Agent instructions
Pass
No instruction to ignore earlier instructions or to hide a step.
Obfuscation
Pass
No encoded or minified payload found.
Licence
Note
no licence file found.
LICENCE_MISSING
No file path was stored.
no licence file found.
Maintainer activity
Pass
The latest commit is within the last 365 days.
Note
Hygiene check of commit a945d087ad95. dependencies are not pinned. accepts a host from input, with no fixed list in this file. reads a credential or environment file. no licence file found.
Date and source
Date checked:
github.com
Commit graded: a945d087ad95e2879e905686ff4f80400e1f9e22
This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.