ModelsAtlas
Explore
Atlas / MCP servers / zihaofu245 / LM Studio Toolpack

LM Studio ToolpackBLOCK

mcp/zihaofu245/lm-studio-toolpack
MCP server by zihaofu245 · llm · lmstudio · mcp server · Audited 2026-10-08
⚑ Report / re-scanSource ↗

A MCP stdio toolpack for local LLMs

Verdict
BLOCK
Grade
D
Trust score
69 /100
Exposed tools
2 2r · 0w · 0d
Transport
stdio
License
MIT
Stars
34
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://lobehub.com/mcp/zihaofu245-lmstudio-toolpack)

[](https://mseep.ai/app/zihaofu245-lmstudio-toolpack)

[](https://mseep.ai/app/acc116e1-414b-418b-8a94-00ab266263d8)

A small collection of Model Context Protocol (MCP) tools, built for local LLMs. One venv, many options.

Why it exists

Many MCP servers are distributed as separate projects and need separate setup. This tool pack keeps a few local MCP servers in one repo and one uv environment.

Features

  • MCP JSON configuration generation: run main.py and go through the wizard
  • One venv for multiple MCP servers

MCP Servers

  • Web Search: Use duckduckgo as search engine, fetch and summarize top results
  • Python SandBox: Allow agents to run Python and use NumPy and SymPy for math tasks
  • Longterm-Memory: Store lightweight long-term notes

Security Notes

  1. Default transport is stdio. You can switch to HTTP in GlobalConfig.
  2. python-sandbox.py uses exec() and eval() for run_python. This is not a secure sandbox.
  3. Treat run_python as local code execution by the agent under your user account.
  4. The generated config now sets PYTHON_SANDBOX_LOG_PATH for local python-sandbox entries so every run_python execution is appended to a JSONL audit log.

Requirements

  • Python >= 3.13
  • Managed with uv

Install

Using uv:

uv sync

Generate LM Studio Config

Run:

uv run python main.py

LM Studio currently follows Cursor-style mcp.json notation. The generated LM Studio output uses the mcpServers object with either:

  • command + args + env for local stdio servers
  • url + headers for remote HTTP servers

If you select the local

Read from source at commit 310d8b22cd3bOBSERVED · 2026-10-08
Advertisement
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add lmstudio-toolpack -- uvx lmstudio-toolpack
claude-desktop
{
  "mcpServers": {
    "lmstudio-toolpack": {
      "command": "uvx",
      "args": [
        "lmstudio-toolpack"
      ]
    }
  }
}
03

Exposed tools (2)

2 read · 0 write · 0 destructive.

ToolRiskDescription
visit_urlreadBreadth-first crawl that mimics a no-login browser session.
web_searchreadDuckDuckGo-powered search that emits detailed, browser-style blocks.
04

Trust audit

BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeFAIL
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (5 observation(s))
Shell
declared (2 observation(s))
Dependencies
pinned
Secrets in source
none-found

Findings (2)

HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
MCPs/python-sandbox.py:97
result = eval(
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
MCPs/python-sandbox.py:102
exec(compiled, globals_env, locals_env)
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 310d8b22cd3bfull audit observations/trust-audit/mcp-server/zihaofu245__lm-studio-toolpack.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-08310d8b22cd3bBLOCKD69first audit
06

Questions

What is the LM Studio Toolpack MCP server?

A MCP stdio toolpack for local LLMs

What tools does LM Studio Toolpack expose?

2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is LM Studio Toolpack safe to connect to an agent?

No — not without reading the findings first. The audit graded it D (69/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.

What credentials does LM Studio Toolpack need?

No credential environment variables were found in its source, so it appears to need none.

How does LM Studio Toolpack run?

It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as lmstudio-toolpack.

How current is this page?

The grade is for one exact copy of the source (310d8b22cd3b), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement