1. Conduid
  2. AI
  3. Tools Server
MCP server · AI

Tools Server

A dependency-free Model Context Protocol server (stdio)

Unclaimed GPL-3.0 last commit 7 months ago devtools
53Fair

Scored 19 days ago · breakdown

About Tools Server

Tools Server is an MCP server published by Rose22 in the AI category: a dependency-free Model Context Protocol server (stdio). It has been installed 0 times through Conduid.

The repository has 4 stars and 1 forks, with the last commit 7 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues (0) before depending on it in production.

Install

Install
npx mcp-tools-server

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

Ask AI about Tools Server

Powered by Claude · Grounded in docs

I know everything about Tools Server. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ·README presentNot checked yet.
  • ·License declaredNot checked yet.
  • ·Tests presentNot checked yet.
  • ·Dependencies pinnedNot checked yet.
  • ·No dynamic code executionNot checked yet.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

README

MCP server that enables any LLM to function as a Siri/Alexa/Google-style AI assistant

this is a very flexible and capable MCP server intended to be run on your own device. it's inspired by classic AI assistants like Siri, Alexa and Google Assistant but adding an LLM to that mix turns it all up to 11!

it's modular and you can turn any of the components on or off depending on what tools you need. if you prefer to just use the web search and url reading functionality, you can turn all the other modules off.

unlike many solutions so far, this is independent of the UI you choose to use for your AI assistant because it's using MCP and can be plugged into any system that supports MCP.

it's cross platform and what tools your LLM will see depends on what operating system you're using (windows, mac, or linux)

it enables your chosen AI assistant to:

  • search the web using duckduckgo (no API key needed, we use page scraping)
  • store memories and retrieve them across conversations. there are memories that are tied to the date they were stored, and there are "persistent" memories (for things like your personal preferences and anything you want the AI to always remember no matter how long ago it was). the memory storage remains snappy because it remembers only 30 days into the past by default, but you can ask the AI to remember further back! memory is stored in msgpack format, for super-fast and compact storage.
  • get the current time/date
  • browse, read and modify your files (with safety features such as automatic backups before modification)
  • read and process a wide range of file types (it can do things like look inside zip archives, see video metadata, stuff like that)
  • read and process remote URLs (links) of those same file types and with the same extraction abilities
  • manage a complete life organization system for you with notes, tasks, events/calendar/appointments, bookmarks, recipes, and so on. it's stored as a plain text markdown database (basically just a simple human readable folder) so it can easily be copied or backed up and you don't have to worry about being locked in to a database format! you can completely customize what types of objects you want in your database by editing the ```config.yaml````` file
  • control a bunch of things about your device (it can even lock your screen!)
  • get a ton of information about your device and then use it to diagnose problems
  • transcribe youtube videos

if you use this with a good model, it'll smartly chain multiple actions together, and you can start doing things like asking it to summarize a youtube video and save it to your notes. or to create a recipe with some healthy vegetables and then save it to your recipes. it gets really powerful real fast!

how to install

run this:

git clone https://github.com/Rose22/mcp_tools_server.git
cd mcp_tools_server
python -m venv venv
python -r requirements.txt

then you will need a way to run a python program in a virtualenv. the simplest way is to use this command:

/path/to/mcp_tools_server/venv/bin/python /path/to/mcp_tools_server/main.py

add that as the command in your AI user interface of choice. the transport type is stdio, but you can uncomment the relevant lines in main.py depending on which type of transport you need

(there will be a proper config system soon..)

see it in action!

README mirrored from the source repository 19 days ago. The original is authoritative.

Questions

About Tools Server

How do I install Tools Server?

Run npx mcp-tools-server, then add the server to your MCP client's configuration. Conduid has recorded 0 installs, so the command is known to work with current clients.

Is Tools Server safe to use with an AI agent?

Its trust score is 53 out of 100 (fair). It passes 0 of 1 static security checks; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Tools Server still maintained?

The last commit was 7 months ago, with 0 open issues. That's long enough that you should check whether the maintainer is responding to issues before depending on it.