ToolFront logo

ToolFront

Organization
statespace-tech

Search for the agentic web.

Publisherstatespace-tech
Repositorystatespace
LanguageRust
Forks
67
Stars
870
Available tools
0
Transport typestdio
Categories
LicenseMIT
Links
  • Connect tools to AI workflows

    ToolFront exposes MCP capabilities that can be used by compatible AI clients and agents.

  • 0 available tools

    Browse the callable actions below, including names and descriptions when provided by the server.

  • Ready-to-copy setup

    Use the installation snippets to configure this server in your preferred MCP client.

  • Open source signals

    870 stars and 67 forks from the linked repository.

Shareable data apps for AI agents

Test Suite License crates.io Discord X


Website: https://statespace.com

Documentation: https://docs.statespace.com


AI doesn't know your data, but it knows Unix and filesystems. Statespace lets you transform your files and CLI tools into shareable data apps that any agent can discover and use. Build database explorers, share business rules, or document legacy APIs. Once you’ve created an app, deploy and monitor it with our cloud platform.

Installation

bash
$ curl -fsSL https://statespace.com/install.sh | bash

Quickstart

1. Create it

Run statespace init in the current directory:

bash
$ statespace init

2. Build it

Add constrained CLI tools to README.md or any other Markdown file:

yaml
---
tools:
  - [grep]
  - [python, scripts/summarize.py]
  - [sqlite3, data/app.db, { regex: "^(SELECT|EXPLAIN)\\b.*" }]
---

# Instructions
- Only run read-only queries against the database
- Use `summarize.py` for aggregations and report generation
- Use `grep` to search across local files and logs

Alternatively, let your coding agent build it out for you:

bash
$ claude "Document my database schema and add tools to query it"

3. Run it

Run your app locally:

bash
$ statespace run --port 8000

Agents and HTTP clients can now read pages and execute tools:

bash
# Read a page
$ curl http://localhost:8000/README.md

# Execute a CLI tool
$ curl -X POST http://localhost:8000/README.md \
  -H "Content-Type: application/json" \
  -d '{"command": ["grep", "-r", "revenue", "."]}'

4. Deploy it

Deploy your app to the cloud:

bash
$ statespace deploy --name demo

Your app is now live at a public URL:

bash
$ curl https://demo.statespace.app/README.md

5. Share it

Point any agent at the URL directly:

bash
$ claude "Use the API at https://demo.statespace.app to break down revenue by region"

Or wire it up as an MCP server:

json
"mcpServers": {
  "statespace": {
    "command": "npx",
    "args": ["-y", "statespace-mcp", "https://demo.statespace.app"]
  }
}

Features

  • 🔌 Any CLI tool — psql, sqlite3, grep, python — if it runs in a shell, it works
  • 🔒 Safe by default — regex constraints mean agents can only run what you explicitly allow
  • 🧠 Self-describing — Markdown pages are both the documentation and the interface
  • 📖 Composable — split across pages so agents load only what they need and save tokens
  • 🚀 Shareable — deploy to a URL, wire up as an MCP server, or share with teammates

Community & Contributing

License

This project is licensed under the terms of the MIT license.

Installation

TypingMind
Prerequisites:

Node.js 18+

{
  "mcpServers": {
    "toolfront": {
      "command": "uvx",
      "args": [
        "toolfront[snowflake]",
        "snowflake://user:pass@account/warehouse/database"
      ]
    }
  }
}

Use ToolFront MCP with multiple AI models

TypingMind connects MCP tools at the workspace level, so once ToolFront is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP runs locally through the TypingMind MCP connector on your device.

Setup guide to use the local connector

Use this when the MCP server needs access to local files, apps, or private resources on your computer.

1

Open the MCP settings

In TypingMind, go to Settings, Advanced Settings, then Model Context Protocol and choose Setup Connector.

  1. Open TypingMind in your browser.
  2. Click the Settings icon.
  3. Go to Advanced Settings.
  4. Open the Model Context Protocol section.
  5. Click Setup Connector and choose This Device.
TypingMind MCP connector setup screen with This Device selected
2

Run the connector command

Choose This Device, copy the command from TypingMind, and run it in Terminal. Keep the process running while you use MCP.

  1. Copy the setup command shown by TypingMind.
  2. Open Terminal on macOS or Windows Terminal on Windows.
  3. Paste and run the command.
  4. Approve the package install if Terminal asks you to proceed.
  5. Keep the Terminal window running while using MCP tools.
3

Add ToolFront as a server

When the connector status is Ready, click Edit Servers and paste the MCP server configuration.

  1. Wait until the connector status shows Ready.
  2. Click Edit Servers.
  3. Paste the ToolFront MCP server configuration.
  4. Save the server list.
  5. Refresh if you want to confirm the connector is still ready.
TypingMind MCP settings showing active server and Edit Servers button
{
  "mcpServers": {
    "toolfront": {
      "command": "npx",
      "args": [
        "-y",
        "toolfront"
      ]
    }
  }
}
4

Use it across models

Save the server list, open Plugins, enable the ToolFront MCP tools, then select any supported AI model in TypingMind and use the tools in chat or assign them to an AI agent.

  1. Open the Plugins page in TypingMind.
  2. Enable the ToolFront MCP tools.
  3. Start a chat and choose the AI model you want to use.
  4. Use the MCP tools in chat or assign them to an AI agent.
  5. Switch to another AI model whenever needed without reconnecting MCP.
TypingMind chat using enabled MCP tools with a selected AI model
Can you use ToolFront to help me with this task?
ToolFront
Sure. I read it.
Here is what I found using ToolFront.

Frequently asked questions

What is the ToolFront MCP server used for?

ToolFront is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.

Can I use ToolFront MCP with multiple AI models in TypingMind?

Yes. TypingMind connects MCP tools at the workspace level, so you can use ToolFront with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.

Why use ToolFront MCP with TypingMind?

TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With ToolFront connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.

How do I connect ToolFront MCP to TypingMind?

ToolFront runs through the TypingMind local MCP connector. This is best when the MCP server needs access to local files, desktop apps, command-line tools, or private resources on your computer.

What tools does ToolFront MCP provide in TypingMind?

ToolFront exposes MCP capabilities that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.

Do I need to share my API keys with TypingMind to use ToolFront MCP?

No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If ToolFront requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.

Related MCP Servers

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇