MCP.so
Sign In

ToolChat

@rectalogic

About ToolChat

PydanticAI LLM chat with MCP server tools

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "toolchat": {
      "command": "uv",
      "args": [
        "run",
        "toolchat",
        "--model",
        "google-gla:gemini-2.5-pro-exp-03-25",
        "--tool-servers",
        "sample-tools.yml",
        "--enable-tool-server",
        "awslabs.aws-documentation-mcp-server"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is ToolChat?

ToolChat is a command-line tool that lets you chat with large language models (LLMs) while giving them access to external tools via MCP (Model Context Protocol) servers. It's designed for developers and users who want to combine conversational AI with real-time data retrieval or actions from configured MCP tool servers.

How to use ToolChat?

Configure MCP tool servers in a YAML file, then run ToolChat with the --tool-servers option pointing to that file. Enable specific tools using --enable-tool-server. The included /help command provides more details on features like multimodal support.

Key features of ToolChat

  • Chat with LLMs using MCP server tools
  • Configure tools in a simple YAML file
  • Enable specific tool servers per session
  • Supports multimodal prompts (images, documents, etc.)
  • Built-in /help and /quit commands

Use cases of ToolChat

  • Search official AWS documentation via a chat interface
  • Enable a documentation MCP server and ask for code snippets
  • Combine multiple MCP tools in one conversational workflow
  • Upload images or PDFs with a multimodal LLM for analysis

FAQ from ToolChat

How do I configure MCP servers for ToolChat?

Create a YAML file following the format shown in sample-tools.yml. Pass its path with the --tool-servers argument when starting ToolChat.

How do I enable a specific tool?

Use the --enable-tool-server flag followed by the tool server name. For example: --enable-tool-server awslabs.aws-documentation-mcp-server.

Can I include images or documents in my prompts?

Yes, if the underlying model supports multimodal inputs. See the /help command for details on attaching files.

Where can I find all available commands?

Run the /help command inside the ToolChat session to list all commands and usage instructions.

What is the runtime dependency?

ToolChat is run via uv run toolchat as shown in the example, but the README does not specify installation requirements beyond Python and the necessary packages.

Frequently asked questions

How do I configure MCP servers for ToolChat?

Create a YAML file following the format shown in `sample-tools.yml`. Pass its path with the `--tool-servers` argument when starting ToolChat.

How do I enable a specific tool?

Use the `--enable-tool-server` flag followed by the tool server name. For example: `--enable-tool-server awslabs.aws-documentation-mcp-server`.

Can I include images or documents in my prompts?

Yes, if the underlying model supports multimodal inputs. See the `/help` command for details on attaching files.

Where can I find all available commands?

Run the `/help` command inside the ToolChat session to list all commands and usage instructions.

What is the runtime dependency?

ToolChat is run via `uv run toolchat` as shown in the example, but the README does not specify installation requirements beyond Python and the necessary packages.

Comments

More AI & Agents MCP servers