ToolChat

@rectalogic

ToolChat について

PydanticAI LLM chat with MCP server tools

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "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"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

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.

よくある質問

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.

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

作者

rectalogic

「AI とエージェント」の他のコンテンツ

21st.dev Magic AI Agent

21st-dev

It's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic

5.3K

MCP Client for Ollama (ollmcp)

jonigl

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre

768