ToolChat
About
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…
Details
- Author
- rectalogic
- Downloads
- 309
- Categories
- AI
Jump to
- 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
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
ToolChatCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
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.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"toolchat": {
"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"
]
}
}
}
}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"
]
}
}ToolChat
Chat with LLMs using MCP servers.
Configure MCP tool servers in a YAML file and provide path to --tool-servers,
enable specific tools with --enable-tool-server.
See sample-tools.yml for format.
If the model is multimodal you can also include images, documents etc. in your prompt.
See the /help command for details.
Example
Use AWS documentation tool with Gemini Pro 2.5 to search AWS docs:
``sh-session
$ uv 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
ToolChat - Ctrl-D or /quit to quit
Enter /multi to enter and exit multiline mode, /help for more commands
> look up documentation on S3 bucket naming rule. cite your sources
Okay, I can help with that. I will search for the S3 bucket naming rules
documentation and provide a summary along with the source URL.
sh-session_Tool search_documentation {'search_phrase': 'S3 bucket naming rules', 'limit':
1}_
Okay, I found a relevant document. I will now read the content to summarize the
S3 bucket naming rules.
sh-session_Tool read_documentation {'url':
'https://docs.aws.amazon.com/AmazonS3/latest/userguide/bucketnamingrules.html'}_
Okay, here is a summary of the naming rules for Amazon S3 general purpose
buckets, based on the official AWS documentation:
S3 General Purpose Bucket Naming Rules:
• Length: Must be between 3 and 63 characters long.
• Characters: Can only contain lowercase letters (a-z), numbers (0-9), periods
(.), and hyphens (-).
• Start/End: Must begin and end with a letter or number.
...[elided]
``
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
