Content
# Tool List
[](https://langgraph-studio.vercel.app/templates/open?githubUrl=https://github.com/langchain-ai/react-agent)
## Project Overview
> Chat Interface
`LangGraph Dynamic MCP Agents` is a project that implements ReAct agents that can access various external tools and data sources through the Model Context Protocol (MCP). This project is based on LangGraph's ReAct agent and provides an interface to easily add and configure MCP tools.
### Key Features
**Dynamic Tool Configuration Dashboard**
You can access the tool configuration dashboard at `http://localhost:2025`.
**Add Tool** tab allows you to add tools by copying and pasting the JSON configuration of the MCP tool from [Smithery](https://smithery.io).
----
**Real-time Updates**
Tools added or modified in the tool configuration dashboard are reflected in real-time.
**System Prompt Configuration**
You can configure the system prompt by modifying the `prompts/system_prompt.yaml` file.
This is also reflected dynamically in real-time.
If you want to modify the system prompt set for the agent, you can modify the contents of the `prompts/system_prompt.yaml` file.
----
### Key Features
* **LangGraph ReAct Agent**: ReAct agent based on LangGraph
* **Real-time Dynamic Tool Management**: Easily add, remove, and configure MCP tools (supports Smithery JSON format)
* **Real-time Dynamic System Prompt Configuration**: Easily modify the system prompt (dynamically reflected)
* **Conversation History**: Track and manage conversation contents with the agent
* **TeddyFlow Integration**: Chat interface integration
* **Docker Image Build**: Docker image build available
* **localhost Support**: Execution on localhost (chat interface integration available)
## Installation
1. Clone the repository
```bash
git clone https://github.com/teddynote-lab/langgraph-dynamic-mcp-agents
cd langgraph-dynamic-mcp-agents
```
2. Configure the `.env` file
Copy the `.env.example` file to `.env` and add the necessary API keys.
```bash
cp .env.example .env
```
Configure `LLM_PROVIDER` in the `.env` file.
Options: `ANTHROPIC`, `OPENAI`, `AZURE_OPENAI`
```
LLM_PROVIDER=AZURE_OPENAI
```
The following API keys are required. (Select one according to the chosen `LLM_PROVIDER`)
- `ANTHROPIC_API_KEY`: Anthropic API key
- `OPENAI_API_KEY`: OpenAI API key
- `AZURE_OPENAI_API_KEY`: Azure OpenAI API key
- `AZURE_OPENAI_ENDPOINT`: Azure OpenAI endpoint
3. Configure MCP tools
Configure the MCP tools to be used by the model based on the `mcp_config.json` file in the `mcp-config` folder.
Therefore, you can set the MCP tools to be used in JSON format in advance.
This process can also be done through the tool configuration dashboard.
The following is an example of a sample configuration.
```json
{
"mcpServers": {
"perplexity-search": {
"command": "npx",
"args": [
"-y",
"@smithery/cli@latest",
"run",
"@arjunkmrm/perplexity-search",
"--key",
"Enter SMITHERY_API_KEY"
],
"transport": "stdio"
},
"get_current_time": {
"command": "python",
"args": [
"/app/resources/mcp_server_time.py"
],
"transport": "stdio"
}
}
}
```
4. Add .py files as MCP `stdio` servers
- (Reference) Refer to the `mcp_server_time.py` file in the `resources` folder.
1. Add the custom-written .py file to the `resources` folder and write the code to execute it as a `stdio` server.
2. Modify the file path when adding to `mcp-config/mcp_config.json`.
**Rules**
`./resources/file.py` > `/app/resources/file.py`
For example, if you want to add the `./resources/mcp_server_time.py` file, set it to `/app/resources/mcp_server_time.py`.
```json
"get_current_time": {
"command": "python",
"args": [
"/app/resources/mcp_server_time.py"
],
"transport": "stdio"
}
```
6. Add registered tools from Smithery
You can bring the JSON configuration of the MCP tool to be used from [Smithery](https://smithery.ai/) and easily add it to the tool dashboard.
1. Visit the [Smithery](https://smithery.io) website and select the tool you want to use.
2. Click the 'COPY' button on the right side of the tool page to copy the JSON configuration.
3. Open the `mcp_config.json` file and add the copied JSON.
> Paste the copied content.
## Run the Application
Once all configurations are complete, you can run the application with the following commands.
> Windows (PowerShell)
```bash
docker compose build --no-cache; docker-compose up -d
```
> Mac / Linux
```bash
docker compose build --no-cache && docker-compose up -d
```
**Access Addresses**
- TeddyFlow Integration: https://teddyflow.com/
- Chat Interface: `http://localhost:2024`
- Tool Configuration Dashboard: `http://localhost:2025`
## Connect to teddyflow.com
1. Sign up for an account on teddyflow.com.
When signing up, enter "teddynote-youtube" in the "Beta Key" field for immediate approval.
2. Click the "Connect New App" button after logging in.
3. Enter the app name and click the "Connect" button.
4. Select the "LangGraph" tab and enter the following information:
- Endpoint: `http://localhost:2024`
- Graph: `agent`
5. Click the "Save" button when the connection settings are complete.
6. Click the "Connect App" button to save.
## Company/Community Logo and Branding
Custom features have been released for companies/communities.
If you are interested in introducing this feature, please contact us at service@brain-crew.com for assistance.
## License
Apache License 2.0 ([LICENSE](LICENSE))
