Oap Langgraph Tools Agent banner
langchain-ai langchain-ai

Oap Langgraph Tools Agent

AI community

Description

A pre-built LangGraph tools agent for Open Agent Platform. It contains support for MCP servers and a LangConnect RAG tool.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

Open Agent Platform LangGraph Tools Agent

A pre-built LangGraph tools agent for Open Agent Platform. It contains support for MCP servers and a LangConnect RAG tool.

[!TIP] This project is built for [Open Agent Platform](https://github.com/langchain-ai/open-agent-platform), a citizen developer platform for building, testing, and using agents.

Setup

First, clone the repository and create a new virtual environment:

git clone https://github.com/langchain-ai/oap-langgraph-tools-agent.git
uv venv

Activate the virtual environment:

source .venv/bin/activate

Install dependencies:

uv sync

Then set the environment variables:

cp .env.example .env

This project requires a Supabase account with authentication to be setup. This is because this project implements custom LangGraph authentication so that it can be called directly from a web client.

After setting your environment variables, you can start the server by running:

# The --no-browser will disable auto-opening LangGraph studio when the server starts
# optional, but recommended since the studio is not needed for this project
uv run langgraph dev --no-browser

The server will now be running on `http://localhost:2024`.

Open Agent Platform

This agent has been configured to work with the [Open Agent Platform](https://github.com/langchain-ai/open-agent-platform). Please see the [OAP docs](https://github.com/langchain-ai/open-agent-platform/tree/main/README.md) for more information on how to add this agent to your OAP instance.

To update the OAP configuration, you can modify the `GraphConfigPydantic` class in the `agent.py` file. OAP will automatically register any changes to this class. You can modify a specific field's properties by editing the `x_oap_ui_config` metadata object. For more information, see the [Open Agent Platform documentation on graph configuration](https://github.com/langchain-ai/open-agent-platform/?tab=readme-