Adaptive Graph of Thoughts MCP server

Processes complex scientific queries through an 8-stage Graph-of-Thoughts pipeline that decomposes questions into hypotheses, gathers evidence, builds knowledge graphs in Neo4j, and provides confidence-scored conclusions with bias detection and falsifiability assessment for systematic research analysis.
Back to servers
Setup instructions
Provider
Sapta Dey
Release date
Jun 08, 2025
Language
Go
Stats
16 stars

The Adaptive Graph of Thoughts MCP server is a sophisticated framework that performs scientific reasoning using graph structures. This implementation leverages the Model Context Protocol (MCP) to integrate with AI applications like Claude Desktop, providing advanced reasoning capabilities for complex research tasks.

Installation

Prerequisites

  • Python 3.11+
  • Neo4j database with APOC library installed
  • Docker (optional, for containerized deployment)

Local Installation

  1. Clone the repository and change to the project directory:
git clone https://github.com/SaptaDey/Adaptive-Graph-of-Thoughts-MCP-server.git
cd Adaptive-Graph-of-Thoughts-MCP-server
  1. Install dependencies using Poetry:
poetry install
  1. Configure the application:
# Copy example configuration
cp config/settings.example.yaml config/settings.yaml

# Edit configuration as needed
vim config/settings.yaml
  1. Run the server:
poetry run uvicorn src.adaptive_graph_of_thoughts.main:app --reload
  1. Access the setup wizard to complete configuration:

Open your browser and navigate to http://localhost:8000/setup

Docker Deployment

For a containerized deployment:

# Build and run all services
docker-compose up --build

# For detached mode (background)
docker-compose up --build -d

# View logs
docker-compose logs -f adaptive-graph-of-thoughts

For production environments:

# Use production compose file
docker-compose -f docker-compose.prod.yml up --build -d

Kubernetes Deployment

A Helm chart is provided for Kubernetes deployment:

helm install agot helm/agot-server

Using the MCP Server

Configuring Claude Desktop

To connect the MCP server with Claude Desktop:

  1. Open Claude Desktop settings
  2. Add a new MCP server configuration:
{
  "mcpServers": {
    "adaptive-graph-of-thoughts": {
      "command": "python",
      "args": ["-m", "adaptive_graph_of_thoughts.main"],
      "cwd": "/path/to/Adaptive-Graph-of-Thoughts-MCP-server",
      "env": {
        "NEO4J_URI": "bolt://localhost:7687",
        "NEO4J_USER": "neo4j",
        "NEO4J_PASSWORD": "your_password",
        "MCP_TRANSPORT_TYPE": "stdio"
      }
    }
  }
}

Available MCP Tools

The server provides several specialized tools for scientific reasoning:

  1. scientific_reasoning_query - Advanced scientific reasoning with graph analysis
  2. analyze_research_hypothesis - Hypothesis evaluation with confidence scoring
  3. explore_scientific_relationships - Concept relationship mapping
  4. validate_scientific_claims - Evidence-based claim validation

Using the API Directly

The primary API endpoint is:

  • MCP Protocol Endpoint: POST /mcp

Example request for the asr_got.query method:

{
  "jsonrpc": "2.0",
  "method": "asr_got.query",
  "params": {
    "query": "Analyze the relationship between microbiome diversity and cancer progression.",
    "parameters": {
      "include_reasoning_trace": true,
      "include_graph_state": false
    }
  },
  "id": "123"
}

Health Check

Check the server status by accessing:

GET /health

Expected response:

{
  "status": "healthy",
  "version": "0.1.0" 
}

Troubleshooting

If you encounter issues:

  1. Ensure your Neo4j instance is running and accessible
  2. Verify the credentials in your configuration file are correct
  3. Check console output for detailed error messages
  4. Ensure the APOC library is installed in your Neo4j instance
  5. Verify network connectivity if using remote services

IDE Integration

For VS Code users, the vscode-agot extension allows querying the server directly. Install the extension and execute AGoT: Ask Graph… from the Command Palette.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "adaptive-graph-of-thoughts" '{"command":"python","args":["-m","adaptive_graph_of_thoughts.main"],"cwd":"/path/to/Adaptive-Graph-of-Thoughts-MCP-server","env":{"NEO4J_URI":"bolt://localhost:7687","NEO4J_USER":"neo4j","NEO4J_PASSWORD":"your_password","MCP_TRANSPORT_TYPE":"stdio"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "adaptive-graph-of-thoughts": {
            "command": "python",
            "args": [
                "-m",
                "adaptive_graph_of_thoughts.main"
            ],
            "cwd": "/path/to/Adaptive-Graph-of-Thoughts-MCP-server",
            "env": {
                "NEO4J_URI": "bolt://localhost:7687",
                "NEO4J_USER": "neo4j",
                "NEO4J_PASSWORD": "your_password",
                "MCP_TRANSPORT_TYPE": "stdio"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "adaptive-graph-of-thoughts": {
            "command": "python",
            "args": [
                "-m",
                "adaptive_graph_of_thoughts.main"
            ],
            "cwd": "/path/to/Adaptive-Graph-of-Thoughts-MCP-server",
            "env": {
                "NEO4J_URI": "bolt://localhost:7687",
                "NEO4J_USER": "neo4j",
                "NEO4J_PASSWORD": "your_password",
                "MCP_TRANSPORT_TYPE": "stdio"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later