trackmcp
Back to directory
saptadey

Adaptive-Graph-of-Thoughts-MCP-server

View on GitHub

AI Reasoning Framework for Scientific Research

22 stars PythonDeveloper Kits Updated Oct 18, 2025
graph-algorithmsgraph-of-thoughtsmcpmcp-serverneo4j-graph

Documentation

MseeP.ai Security Assessment Badge

๐Ÿง  Adaptive Graph of Thoughts


๐Ÿ” Overview

Adaptive Graph of Thoughts (AGoT) is a high-performance MCP server that implements the Advanced Scientific Reasoning Graph-of-Thoughts (ASR-GoT) framework. It uses a Neo4j graph database as a dynamic knowledge store and exposes reasoning capabilities through the Model Context Protocol (MCP), enabling seamless integration with AI assistants like Claude Desktop.

Key Highlights

FeatureDescription
๐Ÿง  Graph-Based ReasoningMulti-stage pipeline with 8 specialized reasoning stages
๐Ÿ“Š Dynamic Confidence ScoringMulti-dimensional evaluation with uncertainty quantification
๐Ÿ”ฌ Evidence IntegrationReal-time connection to PubMed, Google Scholar & Exa Search
โšก High PerformanceAsync FastAPI with Neo4j graph operations
๐Ÿ”Œ MCP ProtocolNative Claude Desktop & VS Code integration
๐Ÿณ Cloud-ReadyFull Docker + Kubernetes (Helm) support

๐Ÿ—๏ธ System Architecture

mermaid
%%{init: {'theme': 'base', 'themeVariables': {'primaryColor': '#4A90D9', 'primaryTextColor': '#fff', 'primaryBorderColor': '#2C5F8A', 'lineColor': '#666', 'secondaryColor': '#52B788', 'tertiaryColor': '#F8F9FA'}}}%%
graph TB
    subgraph Clients["๐Ÿ–ฅ๏ธ Client Layer"]
        CD["๐Ÿค– Claude Desktop"]
        VS["๐Ÿ’ป VS Code / Cursor"]
        CC["๐Ÿ”— Custom MCP Clients"]
    end

    subgraph Gateway["๐ŸŒ API Gateway Layer"]
        MCP_EP["โšก MCP Endpoint\n/mcp"]
        NLQ_EP["๐Ÿ” NLQ Endpoint\n/nlq"]
        GE_EP["๐Ÿ“Š Graph Explorer\n/graph"]
        HE["๐Ÿ’š Health Check\n/health"]
    end

    subgraph Core["๐Ÿง  Core Application Layer"]
        direction TB
        GTP["๐Ÿ”„ GoT Processor\nOrchestrator"]
        subgraph Pipeline["ASR-GoT 8-Stage Pipeline"]
            S1["1๏ธโƒฃ Init &\nContext Setup"]
            S2["2๏ธโƒฃ Query\nDecomposition"]
            S3["3๏ธโƒฃ Hypothesis\nGeneration"]
            S4["4๏ธโƒฃ Evidence\nIntegration"]
            S5["5๏ธโƒฃ Pruning &\nMerging"]
            S6["6๏ธโƒฃ Subgraph\nExtraction"]
            S7["7๏ธโƒฃ Synthesis &\nComposition"]
            S8["8๏ธโƒฃ Reflection &\nAudit"]
            S1 --> S2 --> S3 --> S4 --> S5 --> S6 --> S7 --> S8
        end
        GTP --> Pipeline
    end

    subgraph Services["๐Ÿ› ๏ธ Service Layer"]
        LLM["๐Ÿค– LLM Service\nOpenAI / Claude"]
        EDB["๐Ÿ“š Evidence DB\nPubMed ยท Scholar ยท Exa"]
    end

    subgraph Storage["๐Ÿ—„๏ธ Storage Layer"]
        NEO4J["๐Ÿ“ฆ Neo4j\nGraph Database"]
        CONFIG["โš™๏ธ Config\n(YAML + ENV)"]
    end

    Clients -->|"MCP JSON-RPC\nBearer Auth"| Gateway
    MCP_EP --> GTP
    NLQ_EP --> LLM
    GE_EP --> NEO4J
    GTP --> Services
    GTP --> NEO4J
    LLM --> EDB

    style Clients fill:#E3F2FD,stroke:#1565C0
    style Gateway fill:#F3E5F5,stroke:#6A1B9A
    style Core fill:#E8F5E9,stroke:#1B5E20
    style Services fill:#FFF8E1,stroke:#F57F17
    style Storage fill:#FCE4EC,stroke:#880E4F

๐Ÿ”„ ASR-GoT Reasoning Pipeline

The 8-stage reasoning pipeline transforms a raw question into a comprehensive, evidence-backed answer stored in the knowledge graph:

mermaid
%%{init: {'theme': 'base', 'themeVariables': {'primaryColor': '#7B68EE', 'edgeLabelBackground': '#fff'}}}%%
flowchart LR
    Q([โ“ Scientific\nQuestion]) --> S1

    subgraph S1["Stage 1: Initialization"]
        I1["Set context\n& parameters"]
        I2["Create root\ngraph node"]
        I1 --> I2
    end

    subgraph S2["Stage 2: Decomposition"]
        D1["Identify\nsub-questions"]
        D2["Map knowledge\ndomains"]
        D1 --> D2
    end

    subgraph S3["Stage 3: Hypothesis"]
        H1["Generate\nhypotheses"]
        H2["Score initial\nconfidence"]
        H1 --> H2
    end

    subgraph S4["Stage 4: Evidence"]
        E1["Query PubMed\nScholar ยท Exa"]
        E2["Integrate\nevidence nodes"]
        E1 --> E2
    end

    subgraph S5["Stage 5: Pruning"]
        P1["Remove weak\nhypotheses"]
        P2["Merge related\nnodes"]
        P1 --> P2
    end

    subgraph S6["Stage 6: Subgraph"]
        SG1["Extract key\nsubgraphs"]
        SG2["Score relevance\n& centrality"]
        SG1 --> SG2
    end

    subgraph S7["Stage 7: Synthesis"]
        C1["Compose final\nnarrative"]
        C2["Build\nconclusions"]
        C1 --> C2
    end

    subgraph S8["Stage 8: Reflection"]
        R1["Audit\nconsistency"]
        R2["Return final\nresult"]
        R1 --> R2
    end

    S1 --> S2 --> S3 --> S4 --> S5 --> S6 --> S7 --> S8
    S8 --> A([โœ… Reasoned\nAnswer])

    style Q fill:#FFD700,stroke:#DAA520,color:#000
    style A fill:#90EE90,stroke:#228B22,color:#000

๐Ÿ•ธ๏ธ Knowledge Graph Connectome

The Neo4j knowledge graph captures the reasoning structure as a rich connectome โ€” nodes represent concepts, hypotheses, and evidence, while edges represent semantic and logical relationships:

mermaid
%%{init: {'theme': 'base', 'themeVariables': {'primaryColor': '#6C63FF', 'primaryTextColor': '#fff', 'edgeLabelBackground': '#f0f0ff'}}}%%
graph TD
    RootQuery["๐Ÿ” Root Query\n(Session Node)"]

    subgraph Decomp["๐Ÿ“ Decomposition Layer"]
        D1["๐Ÿ“Œ Sub-question A\n[domain: biology]"]
        D2["๐Ÿ“Œ Sub-question B\n[domain: chemistry]"]
        D3["๐Ÿ“Œ Sub-question C\n[domain: physics]"]
    end

    subgraph Hypo["๐Ÿ’ก Hypothesis Layer"]
        H1["๐Ÿ’ญ Hypothesis 1\nconf: 0.85"]
        H2["๐Ÿ’ญ Hypothesis 2\nconf: 0.72"]
        H3["๐Ÿ’ญ Hypothesis 3\nconf: 0.61"]
        H4["๐Ÿ’ญ Hypothesis 4\nconf: 0.90"]
    end

    subgraph Evid["๐Ÿ”ฌ Evidence Layer"]
        E1["๐Ÿ“„ PubMed Paper\nPMID: 38492"]
        E2["๐Ÿ“„ Scholar Article\nDOI: 10.1038/..."]
        E3["๐ŸŒ Exa Result\nexpert consensus"]
        E4["๐Ÿ“Š Statistical\nMeta-analysis"]
    end

    subgraph Synth["๐ŸŽฏ Synthesis Layer"]
        C1["โœ… Merged\nConclusion A"]
        C2["โœ… Merged\nConclusion B"]
        FINAL["๐Ÿ† Final Answer\n[confidence: 0.88]"]
    end

    RootQuery -->|"DECOMPOSES_TO"| D1
    RootQuery -->|"DECOMPOSES_TO"| D2
    RootQuery -->|"DECOMPOSES_TO"| D3

    D1 -->|"GENERATES"| H1
    D1 -->|"GENERATES"| H2
    D2 -->|"GENERATES"| H3
    D3 -->|"GENERATES"| H4

    H1 -->|"SUPPORTED_BY"| E1
    H2 -->|"SUPPORTED_BY"| E2
    H3 -->|"CONTRADICTED_BY"| E3
    H4 -->|"SUPPORTED_BY"| E4

    H1 -->|"MERGES_WITH"| C1
    H4 -->|"MERGES_WITH"| C1
    H2 -->|"MERGES_WITH"| C2
    C1 -->|"SYNTHESIZES_TO"| FINAL
    C2 -->|"SYNTHESIZES_TO"| FINAL

    style RootQuery fill:#4A90D9,color:#fff,stroke:#2C5F8A
    style FINAL fill:#27AE60,color:#fff,stroke:#1E8449
    style H3 fill:#E74C3C,color:#fff,stroke:#C0392B

๐Ÿ” Request Flow

mermaid
%%{init: {'theme': 'base'}}%%
sequenceDiagram
    actor User as ๐Ÿค– Claude / MCP Client
    participant API as โšก FastAPI Server
    participant Auth as ๐Ÿ” Auth Middleware
    participant GTP as ๐Ÿง  GoT Processor
    participant NEO as ๐Ÿ“ฆ Neo4j DB
    participant LLM as ๐Ÿค– LLM Service

    User->>API: POST /mcp {"method": "asr_got.query"}
    API->>Auth: Verify Bearer Token
    Auth-->>API: โœ… Authorized

    API->>GTP: Process query
    GTP->>NEO: Create session + root node

    loop 8 Pipeline Stages
        GTP->>LLM: Generate hypotheses / summaries
        LLM-->>GTP: LLM response
        GTP->>NEO: Write nodes & relationships
        NEO-->>GTP: Confirmed
    end

    GTP->>NEO: Extract final subgraph
    NEO-->>GTP: Final answer graph
    GTP-->>API: Structured result

    API-->>User: JSON-RPC response\n{result, confidence, graph_state}

๐Ÿ“š Documentation

Full documentation including API reference, configuration guide, and contribution guidelines:

**โžก๏ธ Adaptive Graph of Thoughts Documentation Site**

๐Ÿ“‚ Project Structure

code
Adaptive-Graph-of-Thoughts-MCP-server/
โ”œโ”€โ”€ ๐Ÿ“ .github/             # CI/CD workflows (CodeQL, Dependabot)
โ”œโ”€โ”€ ๐Ÿ“ agt_setup/           # Interactive setup wizard CLI
โ”œโ”€โ”€ ๐Ÿ“ config/              # settings.yaml configuration
โ”œโ”€โ”€ ๐Ÿ“ docs_src/            # MkDocs documentation source
โ”œโ”€โ”€ ๐Ÿ“ helm/                # Kubernetes Helm chart
โ”œโ”€โ”€ ๐Ÿ“ src/
โ”‚   โ””โ”€โ”€ ๐Ÿ“ adaptive_graph_of_thoughts/
โ”‚       โ”œโ”€โ”€ ๐Ÿ“ api/         # FastAPI routes & schemas
โ”‚       โ”œโ”€โ”€ ๐Ÿ“ application/ # GoTProcessor orchestrator
โ”‚       โ”œโ”€โ”€ ๐Ÿ“ domain/      # 8-stage pipeline & models
โ”‚       โ”œโ”€โ”€ ๐Ÿ“ infrastructure/ # Neo4j utilities
โ”‚       โ””โ”€โ”€ ๐Ÿ“ services/    # LLM & external API clients
โ”œโ”€โ”€ ๐Ÿ“ tests/               # Comprehensive test suite
โ”œโ”€โ”€ Dockerfile
โ”œโ”€โ”€ docker-compose.yml
โ”œโ”€โ”€ pyproject.toml
โ””โ”€โ”€ README.md

๐Ÿš€ Quick Start

bash
git clone https://github.com/SaptaDey/Adaptive-Graph-of-Thoughts-MCP-server.git
cd Adaptive-Graph-of-Thoughts-MCP-server
poetry install
poetry run python -m agt_setup   # Interactive credential setup wizard
poetry run uvicorn adaptive_graph_of_thoughts.main:app --reload

Visit `http://localhost:8000/docs` for the interactive API documentation.

๐Ÿš€ Getting Started

Deployment Prerequisites

Before running Adaptive Graph of Thoughts (either locally or via Docker if not using the provided `docker-compose.prod.yml` which includes Neo4j), ensure you have:

  • A running Neo4j Instance: Adaptive Graph of Thoughts requires a connection to a Neo4j graph database.

    *Note: The provided `docker-compose.yml` (for development) and `docker-compose.prod.yml` (for production) already include a Neo4j service with the APOC library pre-configured, satisfying this requirement when using Docker Compose.*

    Prerequisites

    • Python 3.11+ (as specified in `pyproject.toml`, e.g., the Docker image uses Python 3.11.x or 3.12.x, 3.13.x)
    • **Poetry**: For dependency management
    • **Docker and Docker Compose**: For containerized deployment

    Installation and Setup (Local Development)

    1. Clone the repository:

    bash
    git clone https://github.com/SaptaDey/Adaptive-Graph-of-Thoughts-MCP-server.git
       cd Adaptive-Graph-of-Thoughts-MCP-server

    2. Install dependencies using Poetry:

    bash
    poetry install

    This creates a virtual environment and installs all necessary packages specified in `pyproject.toml`.

    3. Activate the virtual environment:

    bash
    poetry shell

    4. Configure the application:

    bash
    # Copy example configuration
       cp config/settings.example.yaml config/settings.yaml
       
       # Edit configuration as needed
       vim config/settings.yaml

    5. Set up environment variables (optional):

    bash
    # Create .env file for sensitive configuration
       echo "LOG_LEVEL=DEBUG" > .env
       echo "API_HOST=0.0.0.0" >> .env
       echo "API_PORT=8000" >> .env

    Secret Management

    In production environments, set the `SECRETS_PROVIDER` environment variable to

    `aws`, `gcp`, or `vault` to fetch sensitive values from a supported secrets

    manager. Optionally provide `_SECRET_NAME` variables (for example

    `OPENAI_API_KEY_SECRET_NAME`) to control the name of each secret. When a secrets

    provider is configured, values for `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, and

    `NEO4J_PASSWORD` are loaded automatically at startup.

    6. Run the development server:

    bash
    python src/adaptive_graph_of_thoughts/main.py

    Alternatively, for more control:

    bash
    uvicorn adaptive_graph_of_thoughts.main:app --reload --host 0.0.0.0 --port 8000

    The API will be available at `http://localhost:8000`.

    โœจ Setup Wizard

    An interactive wizard is available to streamline initial configuration.

    bash
    poetry run python -m agt_setup

    Then visit `http://localhost:8000/setup` to complete the web-based steps.

    *Setup wizard demo GIF will appear here in the full documentation.*

    Docker Deployment

    mermaid
    graph TB
        subgraph "Development Environment"
            A[๐Ÿ‘จโ€๐Ÿ’ป Developer] --> B[๐Ÿณ Docker Compose]
        end
        
        subgraph "Container Orchestration"
            B --> C[๐Ÿ“ฆ Adaptive Graph of Thoughts Container]
            B --> D[๐Ÿ“Š Monitoring Container]
            B --> E[๐Ÿ—„๏ธ Database Container]
        end
        
        subgraph "Adaptive Graph of Thoughts Application"
            C --> F[โšก FastAPI Server]
            F --> G[๐Ÿง  ASR-GoT Engine]
            F --> H[๐Ÿ”Œ MCP Protocol]
        end
        
        subgraph "External Integrations"
            H --> I[๐Ÿค– Claude Desktop]
            H --> J[๐Ÿ”— Other AI Clients]
        end
        
        style A fill:#e1f5fe
        style B fill:#f3e5f5
        style C fill:#e8f5e8
        style F fill:#fff3e0
        style G fill:#ffebee
        style H fill:#f1f8e9

    1. Quick Start with Docker Compose:

    bash
    # 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

    2. Individual Docker Container:

    bash
    # Build the image
       docker build -t adaptive-graph-of-thoughts:latest .
       
       # Run the container
       docker run -p 8000:8000 -v $(pwd)/config:/app/config adaptive-graph-of-thoughts:latest

    3. Production Deployment:

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

    Kubernetes Deployment (Helm)

    A minimal Helm chart is provided under `helm/agot-server` for

    running Adaptive Graph of Thoughts on a Kubernetes cluster.

    bash
    helm install agot helm/agot-server

    Customize values in `helm/agot-server/values.yaml` to set the image repository,

    resource limits, and other options.

    Notes on Specific Deployment Platforms

    • Smithery.ai: Deploy using the included `smithery.yaml`.

      4. Access the Services:

        ๐Ÿ”Œ MCP Client Integration

        Supported MCP Clients

        Adaptive Graph of Thoughts supports integration with various MCP clients:

        • Claude Desktop - Full STDIO and HTTP support
        • VS Code - Via MCP extensions
        • Custom MCP Clients - Generic configuration available

        Quick Client Setup

        Claude Desktop / VS Code settings

        json
        {
          "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

        ToolDescription
        `scientific_reasoning_query`Advanced scientific reasoning with graph analysis
        `analyze_research_hypothesis`Hypothesis evaluation with confidence scoring
        `explore_scientific_relationships`Concept relationship mapping
        `validate_scientific_claims`Evidence-based claim validation

        ๐Ÿ”Œ API Endpoints

        The primary API endpoints exposed by Adaptive Graph of Thoughts are:

        • MCP Protocol Endpoint: `POST /mcp`
          • This endpoint is used for communication with MCP clients like Claude Desktop.
          • Example Request for the `asr_got.query` method:
        json
        {
              "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 Endpoint: `GET /health`
            • Provides a simple health status of the application.
            • Example Response:
          json
          {
                "status": "healthy",
                "version": "0.1.0" 
              }

          The advanced API endpoints previously listed (e.g., `/api/v1/graph/query`) are not implemented in the current version and are reserved for potential future development.

          Session Handling (`session_id`)

          Currently, the `session_id` parameter available in API requests (e.g., for `asr_got.query`) and present in responses serves primarily to identify and track a single, complete query-response cycle. It is also used for correlating progress notifications (like `got/queryProgress`) with the originating query.

          While the system generates and utilizes `session_id`s, Adaptive Graph of Thoughts does not currently support true multi-turn conversational continuity where the detailed graph state or reasoning context from a previous query is automatically loaded and reused for a follow-up query using the same `session_id`. Each query is processed independently at this time.

          Future Enhancement: Persistent Sessions

          A potential future enhancement for Adaptive Graph of Thoughts is the implementation of persistent sessions. This would enable more interactive and evolving reasoning processes by allowing users to:

          1. Persist State: Store the generated graph state and relevant reasoning context from a query, associated with its `session_id`, likely within the Neo4j database.

          2. Reload State: When a new query is submitted with an existing `session_id`, the system could reload this saved state as the starting point for further processing.

          3. Refine and Extend: Allow the new query to interact with the loaded graphโ€”for example, by refining previous hypotheses, adding new evidence to existing structures, or exploring alternative reasoning paths based on the established context.

          Implementing persistent sessions would involve developing robust strategies for:

          • Efficiently storing and retrieving session-specific graph data in Neo4j.
          • Managing the lifecycle (e.g., creation, update, expiration) of session data.
          • Designing sophisticated logic for how new queries merge with, modify, or extend pre-existing session contexts and graphs.

          This is a significant feature that could greatly enhance the interactive capabilities of Adaptive Graph of Thoughts. Contributions from the community in designing and implementing persistent session functionality are welcome.

          Future Enhancement: Asynchronous and Parallel Stage Execution

          Currently, the 8 stages of the Adaptive Graph of Thoughts reasoning pipeline are executed sequentially. For complex queries or to further optimize performance, exploring asynchronous or parallel execution for certain parts of the pipeline is a potential future enhancement.

          Potential Areas for Parallelism:

          • Hypothesis Generation: The `HypothesisStage` generates hypotheses for each dimension identified by the `DecompositionStage`. The process of generating hypotheses for *different, independent dimensions* could potentially be parallelized. For instance, if three dimensions are decomposed, three parallel tasks could work on generating hypotheses for each respective dimension.
          • Evidence Integration (Partial): Within the `EvidenceStage`, if multiple hypotheses are selected for evaluation, the "plan execution" phase (simulated evidence gathering) for these different hypotheses might be performed concurrently.

          Challenges and Considerations:

          Implementing parallel stage execution would introduce complexities that need careful management:

          • Data Consistency: Concurrent operations, especially writes to the Neo4j database (e.g., creating multiple hypothesis nodes or evidence nodes simultaneously), must be handled carefully to ensure data integrity and avoid race conditions. Unique ID generation schemes would need to be robust for parallel execution.
          • Transaction Management: Neo4j transactions for concurrent writes would need to be managed appropriately.
          • Dependency Management: Ensuring that stages (or parts of stages) that truly depend on the output of others are correctly sequenced would be critical.
          • Resource Utilization: Parallel execution could increase resource demands (CPU, memory, database connections).
          • Complexity: The overall control flow of the `GoTProcessor` would become more complex.

          While the current sequential execution ensures a clear and manageable data flow, targeted parallelism in areas like hypothesis generation for independent dimensions could offer performance benefits for future versions of Adaptive Graph of Thoughts. This remains an open area for research and development.

          ๐Ÿงช Testing & Quality Assurance

          Development Commands

          Continuous integration pipelines on GitHub Actions run tests, CodeQL analysis, and Microsoft Defender for DevOps security scans.

          bash
          # Run full test suite with coverage using Poetry
          poetry run pytest --cov=src --cov-report=html --cov-report=term
          
          # Or using Makefile for the default test run
          make test
          
          # Run specific test categories (using poetry)
          poetry run pytest tests/unit/stages/          # Stage-specific tests
          poetry run pytest tests/integration/         # Integration tests
          poetry run pytest -k "test_confidence"       # Tests matching pattern
          
          # Type checking and linting (can also be run via Makefile targets: make lint, make check-types)
          poetry run mypy src/ --strict                # Strict type checking
          poetry run ruff check . --fix                # Auto-fix linting issues
          poetry run ruff format .                     # Format code
          
          # Pre-commit hooks (recommended)
          poetry run pre-commit install                # Install hooks
          poetry run pre-commit run --all-files       # Run all hooks (runs Ruff and MyPy)
          
          # See Makefile for other useful targets like 'make all-checks'.

          ๐Ÿ–ฅ Dashboard Tour

          *Dashboard demo GIF coming soon.*

          ๐Ÿ’ป IDE Integration

          Use the `vscode-agot` extension to query the server from VS Code. Run the extension and execute AGoT: Ask Graphโ€ฆ from the Command Palette.

          โ“ Troubleshooting

          If the server fails to start or setup reports errors, ensure your Neo4j instance is running and the credentials in `.env` are correct. Consult the console output for details.

          ๐Ÿ—บ๏ธ Roadmap and Future Directions

          We have an exciting vision for the future of Adaptive Graph of Thoughts! Our roadmap includes plans for enhanced graph visualization, integration with more data sources like Arxiv, and further refinements to the core reasoning engine.

          For more details on our planned features and long-term goals, please see our Roadmap (also available on the documentation site).

          ๐Ÿค Contributing

          We welcome contributions! Please see our Contributing Guidelines (also available on the documentation site) for details on how to get started, our branching strategy, code style, and more.

          ๐Ÿ“„ License

          This project is licensed under the Apache License 2.0. License.

          ๐Ÿ”’ Security

          Please see our Security Policy for reporting vulnerabilities and details on supported versions.

          ๐Ÿ™ Acknowledgments

          • NetworkX community for graph analysis capabilities
          • FastAPI team for the excellent web framework
          • Pydantic for robust data validation
          • The scientific research community for inspiration and feedback

          Frequently asked questions

          What is Adaptive-Graph-of-Thoughts-MCP-server?

          Adaptive-Graph-of-Thoughts-MCP-server is AI Reasoning Framework for Scientific Research

          How do I install Adaptive-Graph-of-Thoughts-MCP-server?

          Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.

          Is Adaptive-Graph-of-Thoughts-MCP-server open source?

          Yes โ€” it is hosted on GitHub at https://github.com/saptadey/adaptive-graph-of-thoughts-mcp-server and has 22 stars.

          Related MCP tools

          Run your own MCP server? See who uses it and what to fix.

          Measure it with TrackMCP