Skip to main content
Glama
Sign In
enesjakozh

Fledge MCP Server

by Krupalp525
GitHub
Python
MIT License
OverviewInspectNewSchemaRelated ServersReviewsScore
Need Help?View Source CodeReport Issue

Integrations

  • Enables building and deploying the Fledge MCP server using Docker containers, supporting deployment to Smithery.ai for enhanced scalability and availability.

  • Supports deployment behind an Nginx reverse proxy for production environments, enhancing security and performance for the Fledge MCP server.

  • Allows generation of React components for Fledge data visualization, enabling the creation of custom UI elements to display sensor data from Fledge instances.

Fledge MCP Server

This is a Model Context Protocol (MCP) server that connects Fledge functionality to Cursor AI, allowing the AI to interact with Fledge instances via natural language commands.

Prerequisites

  • Fledge installed locally or accessible via API (default: http://localhost:8081)
  • Cursor AI installed
  • Python 3.8+

Installation

  1. Clone this repository:
git clone https://github.com/Krupalp525/fledge-mcp.git cd fledge-mcp
  1. Install the dependencies:
pip install -r requirements.txt

Running the Server

  1. Make sure Fledge is running:
fledge start
  1. Start the MCP server:
python mcp_server.py

For secure operation with API key authentication:

python secure_mcp_server.py
  1. Verify it's working by accessing the health endpoint:
curl http://localhost:8082/health

You should receive "Fledge MCP Server is running" as the response.

Connecting to Cursor

  1. In Cursor, go to Settings > MCP Servers
  2. Add a new server:
  3. For the secure server, configure the "X-API-Key" header with the value from the api_key.txt file that is generated when the secure server starts.
  4. Test it: Open Cursor's Composer (Ctrl+I), type "Check if Fledge API is reachable," and the AI should call the validate_api_connection tool.

Available Tools

Data Access and Management

  1. get_sensor_data: Fetch sensor data from Fledge with optional filtering by time range and limit
  2. list_sensors: List all sensors available in Fledge
  3. ingest_test_data: Ingest test data into Fledge, with optional batch count

Service Control

  1. get_service_status: Get the status of all Fledge services
  2. start_stop_service: Start or stop a Fledge service by type
  3. update_config: Update Fledge configuration parameters

Frontend Code Generation

  1. generate_ui_component: Generate React components for Fledge data visualization
  2. fetch_sample_frontend: Get sample frontend templates for different frameworks
  3. suggest_ui_improvements: Get AI-powered suggestions for improving UI code

Real-Time Data Streaming

  1. subscribe_to_sensor: Set up a subscription to sensor data updates
  2. get_latest_reading: Get the most recent reading from a specific sensor

Debugging and Validation

  1. validate_api_connection: Check if the Fledge API is reachable
  2. simulate_frontend_request: Test API requests with different methods and payloads

Documentation and Schema

  1. get_api_schema: Get information about available Fledge API endpoints
  2. list_plugins: List available Fledge plugins

Advanced AI-Assisted Features

  1. generate_mock_data: Generate realistic mock sensor data for testing

Testing the API

You can test the server using the included test scripts:

# For standard server python test_mcp.py # For secure server with API key python test_secure_mcp.py

Security Options

The secure server (secure_mcp_server.py) adds API key authentication:

  1. On first run, it generates an API key stored in api_key.txt
  2. All requests must include this key in the X-API-Key header
  3. Health check endpoint remains accessible without authentication

Example API Requests

# Validate API connection curl -X POST -H "Content-Type: application/json" -d '{"name": "validate_api_connection"}' http://localhost:8082/tools # Generate mock data curl -X POST -H "Content-Type: application/json" -d '{"name": "generate_mock_data", "parameters": {"sensor_id": "temp1", "count": 5}}' http://localhost:8082/tools # Generate React chart component curl -X POST -H "Content-Type: application/json" -d '{"name": "generate_ui_component", "parameters": {"component_type": "chart", "sensor_id": "temp1"}}' http://localhost:8082/tools # For secure server, add API key header curl -X POST -H "Content-Type: application/json" -H "X-API-Key: YOUR_API_KEY" -d '{"name": "list_sensors"}' http://localhost:8082/tools

Extending the Server

To add more tools:

  1. Add the tool definition to tools.json
  2. Implement the tool handler in mcp_server.py and secure_mcp_server.py

Production Considerations

For production deployment:

  • Use HTTPS
  • Deploy behind a reverse proxy like Nginx
  • Implement more robust authentication (JWT, OAuth)
  • Add rate limiting
  • Set up persistent data storage for subscriptions

Deploying on Smithery.ai

The Fledge MCP Server can be deployed on Smithery.ai for enhanced scalability and availability. Follow these steps to deploy:

  1. Prerequisites
    • Docker installed on your local machine
    • A Smithery.ai account
    • The Smithery CLI tool installed
  2. Build and Deploy
    # Build the Docker image docker build -t fledge-mcp . # Deploy to Smithery.ai smithery deploy
  3. Configuration The smithery.json file contains the configuration for your deployment:
    • WebSocket transport on port 8082
    • Configurable Fledge API URL
    • Tool definitions and parameters
    • Timeout settings
  4. Environment Variables Set the following environment variables in your Smithery.ai dashboard:
    • FLEDGE_API_URL: Your Fledge API endpoint
    • API_KEY: Your secure API key (if using secure mode)
  5. Verification After deployment, verify your server is running:
    smithery status fledge-mcp
  6. Monitoring Monitor your deployment through the Smithery.ai dashboard:
    • Real-time logs
    • Performance metrics
    • Error tracking
    • Resource usage
  7. Updating To update your deployment:
    # Build new image docker build -t fledge-mcp . # Deploy updates smithery deploy --update

JSON-RPC Protocol Support

The server implements the Model Context Protocol (MCP) using JSON-RPC 2.0 over WebSocket. The following methods are supported:

  1. initialize
    { "jsonrpc": "2.0", "method": "initialize", "params": {}, "id": "1" }
    Response:
    { "jsonrpc": "2.0", "result": { "serverInfo": { "name": "fledge-mcp", "version": "1.0.0", "description": "Fledge Model Context Protocol (MCP) Server", "vendor": "Fledge", "capabilities": { "tools": true, "streaming": true, "authentication": "api_key" } }, "configSchema": { "type": "object", "properties": { "fledge_api_url": { "type": "string", "description": "Fledge API URL", "default": "http://localhost:8081/fledge" } } } }, "id": "1" }
  2. tools/list
    { "jsonrpc": "2.0", "method": "tools/list", "params": {}, "id": "2" }
    Response: Returns the list of available tools and their parameters.
  3. tools/call
    { "jsonrpc": "2.0", "method": "tools/call", "params": { "name": "get_sensor_data", "parameters": { "sensor_id": "temp1", "limit": 10 } }, "id": "3" }

Error Codes

The server follows standard JSON-RPC 2.0 error codes:

  • -32700: Parse error
  • -32600: Invalid Request
  • -32601: Method not found
  • -32602: Invalid params
  • -32000: Server error

This server cannot be installed

-
security - not tested
A
license - permissive license
-
quality - not tested

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

Connects Fledge functionality to Cursor AI, allowing interaction with Fledge instances via natural language commands.

  1. Prerequisites
    1. Installation
      1. Running the Server
        1. Connecting to Cursor
          1. Available Tools
            1. Data Access and Management
            2. Service Control
            3. Frontend Code Generation
            4. Real-Time Data Streaming
            5. Debugging and Validation
            6. Documentation and Schema
            7. Advanced AI-Assisted Features
          2. Testing the API
            1. Security Options
              1. Example API Requests
                1. Extending the Server
                  1. Production Considerations
                    1. Deploying on Smithery.ai
                      1. JSON-RPC Protocol Support
                        1. Error Codes

                      Related MCP Servers

                      • Cursor MCP Server

                        johnneerdael
                        -
                        security
                        A
                        license
                        -
                        quality
                        Acts as a bridge between Claude's desktop application and the Cursor editor, enabling seamless AI-powered automation and multi-instance management across platforms with standardized communication and secure token-based authentication.
                        Last updated -
                        21
                        46
                        TypeScript
                        MIT License
                        • Apple
                        • Linux

                      • Talk to Figma MCP

                        sonnylazuardi
                        A
                        security
                        A
                        license
                        A
                        quality
                        An MCP server integration that enables Cursor AI to communicate with Figma, allowing users to read designs and modify them programmatically through natural language commands.
                        Last updated -
                        19
                        5,185
                        3,528
                        JavaScript
                        MIT License
                        • Apple
                        • Linux

                      • Metabase Server MCP

                        berry-street
                        -
                        security
                        F
                        license
                        -
                        quality
                        Enables AI assistants to interact with Metabase, providing access to dashboards, questions, databases, and tools for executing queries and viewing data through natural language.
                        Last updated -
                        JavaScript
                        • Apple

                      • Talk to Figma MCP

                        yhc984
                        -
                        security
                        F
                        license
                        -
                        quality
                        Enables Cursor AI to interact with Figma designs, allowing users to read design information and programmatically modify elements through natural language commands.
                        Last updated -
                        TypeScript

                      View all related MCP servers

                      New MCP Servers

                      ID: 4a3t88dbgq