JSPM

  • Created
  • Published
  • Downloads 106
  • Score
    100M100P100Q97056F
  • License MIT

MCP Server for Driflyte

Package Exports

    This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@driflyte/mcp-server) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

    Readme

    Driflyte MCP Server

    Build Status NPM Version License

    MCP Server for driflyte.

    Prerequisites

    • Node.js 18+

    Quick Start

    This MCP server (using STDIO transport) can be added to any MCP Client like VS Code, Claude, Cursor, Windsurf Github Copilot via the @driflyte/mcp-server NPM package.

    VS Code

    {
      "servers": {
        "driflyte": {
          "command": "npx",
          "args": ["-y", "@driflyte/mcp-server"],
          "envFile": "${workspaceFolder}/.env"
        }
      }
    }

    Claude Desktop

    {
      "mcpServers": {
        "driflyte": {
          "command": "npx",
          "args": ["-y", "@driflyte/mcp-server"]
        }
      }
    }

    Components

    Tools

    • list-topics: Returns a list of topics for which resources (web pages, etc ...) have been crawled and content is available. This allows AI assistants to discover the most relevant and up-to-date subject areas currently indexed by the crawler.
      • Input Schema: No input parameter supported.
      • Output Schema:
        • topics:
          • Optinal: false
          • Type: Array<string>
          • Description: List of the supported topics.
    • search: Given a list of topics and a user question, this tool retrieves the top-K most relevant documents from the crawled content. It is designed to help AI assistants surface the most contextually appropriate and up-to-date information for a specific topic and query. This enables more informed and accurate responses based on real-world, topic-tagged web content.
      • Input Schema:
        • topics
          • Optinal: false
          • Type: Array<string>
          • Description: A list of one or more topic identifiers to constrain the search space. Only documents tagged with at least one of these topics will be considered.
        • query
          • Optinal: false
          • Type: string
          • Description: The natural language query or question for which relevant information is being sought. This will be used to rank documents by semantic relevance.
        • topK
          • Optinal: true
          • Type: number
          • Default Value: 10
          • Min Value: 1
          • Max Value: 30
          • Description: The maximum number of relevant documents to return. Results are sorted by descending relevance score.
      • Output Schema:
        • documents:
          • Optional: false
          • Type: Array<Document>
          • Description: Matched documents to the search query.
          • Type: Document:
            • content
              • Optinal: false
              • Type: string
              • Description: Related content (full or partial) of the matched document.
            • metadata
              • Optinal: false
              • Type: Map<string, any>
              • Description: Metadata of the document and related content in key-value format.
            • score
              • Optinal: false
              • Type: number
              • Min Value: 0
              • Max Value: 1
              • Description: Similarity score (between 0 and 1) for the content of the document.

    Resources

    N/A

    Roadmap

    • Support HTTP Stream transport protocol (SSE transport protocol is deprecated in favor of it) to be able to use the MCP server from remote.
    • Add more supported topics with their resources

    Issues and Feedback

    Issues Closed issues

    Please use GitHub Issues for any bug report, feature request and support.

    Contribution

    Pull requests Closed pull requests Contributors

    If you would like to contribute, please

    • Fork the repository on GitHub and clone your fork.
    • Create a branch for your changes and make your changes on it.
    • Send a pull request by explaining clearly what is your contribution.

    Tip: Please check the existing pull requests for similar contributions and consider submit an issue to discuss the proposed feature before writing code.

    License

    Licensed under MIT.