MCP.so
Sign In

Dependency Context

@Dsinghbailey

About Dependency Context

An MCP server that provides AI assistants with contextual access to your project's dependency documentation, enabling more accurate responses about libraries and frameworks used in your codebase.

Basic information

Category

Other

License

NOASSERTION

Runtime

node

Transports

stdio

Publisher

Dsinghbailey

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "dependency-context": {
      "command": "npx",
      "args": [
        "-y",
        "--package=dependency-context",
        "dependency-context"
      ],
      "env": {
        "GITHUB_TOKEN": "YOUR_GITHUB_TOKEN_HERE",
        "MODEL_NAME": "Xenova/all-MiniLM-L6-v2",
        "DEBUG": "false",
        "MIN_CHUNK_SIZE": "800",
        "MAX_CHUNK_SIZE": "8000",
        "CHUNKS_RETURNED": "5"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Dependency Context?

An MCP server and command line tool that provides AI assistants with contextual access to your project's dependency documentation, enabling more accurate responses about libraries and frameworks used in your codebase.

How to use Dependency Context?

Configure by creating a dependency-context.json file in your project root listing the dependencies to index. If none is present, it falls back to scanning package.json or requirements.txt. Add the MCP config to your editor (Cursor recommended), then prompt the AI to initialize dependency-context. A CLI mode is also available via npx or global install for direct documentation download.

Key features of Dependency Context

  • Indexes dependency documentation from GitHub repositories
  • Provides semantic search over indexed documentation
  • Supports custom dependency configuration via dependency-context.json
  • Falls back to package.json or requirements.txt automatically
  • Includes both MCP tools and a standalone CLI mode
  • Uses local vector embeddings for offline search

Use cases of Dependency Context

  • Ask an AI assistant how to use a specific function in an installed library
  • Search across multiple dependency docs for authentication patterns
  • Quickly download raw documentation for offline browsing
  • Get accurate, context-aware answers about your project's dependencies

FAQ from Dependency Context

How does Dependency Context discover my project's dependencies?

It first looks for a custom dependency-context.json file in the project root. If not present, it falls back to scanning package.json (Node.js) or requirements.txt (Python).

What do I need to run Dependency Context?

Node.js and npm are required. A GitHub personal access token is optional but recommended to avoid API rate limits. No external database or cloud service is needed—vector embeddings run locally.

Where is the indexed documentation stored?

Documentation is cloned into a dependency-context folder within your project directory. Each dependency gets its own folder containing Markdown documentation from its repository.

What happens if my search returns empty results?

Check that the indexing process completed without errors, verify your query is relevant to the indexed dependencies, and try a more general query first.

Does Dependency Context require a GitHub token?

No, but it is recommended. Without it, you may encounter "API rate limit exceeded" errors when cloning repositories. Set it as the GITHUB_TOKEN environment variable.

Comments

More Other MCP servers