agentleFS
Sign inStart free
adezeadeze/raindrop-mcp/.github/skills/dxt-packaging/SKILL.md

dxt-packaging

Skill188 starsChanged 8 months agoMITView on GitHub

MCPB (Model Context Protocol Bundle) Packaging and Distribution

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Add appropriate logging and debugging capabilities

    line 42
  2. Distinctive:

    Use structured logging for error tracking

    line 43
  3. Distinctive:

    Verify manifest loads correctly and host integration works

    line 49
  4. Distinctive:

    Follow the exact MCPB specifications to ensure ecosystem compatibility

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

MCPB Packaging Skill (DXT legacy)

Guidelines for building and packaging MCP servers as MCP Bundles (MCPB). DXT references are legacy.

Overview

MCP Bundles (MCPB) allow AI assistants to discover and use MCP servers from a package archive. This skill covers the complete MCPB development workflow.

Getting Started

Read the Specifications

  1. Architecture & Overview: https://github.com/anthropics/mcpb
  2. MCPB Repository: https://github.com/anthropics/mcpb
  • README.md - Architecture overview, capabilities, and integration patterns
  • MANIFEST.md - Complete bundle manifest structure and field definitions
  • examples/ - Reference implementations including a "Hello World" example

Create Proper Bundle Structure

  • Generate a valid manifest.json following the MANIFEST.md spec
  • Implement an MCP server using @modelcontextprotocol/sdk with proper tool definitions
  • Include proper error handling and timeout management

Development Best Practices

MCP Protocol Communication

  • Implement proper MCP protocol communication via stdio transport
  • Structure tools with clear schemas, validation, and consistent JSON responses
  • Make use of the fact that this bundle will be running locally

Logging & Debugging

  • Add appropriate logging and debugging capabilities
  • Use structured logging for error tracking
  • Include proper documentation and setup instructions

Testing Considerations

  • Validate that all tool calls return properly structured responses
  • Verify manifest loads correctly and host integration works
  • Generate complete, production-ready code that can be immediately tested
  • Focus on defensive programming and clear error messages
  • Follow the exact MCPB specifications to ensure ecosystem compatibility

Key Files

  • manifest.json - Bundle metadata and configuration
  • src/index.ts - Main entry point for the MCP server
  • build/ - Compiled output for distribution

References

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free