dsh-mcp-bridge
Run the following command in DeepSeek Harness:
dsh plugin install Edge-Echo/dsh-mcp-bridge
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, run the command `dsh plugin install Edge-Echo/dsh-mcp-bridge`. The full source code is available at https://github.com/Edge-Echo/dsh-mcp-bridge.
About this plugin
Integrating MCP (Model Context Protocol) servers into AI agent workflows often involves manual configuration, connection troubleshooting, and verification—a time-consuming and error-prone task. The dsh-mcp-bridge plugin solves this by offering a curated bundle of battle-tested MCP servers, such as everything, memory, and filesystem. With a single installation, these servers are ready to use in DeepSeek Harness (dsh), and tools are automatically registered in a standardized format (e.g., mcp__everything__echo). Leveraging the built-in MCP client, the plugin supports hot-reloading and auto-reconnection, streamlining both setup and ongoing management. This plugin is ideal for dsh users, AI developers, and teams seeking to quickly deploy and maintain MCP servers. Whether for prototyping, testing agents, or production use, it reduces setup time and boosts reliability, making it a valuable resource for expanding agent capabilities through the MCP protocol.
Screenshots
Use Cases
- Quickly integrate multiple verified MCP servers into AI agents.
- Use pre-configured tools like file operations or browser automation in development and testing.
- Simplify MCP server management and debugging through hot-reloading.
Best For
- Developers and AI agent engineers using DeepSeek Harness.
- Teams needing efficient MCP server integration.
- Users seeking to simplify workflow configurations and enhance reliability.
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.