Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Remote OpenCode MCP Server Create a new session and ask OpenCode to write a binary search algorithm."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
让 AI（如 Claude Desktop、Cursor）能真正动手干活：改代码、跑命令、跑测试。
原理：AI 负责思考和规划，本项目的 bridge 把任务传给本机的 OpenCode 执行，再把结果带回来。
uv sync
uv run opencode-mcp就这一条命令：bridge 启动时会自动拉起 opencode 后端，退出时自动回收。
Related MCP server: opencode-mcp-tool
AI 默认在你启动命令时所在的目录工作。想固定操作某个项目，在 AI 客户端配置里加一个环境变量即可（见下一节）：
"env": { "OPENCODE_WORKSPACE": "/absolute/path/to/your-project" }bridge 没有界面，需要在 AI 客户端的 MCP 设置里添加一次（以 Claude Desktop 为例）：
{
"mcpServers": {
"opencode-executor": {
"command": "uv",
"args": ["--directory", "/absolute/path/to/remote-opencode-mcp", "run", "opencode-mcp"],
"env": { "OPENCODE_WORKSPACE": "/absolute/path/to/your-project" }
}
}
}保存并重启客户端即可。之后正常对话就行，比如对 AI 说"帮我在项目里加个 README"，它会自动通过 bridge 调用 OpenCode 完成并汇报结果。
在运行 bridge 的终端按 Ctrl+C。
MIT
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Dirichelet/remote-opencode-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
