What languages are supported?
Any language that has a corresponding VS Code language extension installed.
@biegehydra
Basic information
VSCode Extension with an MCP server that exposes semantic tools like Find Usages and Rename to LLMs
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"Bifrost": {
"command": "npx",
"args": [
"-y",
"supergateway",
"--sse",
"http://localhost:8008/sse"
],
"disabled": false,
"autoApprove": [],
"timeout": 600
}
}
}Perform rename on a symbol
This VS Code extension provides a Model Context Protocol (MCP) server that exposes VSCode’s development tools and language features to AI assistants. It enables advanced code navigation, analysis, and manipulation for developers using AI coding tools that support the MCP protocol.
Install the extension from the VS Code marketplace, then install language-specific extensions for your project. The server starts automatically on port 8008 (configurable via bifrost.config.json). Configure your MCP‑compatible AI assistant to connect to http://localhost:8008/sse for SSE and http://localhost:8008/message for messages. For multiple projects, create a bifrost.config.json per project with a unique port and path.
Any language that has a corresponding VS Code language extension installed.
Visual Studio Code version 1.93.0 or higher, and appropriate language extensions for your project.
Create a `bifrost.config.json` in each project root with `projectName`, `description`, `path`, and a unique `port` (default 8008). Each project then gets its own SSE and message endpoints.
The server uses HTTP with Server‑Sent Events (SSE). The SSE endpoint is at `/sse` and the message endpoint at `/message`.

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Zyte MCP is a remote MCP server available at https://mcp.zyte.com/v1/mcp/, that lets an agent use Zyte on your behalf: to get web pages, to extract data from them, to search the web, and to work with your Scrapy Cloud pr
Comments