What is the Model Context Protocol (MCP)?
MCP is a protocol that enables your coding AI to access and query databases, data warehouses, data pipelines, cloud services, and other tools.
@agentmode
Basic information
VS Code extension for agentmode MCP server
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
AgentMode VS Code Extension is an all-in-one Model Context Protocol (MCP) server that connects your coding AI to databases, data warehouses, data pipelines, cloud services, and more. It is designed for developers using Visual Studio Code to streamline their workflow by integrating with various data and cloud platforms.
Install the extension from the Visual Studio Code marketplace by searching for "agentmode". After installation, start the MCP server via the Command Palette (Ctrl+Shift+P or Cmd+Shift+P on macOS) by selecting "MCP: List Servers" and clicking on agentmode. Then click the "AgentMode" text in the bottom‑right corner of VS Code to open a browser tab and sign in.
MCP is a protocol that enables your coding AI to access and query databases, data warehouses, data pipelines, cloud services, and other tools.
All credentials are stored locally on your machine.
Open Visual Studio Code, go to the Extensions view, search for "agentmode", and click the Install button.
Yes, any required dependencies for connections are installed on‑the‑fly.
Start the MCP server and navigate to `http://localhost:13000/setup` in your browser. Click the icon of the connection you want to set up, then fill in the details and credentials.

Give your coding agent access to production. Search your logs in plain language, look up issues and investigate errors from Claude Code, Cursor, Codex or ChatGPT. Requires a Sazabi account; sign in with OAuth.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.
Model Context Protocol (MCP) server for TranscriptFetch: fetch YouTube transcripts, search, channels, and playlists from any MCP client.


Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
Comments