Skip to content
Checking statusStatus

MCP servers

Every MCP server, local or remote, works with your key in every app that speaks MCP.

Every MCP server works with your Evolved key, in every app that speaks MCP. The servers give the model its tools (your files, GitHub, a database, Figma, Blender); the app runs them, and the model behind it decides when to call them. Point the app at evolved.to and that model is ours: tool calls, their results and streaming go through exactly as they would directly.

How it works

  1. Your app starts its MCP servers

    Local servers run on your machine; remote ones are reached at their URL. Nothing about them changes for evolved.to.

  2. It sends your prompt and the tools to evolved.to

    The tool list travels with the request, on Messages, Chat Completions or Responses, whichever your app uses.

  3. The model calls a tool, your app runs it

    The answer asks for a tool with its arguments. Your app calls the MCP server, sends the result back, and the model carries on, as many rounds as the task needs.

Every kind of MCP server

Because the app handles the connection, every MCP transport works the same on your key:

TransportWhat it isWorks
stdioA local program your app starts, such as uvx blender-mcp or npx servers✓
Streamable HTTPA remote server at a URL, the current standard for hosted servers✓
SSEOlder remote servers that stream over server-sent events✓
OAuth sign-inRemote servers that ask you to sign in (GitHub, Notion, Linear…); your app does the sign-in✓

Tools, resources and prompts from a server all reach the model, and so do images a tool returns, on models that read images.

Apps that speak MCP

Connect the app to evolved.to with its guide, then add servers where the app keeps them:

AppWhere MCP servers goConnect it
Claude Code.mcp.json in your project, or ~/.claude.jsonGuide
Claude Code in VS Code & CursorThe same files as Claude CodeGuide
Cursor.cursor/mcp.json, or Settings → MCPGuide
VS Code.vscode/mcp.json (agent mode)Guide
Codex~/.codex/config.toml, under [mcp_servers]Guide
ClineMCP Servers → ConfigureGuide
Roo CodeMCP settings, mcp_settings.jsonGuide
n8nThe MCP Client Tool node, inside an AI AgentGuide
Factory Droid, OpenClaw, Hermes Agent, Open CoworkEach app's MCP settingsGuides
BlenderThrough any app above, with the Blender MCP add-onGuide

Add a server

The same two servers in each app: Blender, a local stdio server, and GitHub, a remote HTTP one. Restart the app (or reload its MCP list) after saving.

.mcp.json · Claude Code
{
  "mcpServers": {
    "blender": { "command": "uvx", "args": ["blender-mcp"] },
    "github": { "type": "http", "url": "https://api.githubcopilot.com/mcp/" }
  }
}
.cursor/mcp.json · Cursor
{
  "mcpServers": {
    "blender": { "command": "uvx", "args": ["blender-mcp"] },
    "github": { "url": "https://api.githubcopilot.com/mcp/" }
  }
}
.vscode/mcp.json · VS Code
{
  "servers": {
    "blender": { "command": "uvx", "args": ["blender-mcp"] },
    "github": { "type": "http", "url": "https://api.githubcopilot.com/mcp/" }
  }
}
~/.codex/config.toml · Codex
[mcp_servers.blender]
command = "uvx"
args = ["blender-mcp"]

Good to know

Pick a model that is good with tools: every Claude model and GPT-5 and up handle long tool chains well. Tool calls count like any other tokens on your Usage page; a server that returns a lot of text makes requests larger.