<picture> <source media="(prefers-color-scheme: dark)" srcset="./static/logo_white.svg"> <source media="(prefers-color-scheme: light)"
MCP Use becomes available to MCP clients through the mcp use mcp server. .
mcp-use is the fullstack MCP framework to build MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.
Once connected, the assistant can call these 10 tools directly:
Discord — Join our communityDocumentation — mcp-use.com/docsWebsite — manufact.comX.com — Follow ManufactContributing — See CONTRIBUTING.mdPreview — NamePackage — Descriptionmcp-use — Complete MCP server and MCP agent SDKcreate-mcp-use-app — Project scaffolding toolTypeScript — const server = new MCPServer({ name: "my-server", version: "1.0.0", });The server is distributed via npm as create-mcp-use-app, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.
Communication servers earn their keep on volume — summarising channels and threads that would otherwise cost you an hour of scrollback. MCP Use sits in that group, and the shape of its toolset — Discord, Documentation, Website among others — tells you what it is really for. Worth comparing against the other communication servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| Discord | [Join our community](https://discord.gg/XkNkSkMz3V) |
| Documentation | [mcp-use.com/docs](https://mcp-use.com/docs) |
| Website | [manufact.com](https://manufact.com) |
| X.com | Follow [Manufact](https://x.com/manufact) |
| Contributing | See [CONTRIBUTING.md](https://github.com/mcp-use/mcp-use/blob/main/CONTRIBUTING.md) |
| Preview | Name |
| Package | Description |
| mcp-use | Complete MCP server and MCP agent SDK |
| create-mcp-use-app | Project scaffolding tool |
| TypeScript | const server = new MCPServer({ name: "my-server", version: "1.0.0", }); |
```python
import asyncio
from langchain_openai import ChatOpenAI
from mcp_use import MCPAgent, MCPClient
async def main():
config = {
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"]
}
}
}
client = MCPClient.from_dict(config)
llm = ChatOpenAI(model="gpt-4o")
agent = MCPAgent(llm=llm, client=client)
result = await agent.run("List all files in the directory")
print(result)
asyncio.run(main())Configuration as documented by the project. Restart the client after saving.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.