Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
mcp-use v2 is now in beta! Check it out here
Let agents write code to call MCP tools
execute_code and search_tools so agents run JavaScript with access to connected MCP tools instead of making individual tool calls. Node.js only.
import { MCPClient } from "@mcp-use/client";
const client = new MCPClient(
{
mcpServers: {
fs: {
command: "npx",
args: ["-y", "@modelcontextprotocol/server-filesystem", "./data"],
},
},
},
{ codeMode: true },
);
const result = await client.executeCode(`
const files = await fs.list_directory({ path: "." });
return files.length;
`);
console.log(result.result, result.logs, result.error);
await client.close();
| Executor | Use case |
|---|---|
"vm" (default) | Local Node.js VM — fast, trusted environments |
"e2b" | Cloud sandbox — untrusted code (@e2b/code-interpreter + API key) |
Custom function / BaseCodeExecutor | Your own runtime |
{ codeMode: {
enabled: true,
executor: "e2b",
executorOptions: { apiKey: process.env.E2B_API_KEY!, timeoutMs: 300_000 },
}}
@mcp-use/agent and PROMPTS.CODE_MODE:
import { MCPAgent, PROMPTS } from "@mcp-use/agent";
const agent = new MCPAgent({ llm, client, systemPrompt: PROMPTS.CODE_MODE });
await agent.run("List all files and count them");
searchTools, and ExecutionResult.
Anthropic: Code execution with MCPWas this page helpful?