跳转到内容

MCP 集成

Model Context Protocol (MCP) 是一种开放协议,用于标准化应用如何向 LLM 提供工具与上下文。来自 MCP 文档:

MCP 是一种开放协议,用于标准化应用如何向 LLM 提供上下文。可以把 MCP 想象成 AI 应用的 USB‑C 接口。正如 USB‑C 为设备连接各种外设与配件提供了标准化方式,MCP 为将 AI 模型连接到不同数据源和工具提供了标准化方式。

本 SDK 支持三种 MCP 服务器类型:

  1. Hosted MCP server tools – 被 OpenAI Responses API 作为工具使用的远程 MCP 服务器
  2. Streamable HTTP MCP servers – 本地或远程服务器,实施了 Streamable HTTP 传输
  3. Stdio MCP servers – 通过标准输入/输出访问的服务器(最简单的选项)

请基于您的用例选择服务器类型:

您的需求推荐选项
使用默认的 OpenAI responses 模型调用可公开访问的远程服务器1. Hosted MCP tools
使用可公开访问的远程服务器,但在本地触发工具调用2. Streamable HTTP
使用本地运行的 Streamable HTTP 服务器2. Streamable HTTP
在非 OpenAI‑Responses 模型中使用任意 Streamable HTTP 服务器2. Streamable HTTP
使用仅支持标准 I/O 协议的本地 MCP 服务器3. Stdio

托管工具将整个往返交互推送进模型中。不是由您的代码调用 MCP 服务器,而是由 OpenAI Responses API 调用远程工具端点并将结果流式返回给模型。

下面是使用托管 MCP 工具的最简例子。您可以将远程 MCP 服务器的标签与 URL 传递给 hostedMcpTool 工具函数,用于创建托管 MCP 服务器工具。

hostedAgent.ts
import { Agent, hostedMcpTool } from '@openai/agents';
export const agent = new Agent({
name: 'MCP Assistant',
instructions: 'You must always use the MCP tools to answer questions.',
tools: [
hostedMcpTool({
serverLabel: 'gitmcp',
serverUrl: 'https://gitmcp.io/openai/codex',
}),
],
});

然后,使用 run 函数(或您自定义的 Runner 实例的 run 方法)运行该 Agent:

Run with hosted MCP tools
import { run } from '@openai/agents';
import { agent } from './hostedAgent';
async function main() {
const result = await run(
agent,
'Which language is the repo I pointed in the MCP tool settings written in?',
);
console.log(result.finalOutput);
}
main().catch(console.error);

如需流式接收增量 MCP 结果,运行 Agent 时传入 stream: true

Run with hosted MCP tools (streaming)
import { run } from '@openai/agents';
import { agent } from './hostedAgent';
async function main() {
const result = await run(
agent,
'Which language is the repo I pointed in the MCP tool settings written in?',
{ stream: true },
);
for await (const event of result) {
if (
event.type === 'raw_model_stream_event' &&
event.data.type === 'model' &&
event.data.event.type !== 'response.mcp_call_arguments.delta' &&
event.data.event.type !== 'response.output_text.delta'
) {
console.log(`Got event of type ${JSON.stringify(event.data)}`);
}
}
console.log(`Done streaming; final result: ${result.finalOutput}`);
}
main().catch(console.error);

对于敏感操作,您可以要求对单个工具调用进行人工审批。传入 requireApproval: 'always',或传入一个细粒度对象,将工具名映射为 'never'/'always'

如果您能以编程方式判断工具调用是否安全,可以使用 onApproval 回调批准或拒绝该调用。若需要人工审批,您可以像本地函数工具一样,配合 interruptions 使用相同的人机协作方法。

Human in the loop with hosted MCP tools
import { Agent, run, hostedMcpTool, RunToolApprovalItem } from '@openai/agents';
async function main(): Promise<void> {
const agent = new Agent({
name: 'MCP Assistant',
instructions: 'You must always use the MCP tools to answer questions.',
tools: [
hostedMcpTool({
serverLabel: 'gitmcp',
serverUrl: 'https://gitmcp.io/openai/codex',
// 'always' | 'never' | { never, always }
requireApproval: {
never: {
toolNames: ['search_codex_code', 'fetch_codex_documentation'],
},
always: {
toolNames: ['fetch_generic_url_content'],
},
},
}),
],
});
let result = await run(agent, 'Which language is this repo written in?');
while (result.interruptions && result.interruptions.length) {
for (const interruption of result.interruptions) {
// Human in the loop here
const approval = await confirm(interruption);
if (approval) {
result.state.approve(interruption);
} else {
result.state.reject(interruption);
}
}
result = await run(agent, result.state);
}
console.log(result.finalOutput);
}
import { stdin, stdout } from 'node:process';
import * as readline from 'node:readline/promises';
async function confirm(item: RunToolApprovalItem): Promise<boolean> {
const rl = readline.createInterface({ input: stdin, output: stdout });
const name = item.name;
const params = item.arguments;
const answer = await rl.question(
`Approve running tool (mcp: ${name}, params: ${params})? (y/n) `,
);
rl.close();
return answer.toLowerCase().trim() === 'y';
}
main().catch(console.error);

托管 MCP 也支持 OpenAI connectors。无需提供 serverUrl,改为传入 connector 的 connectorIdauthorization 令牌。Responses API 将处理认证,并通过托管 MCP 接口暴露该 connector 的工具。

Connector-backed hosted MCP tool
import { Agent, hostedMcpTool } from '@openai/agents';
const authorization = process.env.GOOGLE_CALENDAR_AUTHORIZATION!;
export const connectorAgent = new Agent({
name: 'Calendar Assistant',
instructions:
"You are a helpful assistant that can answer questions about the user's calendar.",
tools: [
hostedMcpTool({
serverLabel: 'google_calendar',
connectorId: 'connector_googlecalendar',
authorization,
requireApproval: 'never',
}),
],
});

在此示例中,环境变量 GOOGLE_CALENDAR_AUTHORIZATION 保存了从 Google OAuth Playground 获取的 OAuth 令牌,用于授权由 connector 支持的服务器调用 Calendar API。包含可运行示例(同时演示流式传输)的样例参见 examples/connectors

完整可运行的示例(托管工具/Streamable HTTP/stdio + 流式传输、HITL、onApproval)请见我们 GitHub 仓库中的 examples/mcp

当您的 Agent 直接与 Streamable HTTP MCP 服务器(本地或远程)通信时,请使用服务器的 urlname 和可选设置实例化 MCPServerStreamableHttp

Run with Streamable HTTP MCP servers
import { Agent, run, MCPServerStreamableHttp } from '@openai/agents';
async function main() {
const mcpServer = new MCPServerStreamableHttp({
url: 'https://gitmcp.io/openai/codex',
name: 'GitMCP Documentation Server',
});
const agent = new Agent({
name: 'GitMCP Assistant',
instructions: 'Use the tools to respond to user requests.',
mcpServers: [mcpServer],
});
try {
await mcpServer.connect();
const result = await run(agent, 'Which language is this repo written in?');
console.log(result.finalOutput);
} finally {
await mcpServer.close();
}
}
main().catch(console.error);

该构造函数还接受其他 MCP TypeScript‑SDK 选项,例如 authProviderrequestInitfetchreconnectionOptionssessionId。详情见 MCP TypeScript SDK 仓库及其文档。

对于仅通过标准 I/O 暴露的服务器,使用 fullCommand 实例化 MCPServerStdio

Run with Stdio MCP servers
import { Agent, run, MCPServerStdio } from '@openai/agents';
import * as path from 'node:path';
async function main() {
const samplesDir = path.join(__dirname, 'sample_files');
const mcpServer = new MCPServerStdio({
name: 'Filesystem MCP Server, via npx',
fullCommand: `npx -y @modelcontextprotocol/server-filesystem ${samplesDir}`,
});
await mcpServer.connect();
try {
const agent = new Agent({
name: 'FS MCP Assistant',
instructions:
'Use the tools to read the filesystem and answer questions based on those files. If you are unable to find any files, you can say so instead of assuming they exist.',
mcpServers: [mcpServer],
});
const result = await run(agent, 'Read the files and list them.');
console.log(result.finalOutput);
} finally {
await mcpServer.close();
}
}
main().catch(console.error);

对于 Streamable HTTPStdio 服务器,每次运行 Agent 时可能会调用 list_tools() 来发现可用工具。由于该往返会增加延迟(尤其对远程服务器),您可以通过向 MCPServerStdioMCPServerStreamableHttp 传入 cacheToolsList: true 将结果缓存在内存中。

仅当您确信工具列表不会变化时才启用此功能。若需之后使缓存失效,请在服务器实例上调用 invalidateToolsCache()

您可以限制每个服务器对外暴露的工具集,可通过 createMCPToolStaticFilter 传入静态过滤器或自定义函数。下面是一个结合两种方式的示例:

Tool filtering
import {
MCPServerStdio,
MCPServerStreamableHttp,
createMCPToolStaticFilter,
MCPToolFilterContext,
} from '@openai/agents';
interface ToolFilterContext {
allowAll: boolean;
}
const server = new MCPServerStdio({
fullCommand: 'my-server',
toolFilter: createMCPToolStaticFilter({
allowed: ['safe_tool'],
blocked: ['danger_tool'],
}),
});
const dynamicServer = new MCPServerStreamableHttp({
url: 'http://localhost:3000',
toolFilter: async ({ runContext }: MCPToolFilterContext, tool) =>
(runContext.context as ToolFilterContext).allowAll || tool.name !== 'admin',
});