跳转到内容

MCP 集成

Model Context Protocol (MCP) 是一个开放协议,用于标准化应用如何向 LLM 提供工具和上下文。摘自 MCP 文档:

MCP 是一个开放协议,用于标准化应用如何向 LLM 提供上下文。把 MCP 想象成 AI 应用的 USB‑C 接口。正如 USB‑C 提供了将设备连接到各种外设和配件的标准化方式,MCP 也提供了将 AI 模型连接到不同数据源和工具的标准化方式。

本 SDK 支持三种 MCP 服务器类型:

  1. Hosted MCP server tools – 由 OpenAI Responses API 作为工具调用的远程 MCP 服务器
  2. Streamable HTTP MCP servers – 实现了 Streamable HTTP 传输 的本地或远程服务器
  3. Stdio MCP servers – 通过标准输入/输出访问的服务器(最简单的选项)

请根据您的用例选择服务器类型:

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
使用非 OpenAI‑Responses 模型调用任意 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过程交由模型完成。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传回模型。

下面是使用托管 MCP 工具的最简单示例。您可以将远程 MCP 服务器的标签和 URL 传给 hostedMcpTool 实用函数,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,您可以使用 run 函数(或您自定义的 Runner 实例的 run 方法)运行智能体:

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);

若要流式获取增量 MCP 结果,在运行 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',或传入一个将工具名映射到 'never'/'always' 的细粒度对象。

如果您能以编程方式判断工具调用是否安全,可以使用 onApproval 回调来批准或拒绝该调用。若需要人工审批,您可以使用与本地函数工具相同的、基于 interruptions人机协作(HITL)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.rawItem.name;
const params = item.rawItem.providerData?.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,改为传入连接器的 connectorId 和一个 authorization 令牌。Responses API 将处理身份验证,并通过托管 MCP 接口暴露连接器的工具。

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,使基于连接器的服务器能够调用 Calendar API。有关还演示了流式传输的可运行示例,请参阅 examples/connectors

功能完整的示例(托管工具/Streamable HTTP/stdio + Streaming、HITL、onApproval)请见我们 GitHub 仓库中的 examples/mcp

当您的智能体直接与本地或远程的 Streamable HTTP MCP 服务器通信时,请使用服务器的 urlname 以及任意可选设置实例化 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);

构造函数也接受其他 MCP TypeScript‑SDK 选项,如 authProviderrequestInitfetchreconnectionOptionssessionId。详见 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。由于该往返可能增加延迟(尤其对远程服务器),您可以通过向 MCPServerStdioMCPServerStreamableHttp 传入 cacheToolsList: true 来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选项。若需之后使缓存失效,可在服务器实例上调用 invalidateToolsCache()

您可以通过传入静态筛选器 createMCPToolStaticFilter 或自定义函数限制每个服务器暴露的工具。下面是同时展示两种方式的组合示例:

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',
});