MCP-base

MCPAI代理

提供方 Asthanaji05

AI代理 stdio · 本地进程 OAuth 授权 社区 / 第三方 Claude DesktopClaudeCursor
查看接入方式

OpenAPI MCP is a lightweight tool that converts any OpenAPI 3 spec into an MCP server for quickly connecting existing APIs to AI clients such as Claude and Cursor.

一句话选型结论

按资料字段整理

MCP-base 属于AI代理类 MCP 服务器,stdio · 本地进程,OAuth 授权,可直接接入 Claude Desktop、Claude、Cursor,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类AI代理 传输方式stdio · 本地进程 鉴权OAuth 授权 部署方式本地部署
GitHub 星标 0 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

AI代理
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

Local Deployment MCP Server OpenAPI 3 JavaScript API Integration AI Client Node.js Tool OAuth Authentication

支持客户端

适用场景

Local DeploymentMCP ServerOpenAPI 3

安装与配置

stdio · 本地进程 OAuth 授权
客户端在本机拉起子进程,数据不出本机
node /full/path/openapi-mcp.mjs /full/path/animechan.openapi.json

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 node,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
给代理接外部能力

让代理在任务中途调用搜索、数据库等真实工具。

多步任务编排

把一串操作拆成步骤,由代理按顺序执行。

自动化重复流程

把固定流程交给代理跑,减少手工操作。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude、Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 使用前要准备好OAuth 授权对应的凭据,并按最小权限配置。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在AI代理场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
MCP-base当前 未标注 stdio · 本地进程 本地部署 有 2026-10-12
Filesystem 560c4363 13 未标注 本地部署 无 2026-05-17
Server Everything (everything) 11 stdio · 本地进程 本地部署 有 2026-05-17
Time 7365cb6d 2 SSE · 服务端推送 远程部署 有 2026-05-18
Everything Claude Code 未标注 stdio · 本地进程 本地部署 有 2026-05-17
Openmemory 557e1585 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

AI代理
字段来自项目仓库与公开索引,中文说明由本站标注
提供方Asthanaji05上游标注的维护方 Asthanaji05
分类AI代理本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式OAuth 授权远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · node本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-10-12上游最后核验时间

详细介绍

6.5 KB
来自项目仓库与上游目录的原文,未做删改

OpenAPI MCP

Turn any OpenAPI 3 spec into a working MCP server. One file, about 130 lines, no dependencies.```
node openapi-mcp.mjs https://your-api.com/openapi.json


Every API endpoint becomes a tool that an AI client (Claude, Cursor, etc.) can call. There is no code generation and no per-endpoint files. The spec is read at startup, and the tools are built in memory.

## Quick start

Requires Node 18 or newer.```bash
git clone <this-repo>
cd openapi-mcp
node openapi-mcp.mjs sample/animechan.openapi.json

It prints openapi-mcp: 4 tools from "Animechan" -> ... and then waits silently for an MCP client. That is normal: it talks JSON-RPC over stdin/stdout and is not meant to be read by humans.

Use it with an AI client

Claude Desktop (local mode)

Add this to ~/Library/Application Support/Claude/claude_desktop_config.json, then restart the app:```json
{
"mcpServers": {
"animechan": {
"command": "node",
"args": ["/full/path/openapi-mcp.mjs", "/full/path/animechan.openapi.json"]
}
}
}


If the client can't find `node`, use the full path from `which node`.

### Claude Code (remote mode)

Start the server, then register it:```bash
MCP_AUTH_TOKEN=secret node openapi-mcp.mjs sample/animechan.openapi.json --http 8787

claude mcp add --transport http animechan http://localhost:8787/mcp \
  --header "Authorization: Bearer secret"

Then ask in plain English: "give me a random quote from Naruto".

Two modes

Mode Command Use when
Local (stdio) node openapi-mcp.mjs The client launches the server on your machine
Remote (HTTP) node openapi-mcp.mjs --http The client connects to a URL, or you want to self-host

In HTTP mode, clients send JSON-RPC messages as POST http://host:/mcp. Put --http last.

Test it by hand:```bash
curl -X POST localhost:8787/mcp -H 'Authorization: Bearer secret' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'


## Options```
node openapi-mcp.mjs <spec-url-or-file> [base-url] [--http <port>]

Argument / env var · What it does
` · OpenAPI 3 spec, as a URL or a local file (JSON; YAML needsnpm i yaml)[base-url]· Overrides the API address. Defaults toservers[0].urlin the specAPI_TOKEN· Your secret for the API. The spec'ssecuritySchemesdecide where it goes (see Authentication)OAUTH_CLIENT_ID,OAUTH_CLIENT_SECRET· OAuth2 client-credentials: the token is fetched and refreshed automaticallyOAUTH_REFRESH_TOKEN· OAuth2 refresh-token grant (use with the client id and secret)OAUTH_TOKEN_URL,OAUTH_SCOPE· Optional: override thetokenUrlfrom the spec, or request a scopeAPI_HEADERS· Extra headers sent on every call, for anything the schemes don't cover. Example:'{"X-App-Id":"abc"}'TOOL_FILTER· Regex. Only tools whose name matches are exposed. Example:'^(get\ · list)'for read-onlyMCP_AUTH_TOKEN· HTTP mode only. RequiresAuthorization: Bearer ` on every request

Big APIs can have hundreds of endpoints. Too many tools makes the model choose worse, so use TOOL_FILTER to keep the useful ones.

Authentication

The server reads securitySchemes from the spec and puts your secret in the right place. You only supply the secret as an environment variable:

Spec says Set Sent as
http / bearer API_TOKEN=tok Authorization: Bearer tok
http / basic API_TOKEN=user:pass Authorization: Basic
apiKey in header API_TOKEN=key The header named in the spec (e.g. X-Key: key)
apiKey in query API_TOKEN=key The query parameter named in the spec
apiKey in cookie API_TOKEN=key Cookie: name=key
oauth2 / openIdConnect, you already have an access token API_TOKEN=token Authorization: Bearer token
oauth2, machine-to-machine OAUTH_CLIENT_ID + OAUTH_CLIENT_SECRET Token fetched from the tokenUrl, cached, and renewed before it expires
oauth2, you logged in once elsewhere the two above + OAUTH_REFRESH_TOKEN Access tokens renewed from the refresh token

Example for Claude Desktop:json { "mcpServers": { "my-api": { "command": "node", "args": ["/full/path/openapi-mcp.mjs", "https://my-api.com/openapi.json"], "env": { "API_TOKEN": "your-secret" } } } }

Notes:
- If the spec declares a security scheme but no credentials are set, a warning is printed to stderr at startup.
- If the spec lists several schemes, the first one in the top-level security list is used (or the first one defined). Per-endpoint security overrides are not applied, so the secret is sent on every call.
- OAuth client credentials are sent as HTTP Basic auth to the token endpoint.
- The OAuth browser login (authorization-code flow) is not built in. Get a token or refresh token once with your provider's tools, then pass it in.
- If a provider rotates refresh tokens, the new one is kept in memory only, so it is lost on restart.

How it works

  1. Load the spec and resolve $ref pointers.
  2. Build tools: each operation becomes one MCP tool. operationId is the name, summary the description, and parameters plus request body the input schema.
  3. Call: a tool call makes the real HTTP request and returns HTTP followed by the response body (cut at 50,000 characters).
  4. Serve the tools over JSON-RPC 2.0, via stdio or HTTP.

APIs without an OpenAPI spec

Many small public APIs only have HTML docs. For those, write a small spec by hand (see sample/animechan.openapi.json, 4 tools in about 35 lines), then run it the same way.

Limitations

  • OpenAPI 3 only. Convert Swagger 2.0 specs first.
  • JSON request bodies only. No file uploads.
  • Auth: bearer, basic, API keys, and OAuth2 client-credentials or refresh-token. There is no interactive OAuth login, and one scheme is used per API.
  • HTTP mode speaks plain HTTP (put HTTPS in front when deploying) and has no streaming, batch requests, or OAuth for clients connecting to the server (it only supports the MCP_AUTH_TOKEN bearer token). Some remote clients may require these.
  • HTTP mode speaks plain HTTP (put HTTPS in front when deploying) and has no streaming, batch requests, or OAuth. Some remote clients may require these.
  • If you deploy remotely, every user shares your server's IP, so upstream rate limits apply to all of them. Set MCP_AUTH_TOKEN, or anyone who finds the URL can use your API key.

Contributing

Issues and pull requests are welcome. The goal is to stay small and readable, so please keep new features to a few lines each.

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
MCP-base 怎么安装?

在客户端按下面的安装命令接入:node /full/path/openapi-mcp.mjs /full/path/animechan.openapi.json。装完在客户端配置里引用同一个包或端点。

MCP-base 怎么在 Claude Desktop、Claude、Cursor 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

MCP-base 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

MCP-base 需要 API Key 吗?

资料标注需要OAuth 授权认证,使用前准备好对应凭据,并按最小权限配置。

MCP-base 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cursor;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

MCP-base 能提供哪些能力?

资料显示能力标签包括 Local Deployment、MCP Server、OpenAPI 3、JavaScript、API Integration、AI Client。具体工具清单以官方文档为准。

MCP-base 需要什么运行环境?

运行时为 node;属于本地进程,需要在本机装好运行环境。

MCP-base 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-10-12。