Typingmind MCP

MCP开发工具

提供方 TypingMind

开发工具 HTTP · 远程 无需鉴权 社区 / 第三方
查看接入方式

Run MCP servers securely.

一句话选型结论

按资料字段整理

Typingmind MCP 属于开发工具类 MCP 服务器,HTTP · 远程,无需鉴权,有可直接复制的远程端点配置。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。

分类开发工具 传输方式HTTP · 远程 鉴权无需鉴权 部署方式远程部署
GitHub 星标 未标注 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

开发工具
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

适用场景

developer-tools

安装与配置

HTTP · 远程 无需鉴权
连远程 HTTPS 端点,通常为 Streamable HTTP
npx @typingmind/mcp <auth-token>

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

    确认你的客户端支持远程端点,并拿到服务地址。

  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
代码与仓库操作

在对话里直接查代码、提 issue、走 PR,省掉来回切工具。

本地命令与脚本

把构建、测试、格式化这类重复命令交给模型执行。

接口联调与测试

让模型调你的接口、跑一遍用例,快速定位问题。

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。
  • 资料标注无需鉴权,装好就能连。

先想清楚的地方

  • 远程端点依赖网络与服务方可用性,注意密钥与调用额度。
  • 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

  • 需要在开发工具场景里让模型直接调用外部能力的人。
  • 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

  • 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
Typingmind MCP当前 未标注 HTTP · 远程 远程部署 有 2026-05-18
Git 838e2ec1 12 stdio · 本地进程 本地部署 有 2026-05-17
Markitdown MCP 2c653a5f 1 stdio · 本地进程 本地部署 有 2026-05-17
JavaGuide 未标注 stdio · 本地进程 本地部署 有 2026-04-11
awesome-claude-skills 未标注 stdio · 本地进程 本地部署 有 2026-04-26
Context7 831acf40 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

开发工具
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TypingMind上游标注的维护方 TypingMind
分类开发工具本站按上游分类展示
连接方式HTTP · 远程连远程 HTTPS 端点,通常为 Streamable HTTP
鉴权方式无需鉴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.js本地安装时用到的包标识与运行时
部署类型远程部署上游给出的部署形态
最近核验2026-05-18上游最后核验时间

详细介绍

7.2 KB
来自项目仓库与上游目录的原文,未做删改

MCP Connector

MCP Connector is a lightweight server that can run and manage multiple Model Context Protocol (MCP) servers, specifically designed to integrate with TypingMind. It provides an easy way to run MCP servers on your local computer or a remote server, making it possible to connect your custom AI models or tools with TypingMind through a simple REST API.


How to Run on Your Local Device

You can quickly start the MCP Connector using npx (no install required):```bash
npx @typingmind/mcp@latest <auth-token>


- Replace `` with your authentication token provided by TypingMind.

You can also provide the auth token via an environment variable:```bash
MCP_AUTH_TOKEN=&lt;auth-token&gt; npx @typingmind/mcp@latest

Keep the process running while you use TypingMind.

HTTPS Support

To enable HTTPS, set the following environment variables:```bash
CERTFILE=./path/to/certificate.crt KEYFILE=./path/to/privatekey.key npx @typingmind/mcp@latest <auth-token>


- `CERTFILE`: Path to your SSL certificate file
- `KEYFILE`: Path to your SSL private key file

When both variables are set, the server will use HTTPS instead of HTTP.

---

## How to Run on a Server

If you prefer running the MCP Connector on a remote server:

1. **Install Node.js** (version 14 or later).
2. Run the server using `npx`:```bash
   npx @typingmind/mcp@latest &lt;auth-token&gt;
   ```

   To run with HTTPS:```bash
   CERTFILE=./path/to/certificate.crt KEYFILE=./path/to/privatekey.key npx @typingmind/mcp@latest &lt;auth-token&gt;
   ```

   Alternatively, for persistent running (e.g., after closing SSH), you may use a process manager like pm2 or `screen`/`tmux`:```bash
   pm2 start npx -- @typingmind/mcp@latest &lt;auth-token&gt;
   ```

---

## How to Run with Docker

You can also run the MCP Connector using Docker.

1.  **Build the Docker Image:**
    Navigate to the project&#x27;s root directory (where the `Dockerfile` is located) and run:```bash
    docker build -t mcp-connector .
    ```

    _(You can replace `mcp-connector` with your preferred image tag.)_

2.  **Run the Docker Container:**

    - **Basic Run (HTTP):**
      Replace `` with your actual token. This command runs the container in detached mode (`-d`) and maps the container&#x27;s default port `50880` to the same port on your host machine.```bash
      docker run -d -p 50880:50880 --name mcp-connector-instance mcp-connector &lt;auth-token&gt;
      ```

    - **Using a Different Port:**
      If you need to use a different port (e.g., 8080 on the host mapped to 12345 in the container), use the `-p` flag for mapping and the `-e PORT` environment variable:```bash
      docker run -d -p 8080:12345 -e PORT=12345 --name mcp-connector-instance mcp-connector &lt;auth-token&gt;
      ```

    - **Running with HTTPS:**
      To enable HTTPS, you need to provide the certificate and key files and set the `CERTFILE` and `KEYFILE` environment variables. Mount your host&#x27;s certificate files into the container (e.g., into a `/certs` directory) and provide the paths via environment variables. Remember to map the appropriate port.```bash
      docker run -d \
        -p 50880:50880 \
        -e PORT=50880 \
        -e CERTFILE=/certs/certificate.crt \
        -e KEYFILE=/certs/privatekey.key \
        -v /path/to/your/certificate.crt:/certs/certificate.crt:ro \
        -v /path/to/your/privatekey.key:/certs/privatekey.key:ro \
        --name mcp-connector-instance \
        mcp-connector &lt;auth-token&gt;
      ```

      _(Replace `/path/to/your/certificate.crt` and `/path/to/your/privatekey.key` with the actual paths on your host machine. The `:ro` flag mounts them as read-only.)_

    - **Viewing Logs:**
      To see the logs from the running container:```bash
      docker logs mcp-connector-instance
      ```

    - **Stopping the Container:**```bash
      docker stop mcp-connector-instance
      ```

    - **Removing the Container:**```bash
      docker rm mcp-connector-instance
      ```

---

## How to Connect to TypingMind

To connect MCP Connector to TypingMind:

1. Follow the instructions at www.typingmind.com/mcp.
2. Paste your MCP Connector server address (`http://localhost:` or your server’s IP address and port) and your authentication token on the TypingMind MCP integration page.

---

## Configuring Tool Call Timeout

You can set a custom timeout for tool calls (in milliseconds) using the `TIMEOUT` environment variable:```bash
# Set timeout to 2 minutes (120000ms)
TIMEOUT=120000 npx @typingmind/mcp@latest &lt;auth-token&gt;

# Or combine with auth token environment variable
TIMEOUT=120000 MCP_AUTH_TOKEN=&lt;auth-token&gt; npx @typingmind/mcp@latest

# Default timeout is 60 seconds (60000ms) if not specified
npx @typingmind/mcp@latest &lt;auth-token&gt;

REST API Endpoints

All API endpoints require authentication via the Bearer token you provide when starting the server.

Endpoint Method Description
/ping GET Health check; returns { status: &quot;ok&quot; }
/start POST Start one or more MCP clients; body: { mcpServers: { ... } }
/restart/:id POST Restart a specific client
/clients GET List all running MCP clients and their tools
/clients/:id GET Get info about a specific client
/clients/:id/tools GET List available tools for a client
/clients/:id/call_tools POST Call a tool for a client; body: { name, arguments }
/clients/:id DELETE Stop and delete a client
/mcp-connect POST Proxy fetch requests; body: { url, options? }

Notes:

  • All requests need an Authorization: Bearer header.
  • Available ports: The server will choose port 50880 or 50881, make sure
    these ports are available in your system. You can also use PORT environment
    variable to specify a different port.

/mcp-connect Endpoint

The /mcp-connect endpoint acts as a proxy for fetch requests, allowing you to make HTTP requests through the MCP Connector server. This is useful for connecting to remote MCP servers or making cross-origin requests.

Request Body:

  • url (required): The URL to fetch
  • options (optional): Fetch options object (method, headers, body, etc.)

Response:

  • The endpoint streams the response from the target URL, including status code, headers, and body
  • Certain headers are filtered out to prevent decoding issues (Content-Encoding, Content-Length, Transfer-Encoding, and CORS headers)
  • All proxied headers are exposed via Access-Control-Expose-Headers for CORS compatibility

Example:bash curl -X POST http://localhost:50880/mcp-connect \ -H &quot;Authorization: Bearer &lt;auth-token&gt;&quot; \ -H &quot;Content-Type: application/json&quot; \ -d &#x27;{ &quot;url&quot;: &quot;https://example.com/api/endpoint&quot;, &quot;options&quot;: { &quot;method&quot;: &quot;POST&quot;, &quot;headers&quot;: { &quot;Content-Type&quot;: &quot;application/json&quot; }, &quot;body&quot;: &quot;{\&quot;key\&quot;: \&quot;value\&quot;}&quot; } }&#x27;


License

MIT

常见问题

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

在客户端按下面的安装命令接入:npx @typingmind/mcp <auth-token>。装完在客户端配置里引用同一个包或端点。

Typingmind MCP 怎么在客户端里配置?

它的传输方式未标注,在客户端 MCP 配置里按官方文档填写启动命令和参数,保存后重启客户端生效。

Typingmind MCP 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。

Typingmind MCP 需要 API Key 吗?

资料标注为无需认证,装好就能连;如果实际调用时报鉴权错误,按官方文档补上凭据。

Typingmind MCP 能提供哪些能力?

资料显示能力标签包括 轻量级、JavaScript、模型集成。具体工具清单以官方文档为准。

Typingmind MCP 需要什么运行环境?

运行时为 Node.js;属于远程端点,不需要在本地装运行时。

Typingmind MCP 是本地还是远程?

它是远程端点,连服务地址即可。传输方式为HTTP · 远程。

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 2026-05-18。