Zhihu MCP

v1.0.0Communicationstable

A simple HTTP API server that allows users to publish articles, create answers, manage columns, and upload images on Zhihu (a Chinese Q&A platform) through straightforward REST API endpoints.

zhihu-mcp-servermcpai-integration
Share:
35
Stars
0
Downloads
0
Weekly
0/5

What is Zhihu MCP?

Zhihu MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to simple http api server that allows users to publish articles, create answers, manage columns, and upload images on zhihu (a chinese q&a platform) through straightforward rest api endpoints.

A simple HTTP API server that allows users to publish articles, create answers, manage columns, and upload images on Zhihu (a Chinese Q&A platform) through straightforward REST API endpoints.

This server falls under the Communication and APIs categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A simple HTTP API server that allows users to publish articl

Use Cases

Publish articles and create answers on Zhihu platform.
Manage columns and upload images via REST API.
Integrate Zhihu content management into workflows.
Victorzwx

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 5, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx zhihu-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Zhihu MCP

zhihu-mcp-server is a Python MCP server that enables AI assistants to publish articles, post answers, manage columns, and upload images on Zhihu — China's largest Q&A and knowledge platform — through a REST API interface. It provides a straightforward HTTP API layer over Zhihu's platform, letting users automate content creation workflows where AI generates the content and the server handles the publishing, all within an MCP-compatible environment.

Prerequisites

  • Python 3.10 or higher installed
  • Google Chrome browser and ChromeDriver installed (for browser-based automation)
  • A Zhihu account with phone-number login capability
  • An MCP-compatible client such as Claude Desktop or Cherry Studio
1

Clone the repository

Clone the zh_mcp_server repository, which powers both the zh-mcp-server and zhihu-mcp-server slugs.

git clone https://github.com/Victorzwx/zh_mcp_server.git
cd zh_mcp_server
2

Install dependencies

Install the required Python packages for Selenium automation, HTTP requests, and MCP integration.

pip install -r requirements.txt
3

Install ChromeDriver

Install the ChromeDriver version that matches your installed Chrome browser version. Check your Chrome version under Help > About Google Chrome.

npx @puppeteer/browsers install [email protected]
4

Save your Zhihu login session

Run the login helper to authenticate with Zhihu. Chrome will open automatically; enter your phone number in the browser, then paste the SMS verification code back into the terminal when prompted.

python -m zh_mcp_server.__login__
5

Add the server to your MCP client config

Configure your MCP client to launch the server as a Python module. Add the following to claude_desktop_config.json or your client's equivalent settings.

{
  "mcpServers": {
    "zhihu-mcp-server": {
      "command": "python",
      "args": ["-m", "zh_mcp_server"]
    }
  }
}

Zhihu MCP Examples

Client configuration (Claude Desktop)

Configuration snippet for claude_desktop_config.json to connect Claude Desktop to the Zhihu MCP server.

{
  "mcpServers": {
    "zhihu-mcp-server": {
      "command": "python",
      "args": ["-m", "zh_mcp_server"]
    }
  }
}

Prompts to try

Example prompts to use with your AI assistant once the Zhihu MCP server is running.

- "Write a detailed article about Python async programming and publish it to my Zhihu account."
- "Create an answer to the question about best practices for code reviews and post it on Zhihu."
- "Publish a column article about machine learning for beginners on Zhihu."

Troubleshooting Zhihu MCP

ChromeDriver version mismatch causes browser launch to fail

Check your exact Chrome version (chrome://settings/help) and reinstall ChromeDriver with that specific version: `npx @puppeteer/browsers install chromedriver@<your-exact-version>`.

Session expires and articles fail to publish

Re-run `python -m zh_mcp_server.__login__` to refresh your Zhihu session cookie. Sessions expire periodically and require periodic re-authentication.

Chinese characters appear garbled in published content

Set PYTHONIOENCODING=utf-8 in the env block of your MCP config and add `--encoding=utf-8` to the args list to force UTF-8 output encoding.

Frequently Asked Questions about Zhihu MCP

What is Zhihu MCP?

Zhihu MCP is a Model Context Protocol (MCP) server that simple http api server that allows users to publish articles, create answers, manage columns, and upload images on zhihu (a chinese q&a platform) through straightforward rest api endpoints. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Zhihu MCP?

Follow the installation instructions on the Zhihu MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Zhihu MCP?

Zhihu MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Zhihu MCP free to use?

Yes, Zhihu MCP is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Communication MCP Servers

Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "zhihu-mcp-server": { "command": "npx", "args": ["-y", "zhihu-mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Zhihu MCP?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides