Parsey McParseface
[Archive] A simple Python Flask app to run Parsey McParseface.
What is Parsey McParseface?
Parsey McParseface is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to [archive] a simple python flask app to run parsey mcparseface.
[Archive] A simple Python Flask app to run Parsey McParseface.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP protocol support
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx parsey-mcparsefaceConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Parsey McParseface
Parsey McParseface Server is a Python Flask application that wraps Google's Parsey McParseface dependency parser and exposes it over HTTP as an API. It allows clients to submit sentences and receive syntactic parse trees showing grammatical relationships between words. Researchers and NLP developers who need dependency parsing integrated into larger pipelines can use this server to query Parsey McParseface programmatically without invoking the TensorFlow model directly each time.
Prerequisites
- Ubuntu 14.04 x64 (the TensorFlow/models dependency is tightly version-constrained to this environment)
- A custom build of TensorFlow models from the author's fork (github.com/JoshData/models, online-parsing branch)
- Python 2 or 3 with Flask and the dependencies from the models fork
- An MCP-compatible client to connect to the running server
Follow the custom TensorFlow/models installation
This server requires a non-standard TensorFlow models installation. Follow the author's Ubuntu 14.04 setup guide linked in the README, which patches the models repo to keep Parsey McParseface running across multiple parse requests.
Clone the author's models fork on the online-parsing branch
The standard tensorflow/models package will not work. You must clone JoshData's fork and check out the online-parsing branch, which keeps the parser process alive between requests.
git clone https://github.com/JoshData/models.git
cd models
git checkout online-parsingClone the Parsey McParseface server repository
Clone the Flask server that wraps the running parser process and exposes it as an HTTP API endpoint.
git clone https://github.com/JoshData/parsey-mcparseface-server.git
cd parsey-mcparseface-serverInstall Python dependencies and start the Flask server
Install the required Python packages and launch the Flask application. The server will expose a local HTTP endpoint for parse requests.
pip install -r requirements.txt
python server.pyConfigure your MCP client to connect to the server
Point your MCP client at the running Flask server. Because this is an archived project without a packaged MCP entry point, you connect via the HTTP endpoint exposed by the Flask app.
{
"mcpServers": {
"parsey-mcparseface": {
"command": "npx",
"args": ["parsey-mcparseface"]
}
}
}Parsey McParseface Examples
Client configuration
Basic MCP client configuration for the Parsey McParseface server. The server must already be running locally before the client connects.
{
"mcpServers": {
"parsey-mcparseface": {
"command": "npx",
"args": ["parsey-mcparseface"]
}
}
}Prompts to try
Sample prompts for using the dependency parser to analyze grammatical structure of English sentences.
- "Parse the sentence 'The quick brown fox jumps over the lazy dog' and show the dependency tree"
- "What is the grammatical subject of 'Scientists discovered a new species of deep-sea fish'?"
- "Show me the dependency relationships in 'She gave him a book for his birthday'"Troubleshooting Parsey McParseface
ImportError or model loading failures on startup
The server only works with JoshData's fork of tensorflow/models on the online-parsing branch. The standard pip install tensorflow-models package is incompatible. Verify you cloned github.com/JoshData/models and checked out the online-parsing branch before starting the Flask server.
Server crashes after the first parse request
This is precisely the issue the online-parsing branch fixes by keeping the TensorFlow session alive. If you see crashes after the first request, confirm you are on the correct branch with git branch inside the models repository.
This project is archived and unmaintained
The author has noted they do not respond to issues in this repository. For production NLP parsing needs, consider alternatives such as spaCy (which has active MCP integrations) or Stanford NLP, which offer better long-term support and broader platform compatibility.
Frequently Asked Questions about Parsey McParseface
What is Parsey McParseface?
Parsey McParseface is a Model Context Protocol (MCP) server that [archive] a simple python flask app to run parsey mcparseface. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Parsey McParseface?
Follow the installation instructions on the Parsey McParseface GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Parsey McParseface?
Parsey McParseface works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Parsey McParseface free to use?
Yes, Parsey McParseface is open source and available under the CC0-1.0 license. You can use it freely in both personal and commercial projects.
Parsey McParseface Alternatives — Similar Developer Tools Servers
Looking for alternatives to Parsey McParseface? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Parsey McParseface in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Parsey McParseface?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.