Resume Parser

resume parser MCP

python

0

GitHub Stars

python

Language

4 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "acidlambunk-resume-parser-mcp": {
      "command": "uv",
      "args": [
        "run",
        "mcp",
        "dev",
        "main.py"
      ],
      "env": {
        "GEMINI_MODEL": "gemini-2.0-flash",
        "GEMINI_API_KEY": "YOUR_GEMINI_API_KEY"
      }
    }
  }
}

You have a JSON-to-JSON Resume Parser MCP that converts unstructured resume text into a structured format, extracting skills, experience, education, and projects. It helps you quickly transform CV data into a clean, programmatic structure that downstream systems can consume or analyze.

How to use

To use this MCP, run it with an MCP client and send a JSON payload containing a raw_text field. The MCP will return a structured JSON object with keys like skills, experience, education, and projects. You can feed resumes in JSON form and immediately obtain a normalized representation that’s easier to search, filter, or display in your applications.

How to install

Prerequisites you need before starting:

Python and a virtual environment (for example, you will create and activate a venv).
The uv utility to run MCP servers.
Internet access to install dependencies.

Concrete steps you can follow to set up and run the MCP locally:

# 1) Clone the repository and navigate to the project
git clone https://github.com/Acidlambunk/Resume-Parser-MCP.git
cd test

# 2) Install uv and create a virtual environment
# (install uv first if needed, then create a venv and activate it)
python -m venv venv
source venv/bin/activate

# 3) Install dependencies
uv pip install -r requirements.txt

# 4) Set up environment variables
# Create a .env file and populate with your Gemini API details
# Example values (replace with real keys)
GEMINI_API_KEY=YOUR_GEMINI_API_KEY
GEMINI_MODEL=gemini-2.0-flash

# 5) Run the MCP server locally
uv run mcp dev main.py

Additional sections

Configuration notes: The MCP relies on environment variables to access Gemini models. Ensure your GEMINI_API_KEY and GEMINI_MODEL are kept secure and not committed to source control.

Security considerations: Run the MCP behind appropriate access controls and avoid exposing API keys. Use a dedicated environment file and restrict access to machines running the MCP.

Troubleshooting tips: If the server fails to start, verify that Python is installed, the virtual environment is activated, dependencies install correctly, and the GEMINI_API_KEY is valid. Check for network access to Gemini endpoints and confirm that the GEMINI_MODEL name matches the available model.

Available tools

parse_resume

Parse a resume JSON input and extract structured fields such as skills, experience, education, and projects from the raw text using Gemini.

validate_output

Validate the parsed JSON against expected schema to ensure required fields exist and data types are correct.