Web3 Jobs MCP Server
About
An MCP server that provides AI agents with real-time access to curated Web3 jobs.
Details
- Author
- kukapay
- Downloads
- 285
- Categories
- Other, AI
Jump to
- Query Web3 jobs with filters: remote status, country, tag, and limit.
- Returns formatted Markdown list with job ID, title, company, location, and more.
- Includes clickable apply URLs and truncated descriptions (100 characters).
- Provides a search prompt generator for role and location.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Web3 Jobs MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install dependencies with uv sync (recommended) or pip install mcp[cli] python-dotenv. Obtain a web3.career API token at web3.career/web3-jobs-api. Configure the server in Claude Desktop using the provided JSON snippet, setting the WEB3_CAREER_API_TOKEN environment variable. Start the server with uv run mcp dev main.py (for testing via MCP Inspector) or uv run main.py. Use the query_jobs tool to filter jobs by remote, country, tag, and limit, and the search_jobs_prompt for generating search queries.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"web3 jobs mcp server": {
"web3-jobs-mcp": {
"command": "uv",
"args": [
"sync"
]
}
}
}
}McpServers
{
"web3-jobs-mcp": {
"command": "uv",
"args": [
"sync"
]
}
}Web3 Jobs MCP Server
An MCP server that provides AI agents with real-time access to curated Web3 jobs from web3.career, enabling intelligent job discovery and career insights.
Features
- Job Query Tool: Filter Web3 jobs by:
- Remote status (remote=True for remote-only jobs)
- Country (e.g., "United States", case-insensitive)
- Job tag (e.g., "react", "blockchain", case-insensitive)
- Limit (1–100 jobs, default 50)
- Markdown Output: Returns job listings as a formatted Markdown list with:
- Job ID, Title, Company, Location, Remote status
- Published At (from date_epoch, formatted as YYYY-MM-DD)
- Apply URL (clickable link to web3.career)
- Description (plain text, truncated to 100 characters)
- Search Prompt: Generates user-friendly job search queries based on role and optional location.
Prerequisites
- Python 3.10+
- A web3.career API token (request at web3.career/web3-jobs-api)
- uv for dependency management (recommended)
Installation
1. Clone the Repository:
git clone https://github.com/kukapay/web3-jobs-mcp.git
cd web3-jobs-mcp
2. Install Dependencies:
Using uv:
uv sync
Alternatively, with
pip: pip install mcp[cli] python-dotenv
3. Installing to Claude Desktop:
Install the server as a Claude Desktop application:
uv run mcp install cli.py --name "Web3 Jobs"
Configuration file as a reference:
{
"mcpServers": {
"Web3 Jobs": {
"command": "uv",
"args": [ "--directory", "/path/to/web3-jobs-mcp", "run", "main.py" ],
"env": { "WEB3_CAREER_API_TOKEN", "your-api-token" },
}
}
}
/path/to/web3-jobs-mcp with your actual installation path, and your-api-token with your web3.career API token.
Usage
Running the Server
Start the server in development mode with the MCP Inspector:
uv run mcp dev main.py
This opens a web interface for testing tools and prompts.
Alternatively, run directly:
uv run main.py
Using the query_jobs Tool
In the MCP Inspector or a compatible client (e.g., Claude Desktop), call the query_jobs tool:
- Example 1: Get 5 remote blockchain jobs:
query_jobs(remote=True, tag="blockchain", limit=5)
- Example 2: Get 10 jobs in the United States:
query_jobs(country="United States", limit=10)
Sample Output:
```markdown
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
