Searches for AI/ML jobs and internships with filtering for entry-level positions and Python proficiency requirements
Searches for AI/ML jobs and internships with filtering for entry-level positions and Python proficiency requirements
Searches for AI/ML jobs and internships with filtering for entry-level positions and Python proficiency requirements
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Job Search MCP Server find AI/ML internships in New York with Python skills"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server that searches across multiple job sites for AI/ML internships and full-time roles with specific filtering criteria.
Multi-site Job Search: Searches LinkedIn, Indeed, Glassdoor, ZipRecruiter, and Monster
AI/ML Focus: Specifically targets artificial intelligence and machine learning positions
Smart Filtering:
Filters for entry-level positions (less than 1 year experience)
Requires Python proficiency
Supports both internships and full-time roles
Real-time Results: Gets the latest job postings from all sites
Structured Data: Returns well-formatted job information with all relevant details
Related MCP server: JobSpy MCP Server
Clone or download this repository
Install dependencies:
npm installBuild the project:
npm run buildnpm startOr for development:
npm run devsearch_ai_ml_jobsSearch for AI/ML jobs across all supported job sites.
Parameters:
location (string, optional): Job location (default: "Remote")
maxResults (number, optional): Maximum results to return (default: 50)
includeInternships (boolean, optional): Include internships (default: true)
includeFullTime (boolean, optional): Include full-time roles (default: true)
keywords (array, optional): Additional search keywords
Example:
{
"location": "San Francisco, CA",
"maxResults": 25,
"includeInternships": true,
"includeFullTime": true,
"keywords": ["deep learning", "NLP", "computer vision"]
}search_specific_job_siteSearch for jobs on a specific job site.
Parameters:
site (string, required): Job site ("linkedin", "indeed", "glassdoor", "ziprecruiter", "monster")
location (string, optional): Job location (default: "Remote")
maxResults (number, optional): Maximum results to return (default: 25)
Example:
{
"site": "linkedin",
"location": "Remote",
"maxResults": 20
}The server automatically applies the following filters:
Experience Level: Entry-level (less than 1 year experience)
Required Skills: Must include Python proficiency
Job Type: AI/ML related positions only
Job Type: AI/ML related positions only
Skills: Python proficiency preferred
Machine Learning
Artificial Intelligence
Data Science
Deep Learning
NLP (Natural Language Processing)
Computer Vision
Neural Networks
TensorFlow, PyTorch, Scikit-learn
The server returns structured job data including:
{
"results": [
{
"site": "LinkedIn",
"jobs": [
{
"id": "unique_job_id",
"title": "Machine Learning Engineer",
"company": "Tech Company",
"location": "San Francisco, CA",
"type": "full-time",
"experienceLevel": "entry",
"description": "Job description...",
"requirements": ["Python", "Machine Learning"],
"skills": ["python", "tensorflow", "pytorch"],
"postedDate": "2024-01-15T10:30:00Z",
"applicationUrl": "https://...",
"source": "LinkedIn",
"isRemote": false,
"hasPythonRequirement": true,
"isAIMLRelated": true
}
],
"totalFound": 1,
"searchTime": 1500
}
],
"totalJobs": 1,
"searchTimestamp": "2024-01-15T10:30:00Z",
"filters": {
"location": "San Francisco, CA",
"maxResults": 50,
"includeInternships": true,
"includeFullTime": true,
"keywords": [],
"experienceLevel": "entry",
"requiredSkills": ["python"],
"jobTypes": ["ai", "ml", "machine learning", "artificial intelligence", "data science"]
}
}Copy env.example to .env and modify as needed:
cp env.example .envAvailable configuration options:
RATE_LIMIT_PER_MINUTE: Rate limiting for requests (default: 30)
REQUEST_TIMEOUT: Request timeout in milliseconds (default: 30000)
USER_AGENT: User agent string for web scraping
LinkedIn - Professional networking and job board
Indeed - General job search engine
Glassdoor - Job search with company reviews
ZipRecruiter - Job matching platform
Monster - Traditional job board
Language: TypeScript
Runtime: Node.js
Web Scraping: Cheerio for HTML parsing, Axios for HTTP requests
Architecture: Modular scraper system with base class and site-specific implementations
The server includes comprehensive error handling:
Network timeouts and connection errors
HTML parsing errors
Rate limiting protection
Graceful degradation when individual sites fail
This tool is for educational and personal use. Please respect:
Website terms of service
Rate limiting to avoid overloading servers
Robots.txt files and scraping policies
Consider using official APIs when available
Fork the repository
Create a feature branch
Add tests for new functionality
Submit a pull request
Search for AI/ML internships and full-time roles across multiple job sites
| Name | Required | Description | Default |
|---|---|---|---|
| location | No | Job location (e.g., "Remote", "San Francisco, CA", "New York, NY") | Remote |
| maxResults | No | Maximum number of results to return | |
| includeInternships | No | Include internship positions | |
| includeFullTime | No | Include full-time positions | |
| keywords | No | Additional keywords to search for (e.g., ["machine learning", "deep learning", "NLP"]) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions searching 'across multiple job sites', which hints at aggregation behavior, but fails to detail critical aspects like rate limits, authentication needs, result format, pagination, or error handling for a search tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core purpose without unnecessary elaboration. Every word contributes directly to understanding the tool's function, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a search tool with 5 parameters, no annotations, and no output schema, the description is insufficient. It lacks details on behavioral traits, result format, and usage guidelines, leaving significant gaps for an AI agent to operate effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, providing full parameter documentation. The description adds no additional semantic context beyond the schema, such as explaining interactions between parameters (e.g., how 'keywords' refine searches). Baseline 3 is appropriate as the schema handles the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'search' and the resource 'AI/ML internships and full-time roles across multiple job sites', making the purpose evident. However, it doesn't explicitly differentiate from the sibling tool 'search_specific_job_site', which might handle single-site searches versus this multi-site approach.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, such as the sibling 'search_specific_job_site'. It lacks context on prerequisites, exclusions, or comparative scenarios, leaving the agent without clear usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for jobs on a specific job site
| Name | Required | Description | Default |
|---|---|---|---|
| site | Yes | Job site to search | |
| location | No | Job location | Remote |
| maxResults | No | Maximum number of results to return |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the action is a search but doesn't disclose behavioral traits like whether it's read-only, what permissions are needed, rate limits, or what the output looks like (e.g., list of jobs with details). This leaves significant gaps for a tool with parameters.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero waste. It's appropriately sized and front-loaded, clearly stating the core purpose without unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and a tool with 3 parameters, the description is incomplete. It doesn't explain what the search returns (e.g., job listings, error handling) or behavioral aspects, making it inadequate for proper agent usage despite good conciseness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters (site, location, maxResults) with descriptions and defaults. The description adds no additional meaning beyond implying a search context, which is minimal value. Baseline 3 is appropriate when schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Search for jobs') and resource ('on a specific job site'), making the purpose understandable. However, it doesn't differentiate from the sibling tool 'search_ai_ml_jobs' (which presumably searches for AI/ML jobs rather than by site), so it lacks explicit sibling distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'search_ai_ml_jobs'. It mentions 'specific job site' but doesn't explain when to choose this over other search methods or what contexts it's best suited for.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
search_ai_ml_jobssearch_specific_job_siteThe two tools have overlapping purposes, as both are for searching jobs, with one being a general AI/ML search and the other for specific sites. This creates ambiguity—an agent might struggle to choose between them when searching on a particular site, as the descriptions don't clearly delineate when to use each tool.
Both tools follow a consistent snake_case naming pattern with 'search' as the verb, which is predictable and readable. However, the slight inconsistency in naming (e.g., 'search_ai_ml_jobs' vs. 'search_specific_job_site') is minor, as they maintain a clear verb_noun structure.
With only 2 tools, the server feels thin for a job search domain, lacking essential operations like filtering, applying, or managing job listings. This limited scope suggests the tool set is underdeveloped and may not support comprehensive agent workflows.
The tool set is severely incomplete for job searching, missing critical functions such as filtering by location or salary, applying to jobs, saving listings, or tracking applications. This will likely cause agent failures in handling typical job search tasks beyond basic searches.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search AI-native jobs, inspect application forms, and fetch free interview-prep resources.
Job platform for AI agents. Track tech jobs from companies that match your stack.
AI job search MCP — fact-checked jobs, application tracker, alerts. ChatGPT, Claude, Cursor.
Search job postings, companies, and technology stacks across 10M+ companies.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Ritesh-sudo/MCPJobSearch'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
