jobswithgpt
OfficialThis server provides job search capabilities through the JobsWithGPT API, enabling searches with keywords, job titles, and location data. You can filter by geographic location using location names, administrative codes (admin1_code, country_code), and remote work options. Distance-based filtering allows you to set a search radius in meters from a specified location. Results can be paginated to browse multiple pages of listings. The server returns structured JSON responses with comprehensive job data including company names, job titles, and application links. It integrates with AI assistants like Claude Desktop and OpenAI agents for conversational, automated job searching.
Integrates with Greenhouse job board data, allowing job searches with results that include Greenhouse job listings
Enables OpenAI models to directly use the hosted MCP server to search for jobs using the search_jobs tool
Click on "Deploy 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., "@jobswithgptfind remote software engineer jobs in New York"
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.
Corvi Careers MCP Marketplace
This repository publishes the Corvi Careers Codex plugin marketplace entry and plugin package.
Corvi Careers lets Codex and other MCP-capable clients search jobs through the public Corvi Careers MCP server.
Install in Codex
Add this repository as a Codex plugin marketplace/catalog source:
https://github.com/jobswithgpt/mcpThen install Corvi Careers from the Codex plugin marketplace UI.
Related MCP server: Agent47
Repository Layout
.agents/plugins/marketplace.json
plugins/corvi-careers/The marketplace file registers the Corvi Careers plugin and points Codex to:
./plugins/corvi-careersDirect MCP Endpoint
For MCP clients that support remote Streamable HTTP directly:
https://corvi.careers/mcpFor clients that expect a local stdio MCP server, use mcp-remote:
{
"mcpServers": {
"corvi-careers": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://corvi.careers/mcp"
]
}
}
}Plugin Documentation
See the plugin README:
plugins/corvi-careers/README.mdSupport
Website: https://corvi.careers
Support: support@corvi.careers
License: MIT
Available Tools
1 toolsearchCInspect
Proxy to JobsWithGPT search API.
Args:
keywords: list of keyword strings
locations: list of dicts with keys name, admin1_code, country_code, remote (bool)
titles: list of title strings
distance: integer distance in meters
page: integer page number
Returns:
Parsed JSON response from JobsWithGPT API
| Name | Required | Description | Default |
|---|---|---|---|
| distance | Yes | ||
| keywords | Yes | ||
| locations | Yes | ||
| page | Yes | ||
| titles | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
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 being a 'proxy' and returns 'Parsed JSON response', but doesn't describe error handling, rate limits, authentication requirements, or what the API does beyond searching. This leaves significant gaps in understanding how the tool behaves in practice.
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 appropriately sized and front-loaded, starting with the tool's purpose as a proxy. The parameter and return value explanations are clear and efficient, with no redundant information. However, it could be slightly more structured by separating usage notes from parameter details for better readability.
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 (5 parameters, no annotations, but with an output schema), the description is partially complete. It covers parameter semantics well but lacks behavioral details like error handling or authentication. The output schema existence means return values don't need explanation, but overall, it's adequate with clear gaps in operational context.
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?
The description adds meaningful context beyond the input schema, which has 0% description coverage. It explains that 'keywords' are 'list of keyword strings', 'locations' are 'list of dicts with keys name, admin1_code, country_code, remote (bool)', 'titles' are 'list of title strings', 'distance' is 'integer distance in meters', and 'page' is 'integer page number'. This clarifies the purpose and structure of each parameter, compensating well for the schema's lack of descriptions.
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 states it's a 'Proxy to JobsWithGPT search API', which indicates it performs search operations, but it's vague about what exactly is being searched (e.g., jobs, content, data). It doesn't specify the resource or domain clearly, though 'JobsWithGPT' implies job-related searches. Without siblings, differentiation isn't needed, but the purpose remains somewhat ambiguous.
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?
No guidance is provided on when to use this tool versus alternatives. The description lacks context about prerequisites, such as authentication or API limits, and doesn't mention any exclusions or specific scenarios for usage. It's a basic functional statement without operational context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v1.0.0- First observed
search
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single 'search' tool has a clearly defined and distinct purpose.
A single tool inherently has perfect naming consistency. The tool name 'search' follows a clear, simple verb pattern appropriate for its function.
One tool is too few for a job search server's apparent scope. A complete job search domain would typically require additional tools like filtering, job detail retrieval, application submission, or saved searches to be functional for agents.
The server is severely incomplete for job search functionality. While the search tool exists, there are significant gaps: no way to get detailed job information, apply to jobs, manage applications, or perform other essential job search operations, which will cause agent failures.
Maintenance
Related MCP Connectors
Public MCP server for discovering open jobs. Search, filter, and get application links.
GetJobzi MCP server for job search, application tracking, and career forecasting.
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that provides AI agents with real-time access to curated Web3 jobs.18MIT
- FlicenseNot gradedqualityFmaintenanceUnified job aggregator for AI agents. Searches 1,680+ opportunities across x402 Bazaar, RentAHuman, Virtuals Protocol, ClawTasks, Work402, Moltverr, AgentWork, m/jobs, and Clawlancer.4-
- AlicenseNot gradedqualityCmaintenanceJobPilot is a next-generation career assistant powered by AI Agents and the Model Context Protocol (MCP). It acts as your personal recruiter, tirelessly searching for jobs on platforms like LinkedIn, optimizing your resume for specific job descriptions (JD), and even automating the application process. Designed for the age of AI, JobPilot exposes a full MCP server, allowing you to connect it with2MIT
- AlicenseNot gradedqualityAmaintenanceEnables job search and scraping across multiple job boards (LinkedIn, Indeed, Glassdoor, etc.) with advanced filtering, directly from Claude Desktop or other MCP clients.6MIT