Search for jobs across LinkedIn, Indeed, Glassdoor, ZipRecruiter, Google Jobs, Bayt, Naukri, and BDJobs using the JobSpy MCP server.
Security Analysis
medium confidenceThe skill's requirements and instructions are consistent with a job-search aggregator that expects you to run a local JobSpy MCP server; nothing in the SKILL.md contradicts that purpose, but the install-and-config guidance asks you to install third‑party code and edit a local app config so review before proceeding.
The name/description claim to search multiple job boards via a JobSpy MCP server and the SKILL.md consistently instructs the agent/user to install and run such a server and wire it into an MCP-enabled client. No unrelated services, credentials, or hidden capabilities are requested.
Runtime instructions are focused on installing/running the JobSpy MCP server and calling its MCP tools. The SKILL.md asks you to modify the Claude Desktop config file (~Library/Application Support/Claude/claude_desktop_config.json) to register an MCP server—this is relevant to integration but is a sensitive local config change and should be done intentionally. The instructions do not direct the agent to read arbitrary system files or export unrelated data.
The skill is instruction-only (no automatic install), but the documentation tells users to pip install packages and to git clone a GitHub repo (https://github.com/chinpeerapat/jobspy-mcp-server.git). Using GitHub releases/repos is normal, but installing unreviewed pip packages or running code from a cloned repo carries the usual risk: arbitrary code execution on the host. The SKILL.md also references an unfamiliar 'uv' tool for package/server management; verify what 'uv' does before using it.
The skill declares no required environment variables or credentials, which aligns with instructions that suggest running a local MCP server. Note: scraping some sites (e.g., LinkedIn) can require authentication or proxying in practice; the skill does not request or document credentials for those platforms.
always:false and model invocation allowed (default). The skill does not request persistent, system-level privileges or attempt to modify other skills. The only persistence-related action it suggests is editing a client config to register the MCP server—this is expected for integration but should be done cautiously.
Guidance
This skill appears to do what it says (use a JobSpy MCP server to scrape multiple job boards), but you should not blindly run the install steps. Before installing or running anything: 1) Inspect the GitHub repository and any pip packages (mcp, python-jobspy, etc.) to confirm their code and maintainer reputation. 2) Use a virtual environment or isolated machine to install and run server code. 3) Back up any client config files before editing (the SKILL.md asks you to modify Claude Desktop config). 4) Be aware that scraping some sites can violate terms of service and may require authentication or proxies; the skill does not request credentials but could perform network scraping that triggers rate limits or IP blocking. 5) If you need to provide credentials to any job board, prefer service-specific API keys and review how those secrets will be stored/used. If you want higher assurance, ask the skill author for a signed release or vetted package sources before installation.
Latest Release
v1.0.0
Job Search MCP v1.0.0 - Initial public release. - Search for jobs across LinkedIn, Indeed, Glassdoor, ZipRecruiter, Google Jobs, Bayt, Naukri, and BDJobs through the JobSpy MCP server. - Supports comprehensive filtering by role, location, platform, salary, recency, job type, remote/on-site, and "easy apply" options. - Includes helper tools for listing supported sites, countries, and providing job search tips. - Provides detailed setup instructions for both Python and Node.js MCP servers, including Claude Desktop integration. - Returns rich job data including salary, posting date, company info, and platform-specific details.
Popular Skills
Published by @Amoghpurohit on ClawHub
