← Back to Skills Marketplace
Job Search MCP (JobSpy)
by
NikkiJasmine
· GitHub ↗
· v1.0.3
2480
Downloads
2
Stars
7
Active Installs
1
Versions
Install in OpenClaw
/install job-search-mcp-jobspy
Description
Search and compare job listings across multiple boards using JobSpy MCP, with filters for criteria, location, salary, remote options, and easy apply roles.
README (SKILL.md)
Job Search MCP Skill
This skill enables AI agents to search for job listings across multiple job boards using the JobSpy MCP server.
JobSpy aggregates listings from sources such as LinkedIn, Indeed, Glassdoor, ZipRecruiter, Google Jobs, and more into a unified interface.
When to Use This Skill
Use this skill when you want to:
- Find job listings matching specific criteria (role, location, company)
- Search for remote or on-site positions
- Compare opportunities across job boards
- Retrieve salary information when available
- Find recently posted jobs
- Filter for “Easy Apply” roles
Prerequisites
- Python 3.10+
- JobSpy MCP server installed and configured
Installation & Setup
macOS Setup (Homebrew Python)
Homebrew-managed Python is externally managed (PEP 668). Create and activate a virtual environment before installing dependencies:
python3 -m venv .venv
source .venv/bin/activate
pip install mcp python-jobspy pandas pydantic
Usage Guidance
This skill may do what it claims, but important information is missing and it asks you to install third‑party Python packages from unknown sources. Before installing or using it: 1) Ask the publisher for a homepage, source repository, and package authorship; 2) Request explicit instructions for connecting to the JobSpy MCP server (endpoint URL, required auth, where credentials are stored); 3) Prefer pinned package versions and review the packages' source code or PyPI pages; 4) Test installation in an isolated environment (container or disposable VM) rather than your primary machine; and 5) if you can't verify the packages or server origin, do not install — the pip packages could run arbitrary code.
Capability Analysis
Type: OpenClaw Skill
Name: job-search-mcp-jobspy
Version: 1.0.3
The skill bundle appears benign. The `SKILL.md` provides standard instructions for setting up a Python virtual environment and installing common, relevant dependencies (`mcp`, `python-jobspy`, `pandas`, `pydantic`) to interact with a stated 'JobSpy MCP server'. There is no evidence of data exfiltration, malicious execution, persistence, or prompt injection attempts against the agent with harmful intent. All instructions align with the stated purpose of a job search skill.
Capability Assessment
Purpose & Capability
The SKILL.md describes a job-search capability using a 'JobSpy MCP' server and Python packages (mcp, python-jobspy). That generally aligns with the name, but the package registry metadata has no description, no source/homepage, and the skill gives no concrete details about how to connect to the JobSpy server (URL, auth, API key). The lack of publisher/source makes it hard to verify the claimed capability.
Instruction Scope
Runtime instructions tell the agent (and user) to create a venv and pip install mcp, python-jobspy, pandas, pydantic. There are no further runtime instructions in the SKILL.md about how the agent should authenticate to the JobSpy MCP server or where credentials/config live. The instructions thus require installing and running third-party code but leave out critical configuration and security details.
Install Mechanism
There is no formal install spec, but the SKILL.md advises pip install of packages with no pinned versions or provenance. Installing unvetted PyPI packages can execute arbitrary code; because the skill's package names and publisher are unknown and no homepage/source is provided, this is a meaningful risk.
Credentials
The skill declares no required environment variables or credentials, yet it depends on a separate JobSpy MCP server being 'installed and configured'. The mismatch (no declared env or auth guidance) is concerning: the agent or user will likely need to provide a server URL, credentials, or API token that are not described, leaving ambiguity about where secrets would be stored or how they'd be used.
Persistence & Privilege
The skill does not request always:true and has no special OS restrictions or config paths. Autonomous invocation is enabled by default (disable-model-invocation: false) but that is the platform default and not a unique concern here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install job-search-mcp-jobspy - After installation, invoke the skill by name or use
/job-search-mcp-jobspy - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
Initial release of the Job Search MCP skill.
Provides aggregated job search across multiple job boards using JobSpy.Minor metadata update
Metadata
Frequently Asked Questions
What is Job Search MCP (JobSpy)?
Search and compare job listings across multiple boards using JobSpy MCP, with filters for criteria, location, salary, remote options, and easy apply roles. It is an AI Agent Skill for Claude Code / OpenClaw, with 2480 downloads so far.
How do I install Job Search MCP (JobSpy)?
Run "/install job-search-mcp-jobspy" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Job Search MCP (JobSpy) free?
Yes, Job Search MCP (JobSpy) is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Job Search MCP (JobSpy) support?
Job Search MCP (JobSpy) is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Job Search MCP (JobSpy)?
It is built and maintained by NikkiJasmine (@nikkijasmine); the current version is v1.0.3.
More Skills