Skip to main content
Glama
deenesfrjakoruzh
XavierBeheydt

jobs-scrape-mcp

by XavierBeheydt
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

jobs-scrape-mcp

MCP（模型上下文协议）服务器，将 jobs-scrape 语料库暴露给 AI。

一旦接入，Claude 可以直接查询收集到的职位信息： “沃州要求哪些技能？”、“八月份医疗行业有多少兼职职位？”、“给我总结一下这个公告”。

安装

uv pip install git+https://github.com/XavierBeheydt/jobs-scrape-mcp.git
claude mcp add jobs-scrape -- uv run jobs-scrape-mcp

服务器读取与 CLI 相同的数据库：

变量

默认值

JOBS_SCRAPE_DB

data/jobs.db

JOBS_SCRAPE_DATA_DIR

data

Related MCP server: mcp-jobs

公开工具

工具

何时调用

search_jobs

任何关于职位、所需技能、观察到的薪资、公司活动的问题

get_job

在找到一个公告后，完整阅读该公告

list_facets

在筛选前了解语料库内容（州、公司、来源）

top_skills

趋势问题：按地区或来源，哪些技能最受需求

timeline

每天发布的职位数量

stats

概览——应首先调用以了解数据库包含什么

list_sources

数据来源，以及为什么某个预期来源可能缺失

资源：jobs://summary 和 jobs://sources。

响应量是真正的挑战

MCP 工具将其结果返回在模型上下文中。返回二十份完整公告——数万字符——会耗尽上下文，却毫无益处：我们不会为了回答“日内瓦需要哪些技能”而阅读二十份完整描述。

因此，该服务器应用一条简单规则：

  • 列表工具返回摘要（320 字符）和用于判断相关性的结构化字段；

  • get_job 返回一份公告的完整文本；

  • limit 上限为 50，无论请求什么值；

  • 每个响应区分 total（匹配数）和 returned（返回数），以便模型知道它只看到一部分。

这里没有搜索逻辑

BM25 排序、分面和聚合都存在于 jobs_scrape.search 中，位于项目核心。本模块仅负责暴露它们。搜索逻辑只定义在一处——Web 界面和 MCP 服务器都继承它，排序的改进对两者都有益。

工具描述：触发条件，而不仅仅是功能

模型根据描述选择工具。只描述工具做什么的描述会让模型猜测何时使用它。因此，每个工具都说明其触发条件——“只要问题涉及可用职位，就调用此工具”——并且测试确保没有描述过于简略。

开发

uv venv
uv pip install git+https://github.com/XavierBeheydt/jobs-scrape.git
uv pip install -e ".[dev]"
uv run pytest -q      # hors ligne, base temporaire

This server cannot be installed

F
license - not found
Not graded
quality - not tested
C
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • Rishi's Interactive Resume MCP

    RishiA
    F
    license
    Not graded
    quality
    D
    maintenance
    Enables natural language querying of a resume with AI/ML experience, business impact metrics, and technical skills. Supports searching by company, skill, or achievement with built-in analytics and evaluation capabilities.

  • mcp-jobs

    mergedao
    A
    license
    Not graded
    quality
    D
    maintenance
    A zero-configuration job aggregation server that enables searching for positions and retrieving details across multiple recruitment platforms using natural language. It provides standardized data for job requirements, salary comparisons, and market trends directly within AI clients.
    49
    122
    ISC

  • JobDataLake MCP Server

    echojobsio
    A
    license
    A
    quality
    B
    maintenance
    Enables searching over 1 million enriched job listings from 20,000+ companies directly from MCP-compatible AI tools. Provides tools for job search, company profiles, and AI-powered similar job recommendations with real-time data updates.
    4
    81
    2
    MIT
  • @career-now/mcp by Career-Now

    @career-now/mcpofficial

    Career-Now
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to search and explore a large database of tech job listings with filtering options.
    MIT

View all related MCP servers

Related MCP Connectors

  • Magnificent Jobs

    Semantic search over 3.5M+ live US job postings pulled straight from company ATSes. Read-only.

  • Trackly CLI

    AI job search for Claude, ChatGPT, Cursor. 170K+ jobs, 3,800+ companies. OAuth or stdio.

  • JobsPipe

    Live job postings from 30+ ATS feeds and job boards, one schema. Live results need a Bearer key.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/XavierBeheydt/jobs-scrape-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server