Federal Compass MCP

io.github.skivuha由 GitHub 账号 skivuha 发布v0.1.10更新于 Nov 3, 2026

AI compass from private sector to federal career — USAJobs search, salary, KSA

已验证STDIO仅桌面位置与生活知识与记忆

概览

AI 生成的概览

本地 MCP 服务器,把助手接入 USAJobs API,用于搜索联邦职位、解释 GS 职级与安全审查,并将简历与职位进行比对。

可以做什么
  • 按关键词、地点、薪资、职级、机构或远程条件搜索联邦职位,并获取单个职位的完整详情。
  • 将 2 至 5 个职位并排比较。
  • 在本地保存和读取简历,并根据从中提取的技能查找匹配职位。
  • 将简历与特定职位比对,并提取该职位的 KSA 要求。
  • 解释 GS 职级、薪酬计划、安全审查和招聘路径等联邦概念,并按地区补贴计算 GS 薪资。
适用场景
适合从私营部门技术岗位转向美国联邦或政府职位的人,用通俗语言理解职位公告、判断自身资格并弄清职级与安全审查。不能替代官方公告或机构的资格认定。
运行要求
通过 npx 在本地运行,需要 Node.js v22 或更高版本,以及兼容 MCP 的客户端(如 Claude Desktop、VS Code、Cursor 或 Windsurf)。需要免费的 USAJobs API 密钥及申请该密钥所用的邮箱,通过 USAJOBS_API_KEY 和 USAJOBS_EMAIL 环境变量提供。需要能访问 USAJOBS 的网络。
安装前请注意
简历保存在用户主目录下的本地文件中,get_cv 和 check_qualification 工具会把简历文本返回给客户端,客户端可能将其转交给 AI 服务商;find_matching_jobs 会把从简历中提取的关键词发送给 USAJOBS。每位用户应自行注册并使用自己的 API 凭据。解释与资格匹配均为非官方分析,申请前请以官方公告核实要求与截止日期。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Federal Compass MCP,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

federal-compass-mcp

Your AI compass from private sector to federal career

[npm version] [CI] [License: MIT] [MCP] [OpenSSF Scorecard]

Federal job descriptions are 5 pages of legal language. GS grades, clearance levels, hiring paths — none of this is explained anywhere. federal-compass-mcp connects Claude to the official USAJobs API and turns it into an AI advisor that speaks plain English.

Built for tech professionals transitioning from private sector to federal/government careers.


What it does

  • Searches federal job openings with optional filters — keyword, location, salary, clearance level
  • Translates federal job descriptions into plain language — what they actually want, without the jargon
  • Supports CV analysis by providing your CV and job requirements to your AI assistant for comparison
  • Explains federal concepts — GS grades, pay plans, security clearances, hiring paths
  • Saves your CV locally so Claude can reference it automatically

Getting started

1. Get your free USAJobs API key

Register at developer.usajobs.gov — takes about 3 minutes. Verify your email and you'll receive an API token.

2. Add to your MCP client

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):

json
{  "mcpServers": {    "federal-compass": {      "command": "npx",      "args": ["-y", "federal-compass-mcp@latest"],      "env": {        "USAJOBS_API_KEY": "your_api_key",        "USAJOBS_EMAIL": "[email protected]"      }    }  }}

VS Code / Cursor / Windsurf — same config, different config file path. See your client's MCP documentation.

3. Try it

Find me senior software developer jobs in Raleigh, NC
What is a GS-13 and how much does it pay?
Save my CV [attach file]
Look at this job posting — am I qualified?

Tools

ToolDescription
search_jobsSearch federal job openings. All filters optional — keyword, location, salary, grade, agency, remote
get_job_detailsGet full details for a specific job posting
compare_jobsCompare 2-5 job postings side by side
save_cvSave your CV locally for automatic use in analysis
get_cvRead your saved CV
explain_federal_conceptExplain GS grades, clearances, hiring paths, pay plans
calculate_salaryCalculate GS salary with locality pay for any grade, step, and location
find_matching_jobsFind jobs matching your CV — extracts skills and searches USAJobs
check_qualificationCompare your CV against a specific job posting
extract_ksaExtract KSA requirements from a job posting, optionally match against your CV

CV storage and privacy

Your saved CV is stored locally on your machine:

~/.federal-compass/  cv.json  codelists/     <- cached USAJobs reference data

The get_cv and check_qualification tools return your CV text to your MCP client. Depending on your client and its configuration, that text may be sent to an AI provider for processing. Review your client's and provider's privacy settings before sharing personal information.

The find_matching_jobs tool sends keywords extracted from your CV to USAJOBS to search for relevant vacancies.


Data source and independent analysis

Federal job announcements and API reference data come from USAJOBS. Use of the API is subject to the USAJOBS API Terms of Service. Each user should register for and use their own API credentials.

This is an independent project. It is not operated, sponsored, approved, or endorsed by the U.S. Office of Personnel Management (OPM) or USAJOBS.

AI explanations, CV comparisons, and extracted requirement matches are unofficial analysis, not an agency determination of eligibility. Verify requirements, deadlines, and application instructions against the current official announcement on USAJOBS before applying.


Why federal jobs are confusing (and how this helps)

Coming from private sector, federal job postings feel like a different language:

  • GS-13 Step 1-10 — what grade am I? what does step mean?
  • TS/SCI with polygraph — do I need this? how long does it take?
  • Competitive vs Excepted Service — which one can I apply to?
  • HiringPath: fed-transition — what is this and why does it matter?

federal-compass-mcp answers all of these through natural conversation with Claude.


Requirements

  • Node.js v22+
  • Free USAJobs API key
  • Any MCP-compatible client (Claude Desktop, VS Code, Cursor, etc.)

Contributing

Issues and PRs welcome. See CONTRIBUTING.md.


License

MIT — see LICENSE


Built by @skivuha — a Senior Frontend Engineer navigating the private-to-federal transition firsthand.

来源:README.md,提交 b3343fc

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v0.1.10最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分