Skip to main content
Glama
DrawOffer MCP Server

DrawOffer MCP Server

by ql-link

DrawOffer MCP Server

让 Claude、Cursor 等 AI 工具读取你在 DrawOffer 职绘里的简历、岗位和投递记录


DrawOffer 职绘 是一个 AI 求职工具:AI 改简历、按岗位 JD 调整简历、AI 模拟面试和求职进度管理。这个 MCP Server 让你在自己常用的 AI 工具里直接用上 DrawOffer 里的数据,例如:

  • "读一下我的后端简历,按这个岗位的 JD 帮我改项目经历"

  • "我保存的岗位里,哪些和我的简历最匹配?"

  • "把这个招聘页面的岗位存进 DrawOffer"

  • "我还有哪些投递在等结果?"

它在你的电脑上运行,用你自己的 API Key 调用 DrawOffer 的开放接口,只能访问你自己的数据。

快速开始

1. 创建 API Key

登录 DrawOffer,打开 账号 → API Key,点「创建 Key」:

  • 只读(推荐):只能读取简历、岗位和投递记录。

  • 读写:还能新增岗位和投递记录。

完整的 Key 只在创建时显示一次,请立刻复制保存。Key 以 dok_ 开头。

2. 配置 AI 工具

需要 Node.js 18 或更高版本。

Claude Code

claude mcp add drawoffer --env DRAWOFFER_API_KEY=dok_你的Key -- npx -y drawoffer-mcp

Claude Desktop、Cursor 等:在 MCP 配置文件(Claude Desktop 为 claude_desktop_config.json,Cursor 为 ~/.cursor/mcp.json)中加入:

{
  "mcpServers": {
    "drawoffer": {
      "command": "npx",
      "args": ["-y", "drawoffer-mcp"],
      "env": { "DRAWOFFER_API_KEY": "dok_你的Key" }
    }
  }
}

重启 AI 工具后,问它"列出我在 DrawOffer 的简历"试试。

Related MCP server: Job Application MCP

工具一览

工具

作用

权限

list_resumes

列出全部简历

只读

get_resume

读取一份简历的正文(Markdown)

只读

list_jobs

列出保存的岗位,支持关键词搜索

只读

get_job

读取岗位的完整 JD

只读

create_job

保存一个岗位,并自动生成「待投递」记录

读写

list_applications

列出投递记录和当前阶段

只读

get_application

读取一条投递记录

只读

create_application

为已保存的岗位新建投递记录

读写

AI 改简历、匹配分析、模拟面试等会消耗积分的功能,目前不通过 MCP 开放,请在 DrawOffer 里使用。

配置项

环境变量

说明

DRAWOFFER_API_KEY

必填,你的 API Key

DRAWOFFER_BASE_URL

选填,默认 https://www.drawoffer.com

安全

  • Key 只放在请求头里发给 DrawOffer,不会写入日志,也不会出现在错误信息里。

  • 不要把 Key 提交进代码仓库。不用的 Key 请在账号页删除,删除后立即失效。

  • 账号页能看到每把 Key 的最近使用时间,发现异常可以随时删除。

  • 每把 Key 每分钟最多调用 60 次。

开发

git clone https://github.com/ql-link/drawoffer-mcp.git
cd drawoffer-mcp
npm install
npm test
DRAWOFFER_API_KEY=dok_你的Key node src/index.js

接口说明:所有请求发往 /api/open/v1/*,带 Authorization: Bearer dok_...。版本内只增加字段,不兼容的变化会放进 /api/open/v2。

更多 DrawOffer 开源项目

许可证

MIT © ql-link

Available Tools

8 tools
create_application新建投递记录A

为已保存的岗位新建投递记录。不填 applied_at 时记为「待投递」,填了则记为已投递、进入「筛选中」。岗位已有「待投递」记录时直接沿用并更新它;已经投递过的岗位会返回冲突。需要读写权限的 Key。

Inputs: job_description_id (required), notes, resume_id, applied_at.

create_job新增岗位A

把一个岗位 JD 保存到 DrawOffer,并自动生成一条「待投递」记录。同一岗位已存在时返回已有记录。需要读写权限的 Key。

Inputs: job_title (required), company_name (required), notes, skills, +4 more.

get_application读取投递记录B
Read-only

读取一条投递记录的当前阶段、状态、关联岗位与简历。

Inputs: application_id (required).

get_job读取岗位A
Read-only

读取一个岗位的完整 JD:职责描述、技能要求、城市、薪资、学历与经验要求和备注。

Inputs: job_id (required).

get_resume读取简历A
Read-only

读取一份简历的正文(Markdown)。适合用来按岗位改简历、准备面试或写求职信。

Inputs: resume_id (required).

list_applications列出投递记录B
Read-only

列出求职进度:每条记录对应一个岗位,包含当前阶段、状态、投递时间和备注。

Inputs: limit, scope, cursor, keyword.

list_jobs列出岗位A
Read-only

列出账号里保存的岗位 JD,支持关键词搜索和分页。

Inputs: limit, cursor, keyword.

list_resumes列出简历A
Read-only

列出当前 DrawOffer 账号里的全部简历(ID、标题、是否默认简历、更新时间),按最近更新排序。

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 8 tools

    Disambiguation4/5

    The set splits cleanly into three resources (resumes, jobs, applications) each with obvious read tools, so an agent can pick list_/get_ variants confidently. The one soft spot is create_job vs create_application: create_job silently also creates a '待投递' application record, which overlaps with create_application and could make an agent choose the wrong entry point for logging a new opportunity.

    Naming Consistency5/5

    Every tool follows the same verb_noun snake_case pattern (list_resumes, get_resume, create_job, create_application). Resource nouns are reused consistently across the set (resume/job/application), so names map predictably to the domain model.

    Tool Count5/5

    Eight tools is well within the sweet spot and each one maps to a concrete job-seeking step (browse resumes, read JD, save JD, log/track application). No tool looks like filler or a near-duplicate.

    Completeness3/5

    Read coverage is solid for all three resources, but the write surface is thin: there is no way to update or delete a job, no way to advance or change an application's stage (the core action in a job tracker, despite get_application exposing 'current stage'), and resumes are read-only with no edit/upload path. Agents can read and create but will hit dead ends for the main lifecycle mutation.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Enables parsing a master resume, analyzing job descriptions for ATS/match scores, generating truthful tailored resumes, tracking applications, and producing PDF reports through Claude Desktop.
      17
      MIT
    • F
      license
      Not graded
      quality
      B
      maintenance
      Enables Claude Web users to manage their job application workflow by storing profile and resume data, analyzing job descriptions, preparing applications, and tracking progress — all with manual submission and no platform automation.
      1
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Connects an AI assistant to a job-matching account so it can read roles matched to your resume, pull full job details and hiring contacts, and save tailored resume versions. With explicit opt-in and per-job confirmation in the chat, it can also start applications, relay questions only you can answer, and report each application's status.
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI clients to browse public job listings, save and rank roles into a pipeline, tailor resumes and cover letters, submit applications, and track replies, interviews, and escalations over time. Works anonymously for job browsing or with a scoped API key for full account, apply, and recruiter-outreach capabilities.
      74
      15
      MIT