Skip to main content
Glama
resume-mcp

resume-mcp

by YongBoYu1

resume-mcp

Problem

Agents invent bios and career claims without citations. When you ask an MCP client who someone is or what they shipped, you often get fluent prose and no way to verify it.

Related MCP server: Resume MCP Server

Solution

A stdio MCP server that:

  1. Fetches public machine-readable pages (resume.json, optionally llms.txt)

  2. Caches them in-process (1-hour TTL)

  3. Exposes tools that return structured answers with a top-level sources[] of public URLs on every response

No secrets, no LinkedIn scraping, no private app links — only HTTPS to the wired public corpus.

The default dataset is YongBo Yu’s public site (resume.json / llms.txt). The pattern is general: point the same fetch/cache/source-URL shape at any public machine-readable resume corpus.

Requirements

  • Python 3.11+

  • Network access to the wired public host (default: yongbo-yu.vercel.app)

Install

# from this repo
pip install -e .

# or with uv
uv pip install -e .

Dev / smoke tests:

pip install -e ".[dev]"
pytest -q

Run (stdio)

# module entrypoint
python -m resume_mcp

# console script (after install)
resume-mcp

# with uv
uv run python -m resume_mcp

The process speaks MCP over stdin/stdout. Do not pipe unrelated stdout into the same process.

Cursor mcp.json

Add a server entry (Cursor: Settings → MCP, or edit ~/.cursor/mcp.json / project .cursor/mcp.json):

{
  "mcpServers": {
    "resume-mcp": {
      "command": "python3",
      "args": ["-m", "resume_mcp"],
      "cwd": "/absolute/path/to/resume-mcp"
    }
  }
}

If the package is installed into a venv, point command at that interpreter (or use the resume-mcp console script).

With uv:

{
  "mcpServers": {
    "resume-mcp": {
      "command": "uv",
      "args": ["run", "python", "-m", "resume_mcp"],
      "cwd": "/absolute/path/to/resume-mcp"
    }
  }
}

After saving, reload MCP servers in Cursor. The tools below should appear as resume-mcp tools.

Tools

Tool

Purpose

who_is_yongbo_yu

Identity blurb + canonical public links from the wired corpus

list_projects

Projects from resume.json with highlights; KiloDock links to the project page

get_resume_summary

Condensed work / education / skills

search_evidence

Keyword search over cached resume + llms.txt (snippets + source URLs)

Every tool response is JSON text that includes a top-level sources array of public URLs.

Example prompts (in Cursor / Claude)

  • “Summarize the public resume this MCP is wired to, with sources.”

  • “List projects from the cached resume.json and cite the source URLs.”

  • “Search the wired public corpus for ‘LangGraph’ and quote snippets with URLs.”

  • “Use who_is_yongbo_yu for the identity blurb + links from this corpus (not invented bio text).”

Data sources (public only)

On startup (and on first tool use if needed), the server fetches:

  1. https://yongbo-yu.vercel.app/resume.json

  2. https://yongbo-yu.vercel.app/llms.txt (optional; search still works if it fails)

No API keys. No private WOD-APP or similar links.

Author

YongBo Yu (also Yong Yu) — Toronto, Canada · GitHub YongBoYu1

License

MIT — see LICENSE.

Available Tools

4 tools
get_resume_summaryA

Condensed work experience, education, and skills from public resume.json.

Inputs: no named parameters. Returns: result

list_projectsA

List projects from public resume.json with highlights; KiloDock links to its project page.

Inputs: no named parameters. Returns: result

search_evidenceA

Keyword search over cached resume.json and llms.txt; returns snippets with source URLs.

Inputs: query (required), limit. Returns: result

who_is_yongbo_yuA

Identity blurb and canonical public links for YongBo Yu (also Yong Yu).

Inputs: no named parameters. Returns: result

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 4 tools

    Disambiguation4/5

    The tools are mostly distinct: one covers identity and links, one covers projects, one covers a career summary, and one is a search tool. The only slight overlap is between who_is_yongbo_yu and get_resume_summary since both describe the person, but their focus areas are clear enough to guide tool selection.

    Naming Consistency4/5

    Three tools follow a clean verb_noun snake_case pattern: list_projects, get_resume_summary, and search_evidence. who_is_yongbo_yu is the exception because it uses a question-style name instead of a verb_noun form, but the overall naming style remains readable and predictable.

    Tool Count5/5

    Four tools is well-scoped for a personal resume server. Each tool earns its place: identity, projects, resume summary, and evidence search cover the main consumption modes without redundancy or bloat.

    Completeness5/5

    The server covers the core needs of the resume domain: who the person is, what projects they have, a condensed career summary, and searchable evidence. Agents can answer typical questions about YongBo Yu without hitting obvious dead ends.

    Maintenance

    ActivityStale
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Exposes a public, read-only professional profile with tools to search resume evidence, fetch curated links, and generate career briefs for LLM agents.
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Exposes a structured professional resume as a set of AI-queryable tools, enabling AI clients like Claude Desktop to query summary, experience, skills, projects, and tailor resumes to job descriptions.
      1
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to query a person's CV and portfolio content via MCP tools and resources, returning grounded answers from local markdown data instead of relying on resume parsing.
      -
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to fetch web pages, extract clean Markdown, save and search versions offline, crawl sites within bounds, and retrieve stable citations through MCP tools.
      12 npm
      Apache 2.0