Skip to main content
Glama
Pavan Madduri — Personal Knowledge MCP Server

Pavan Madduri — Personal Knowledge MCP Server

Pavan Madduri — Personal Knowledge MCP Server

MCP Python License

A Model Context Protocol (MCP) server that exposes my professional profile — certifications, industry articles, open source contributions, and live GitHub activity — as a queryable API for AI agents.

Why? Instead of a static resume, this is a Personal Knowledge API. Any AI agent (Claude, Gemini, Copilot) can query my career data in real-time. This is AI infrastructure, not just AI usage.


What's Inside

Resources (Static Data)

Resource URI

Description

profile://about

Bio, links, expertise areas

profile://certifications

CNCF Golden Kubestronaut (all 15 certs + LFCS)

profile://articles

9 industry articles (CNCF Blog, IEEE ComSoc, CloudNativeNow, PlatformEngineering.com, d7y.io)

profile://open-source-summary

26 PRs across 15 projects

profile://contributions/cncf

Detailed CNCF project PRs

profile://contributions/aswf

Detailed ASWF project PRs

Tools (Dynamic Functions)

Tool

Description

search_contributions(project)

Search contributions by project name

search_articles(keyword)

Search industry articles by keyword, category, or publication

get_expertise(domain)

Check expertise in a technical domain

get_eb1a_evidence(criterion)

Retrieve EB-1A extraordinary ability evidence

get_github_activity(repo, limit)

Live GitHub PR data via API

get_github_stats()

Live GitHub profile statistics

get_profile_summary()

One-page comprehensive summary


Related MCP server: GitHub MCP Server

Quick Start

Prerequisites

  • Python 3.11+

  • uv (recommended) or pip

Install & Run

# Clone
git clone https://github.com/pmady/pavan-profile-mcp.git
cd pavan-profile-mcp

# Option A: uv (recommended)
uv sync
uv run server.py

# Option B: pip
pip install -e .
python server.py

Environment Variables (Optional)

# For higher GitHub API rate limits (optional — works without it)
export GITHUB_TOKEN="ghp_your_token_here"

Connect to Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "pavan_profile": {
      "command": "uv",
      "args": ["--directory", "/path/to/pavan-profile-mcp", "run", "server.py"]
    }
  }
}

Restart Claude Desktop. You'll see the tools appear in the MCP panel.

Example Prompts

  • "What are Pavan's contributions to Dragonfly?"

  • "Show me his published articles on AI infrastructure"

  • "What EB-1A evidence does Pavan have for original contributions?"

  • "Get his latest GitHub activity"

  • "Does he have expertise in GPU scheduling?"


Connect to Other Clients

Cursor / Windsurf

Add to your MCP config:

{
  "pavan_profile": {
    "command": "uv",
    "args": ["--directory", "/path/to/pavan-profile-mcp", "run", "server.py"]
  }
}

Render (Public Hosting)

One-Click Deploy: Deploy to Render

This server deploys on Render with HTTP transport for remote access.

Live Production Server: https://pavan-profile-mcp.onrender.com/mcp

Connect any MCP client to the remote endpoint:

{
  "mcpServers": {
    "pavan_profile": {
      "url": "https://pavan-profile-mcp.onrender.com/mcp"
    }
  }
}

Manual deployment:

  1. Fork this repo

  2. Go to Render Dashboard

  3. Click "New" → "Blueprint"

  4. Connect your forked repo

  5. Render auto-detects render.yaml and deploys

  6. Your MCP endpoint will be at https://<your-service-name>.onrender.com/mcp


Architecture

AI Agent (Claude / Gemini / Copilot)
        │
        ▼
┌─────────────────────────────┐
│   MCP Protocol (stdio/SSE)   │
├─────────────────────────────┤
│   FastMCP Server            │
│                             │
│   Resources:                │
│   ├── profile://about       │
│   ├── profile://certs       │
│   ├── profile://articles    │
│   └── profile://oss-summary │
│                             │
│   Tools:                    │
│   ├── search_contributions  │
│   ├── search_articles       │
│   ├── get_expertise         │
│   ├── get_eb1a_evidence     │
│   ├── get_github_activity ──┼──► GitHub API (live)
│   ├── get_github_stats    ──┼──► GitHub API (live)
│   └── get_profile_summary   │
│                             │
│   Data: data/profile.json   │
└─────────────────────────────┘

Project Structure

pavan-profile-mcp/
├── server.py              # MCP server — all resources and tools
├── data/
│   └── profile.json       # Structured profile data (certs, articles, PRs)
├── Dockerfile             # Railway/Render deployment
├── pyproject.toml         # Python project config
├── SKILL.md               # Smithery skill definition
├── smithery.yaml          # Smithery.ai config
├── claude_desktop_config.example.json
├── README.md
└── LICENSE

About the Author

Pavan Madduri — Senior DevOps/Platform Engineer

  • CNCF Golden Kubestronaut (all 15 CNCF certifications + LFCS)

  • Published author on CNCF Blog, IEEE ComSoc, CloudNativeNow, PlatformEngineering.com

  • 26 PRs across 15 CNCF & ASWF projects (Dragonfly, Volcano, KEDA, Kubernetes, TiKV, OpenColorIO, and more)

  • Dragonfly Community Member (CNCF Incubating)

GitHub · LinkedIn · Blog


License

MIT

Available Tools

7 tools
get_eb1a_evidenceB

Retrieve evidence supporting a specific EB-1A extraordinary ability criterion.

Inputs: criterion (required). Returns: result

get_expertiseB

Check if Pavan has expertise in a specific technical domain.

Inputs: domain (required). Returns: result

get_github_activityA

Fetch Pavan's latest GitHub pull requests (live from GitHub API).

Inputs: repo, limit. Returns: result

get_github_statsA

Fetch Pavan's live GitHub profile statistics (repos, followers, contributions).

Inputs: no named parameters. Returns: result

get_profile_summaryA

Get a comprehensive one-page summary of Pavan Madduri's professional profile. Ideal for AI agents that need a quick overview.

Inputs: no named parameters. Returns: result

search_articlesB

Search Pavan's published industry articles by keyword, category, or publication.

Inputs: keyword (required). Returns: result

search_contributionsB

Search Pavan's open source contributions by project name.

Inputs: project (required). Returns: result

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 7 tools

    Disambiguation5/5

    Each tool targets a distinct aspect: EB-1A evidence, expertise check, GitHub activity vs. stats, profile summary, article search, and contribution search. No functional overlap.

    Naming Consistency5/5

    All tools follow a consistent 'verb_noun' pattern in snake_case: get_* for retrieval and search_* for searching. No mixing of conventions.

    Tool Count5/5

    Seven tools cover the personal knowledge domain without being excessive. Each tool serves a clear purpose, and the count feels well-scoped.

    Completeness4/5

    Covers key areas (evidence, expertise, GitHub, articles, contributions) but lacks direct access to a 'projects' or 'skills' list. The profile summary partly compensates, but minor gaps exist.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      An MCP server that provides a structured API for AI agents to query a person's resume, including profile, projects, writing, and gated access to experience and skills.
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol (MCP) server that connects Claude AI directly to the GitHub API, enabling natural language queries for live repository data, issues, PRs, and contributions.
      1
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Aggregates your digital footprint (GitHub, blogs, resume) into a single AI-readable profile and exposes it via MCP tools so AI agents can query your context live.
      1
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Exposes a personalized AI agent that reads your resume and provides intelligent responses about your professional background through a standardized MCP server interface with RAG capabilities.
      MIT