Skip to main content

MCP server for re:Invent 2025 session catalog with 1,843 sessions and 13 search tools

Project description

AWS re:Invent 2025 MCP Server (Python)

Python implementation of the MCP server for AWS re:Invent 2025 session catalog with 1,843 sessions.

Features

  • 13 MCP Tools for comprehensive session discovery
  • MessagePack data format for 30% faster loading and smaller size
  • Simple array-based architecture for minimal complexity
  • Pagination support for all search and filter operations

Quick Start

Install Dependencies

pip install -e .

Run Server

python3 src/reinvent_2025_mcp/main.py

Test with MCP Inspector

npx @modelcontextprotocol/inspector python3 src/reinvent_2025_mcp/main.py

Available Tools

  1. search_sessions - Fuzzy search across all session content
  2. search_services - Find AWS services by name/abbreviation
  3. get_session_details - Get complete session information
  4. list_categories - Browse available category values
  5. get_sessions_by_service - Find sessions for specific AWS service
  6. get_sessions_by_level - Filter sessions by difficulty level
  7. get_sessions_by_role - Find sessions for specific job functions
  8. get_sessions_by_industry - Find sessions for industry verticals
  9. get_sessions_by_segment - Find sessions for business segments
  10. get_sessions_by_feature - Find sessions by format/feature type
  11. get_sessions_by_topic - Find sessions by technical domain
  12. get_sessions_by_area_of_interest - Find sessions by interest areas
  13. search_speakers - Search speakers by name or get all speakers with their sessions

Architecture

  • Data Layer: MessagePack loading into memory array
  • Service Layer: Array filtering and search operations
  • MCP Layer: Tool registration and request handling
  • Utilities: Simple string matching and pagination

Performance

  • Startup: <1 second for 1,843 sessions
  • Memory: ~30MB total footprint
  • Search: <10ms response times for typical queries
  • Data Size: 2.3MB MessagePack vs 3.1MB JSON (25% smaller)

Dependencies

  • mcp>=1.15.0: MCP protocol implementation
  • msgpack>=1.1.0: Fast binary serialization

Testing

Core functionality verified:

  • ✅ Data loading (1,843 sessions from MessagePack)
  • ✅ Search operations (294 sessions found for "bedrock")
  • ✅ Session filtering and pagination
  • ✅ All 13 tools initialized correctly

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

re_invent_2025_mcp-1.0.2.tar.gz (569.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

re_invent_2025_mcp-1.0.2-py3-none-any.whl (568.8 kB view details)

Uploaded Python 3

File details

Details for the file re_invent_2025_mcp-1.0.2.tar.gz.

File metadata

  • Download URL: re_invent_2025_mcp-1.0.2.tar.gz
  • Upload date:
  • Size: 569.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.4

File hashes

Hashes for re_invent_2025_mcp-1.0.2.tar.gz
Algorithm Hash digest
SHA256 10277d105ce87c490e4a8176a79d185b9c6b63add2dd13f3984b37dfde71e140
MD5 877f94bf42cbc95f548aeba2c0f756b6
BLAKE2b-256 4662ddf4ae5eabfb1a1a0f6217ab553309d674b88d2f479f46d74743ccd4d2a3

See more details on using hashes here.

File details

Details for the file re_invent_2025_mcp-1.0.2-py3-none-any.whl.

File metadata

File hashes

Hashes for re_invent_2025_mcp-1.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 38e95df958484e72886e1c3eb33bdbb78748b7d054766ad4c9b7cf77b007856b
MD5 8efad44b2a609bcab4963622169440d6
BLAKE2b-256 223a3c20cd137b1cf62c5d9097acde0425628b7b2e67c95d6837f6abdf098ec7

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page