"IRIS" matching MCP servers:

Enables AI agents to trace Python code execution in real time via PEP 669, exposing call trees, variable deltas, and async context through MCP tools.

Enables Claude Code instances across different project directories to communicate and coordinate. Stay in one project while asking questions to teams in other codebases through cross-project messaging and coordination.

MCP server that enables AI assistants to interact with InterSystems IRIS databases through tools for SQL, globals, class methods, Atelier API, and interoperability, plus guided prompts for common workflows.

A Model Context Protocol server that automatically generates structured release notes from Git repository tags, analyzing differences between tags and saving formatted Markdown output to the .iris directory.

MCP server for InterSystems IRIS that provides 8 tools including ObjectScript execution, class compilation, and unit testing with a fast DirectTestRunner.

Provides access to InterSystems IRIS ObjectScript documentation, examples, and intelligent search tools. Enables developers to query documentation, search class references, and access official IRIS resources through natural language.

Enables AI assistants to interact with InterSystems IRIS databases through SQL queries, document management, ObjectScript execution, debugging, and unit testing via the Atelier REST API.

Resolves scholarly identifiers — DOI, PubMed ID, PMCID, ISBN, ISSN, arXiv, ADS bibcode — into clean, formatted citations in any of 10,000+ CSL styles. Returns plain text, HTML, Markdown, RIS, BibTeX, CSL-JSON, or EndNote XML for direct paste or reference manager import.

MCP server for self-hosted Supabase with RLS-aware PostgreSQL and PostgREST layers, enabling safe database introspection, SQL queries, and PostgREST access via natural language.

A streamlined foundation for building Model Context Protocol servers in Python, designed to make AI-assisted development of MCP tools easier and more efficient.

A minimal, well-structured MCP server implementation for learning and experimentation that exposes three tools: web search, API search, and client ID processing. It demonstrates clean separation between tool, transport, and LLM layers while supporting multiple AI clients through the Model Context Protocol standard.