MCP Projects
Model Context Protocol servers that connect AI assistants to real tools and data.
Building MCP servers and clients that give assistants safe, structured access to databases, SaaS APIs and internal systems — and exploring how tool design shapes agent behaviour.
- Experiments
- 4
- Open Source
- 4
- Technologies
- 10
- More to Explore
- ∞
Featured MCP Projects
A few highlighted experiments and prototypes.
- AI AgentsFeatured
AegiSense AI Assistant
An AI-powered assistant for identity and security operations. Uses RAG, tool calling, and guardrails to answer security questions and automate workflows.
- LangGraph
- FastAPI
- PostgreSQL
- Docker
- MCPFeatured
MCP Integrations
Exploring Model Context Protocol (MCP) with real-world tools like Google Drive, Notion, GitHub, and custom APIs.
- MCP
- Python
- Notion API
- GitHub API
- AI Agents
Personal Assistant Agent
A general-purpose assistant for daily tasks, research, and learning.
- LangGraph
- MCP
- Tool Use
How My MCP Integrations Work
A typical architecture used in these experiments.
- Assistant(Claude, IDEs)
- MCP Client(Discovers tools)
- MCP Server(Typed tools)
- Auth(Scoped access)
- System(DB, API, files)
- Result(Structured data)
All MCP Projects
Explore all my MCP experiments, from simple prototypes to advanced systems.
4 experiments
An AI-powered assistant for identity and security operations. Uses RAG, tool calling, and guardrails to answer security questions and automate workflows.
- LangGraph
- FastAPI
- PostgreSQL
Exploring Model Context Protocol (MCP) with real-world tools like Google Drive, Notion, GitHub, and custom APIs.
- MCP
- Python
- Notion API
A read-only MCP server that lets assistants explore schemas and run safe SQL queries.
- MCP
- TypeScript
- PostgreSQL
A general-purpose assistant for daily tasks, research, and learning.
- LangGraph
- MCP
- Tool Use
Experiment · Learn · Build · Share
Let’s Build the Next Generation of MCP Projects
Check out the code, try the demos, or get in touch to collaborate on exciting ideas.