About nostr-agent-tools
nostr-agent-tools is a Python SDK and CLI for developers building decentralized agent applications on Nostr and Lightning. It includes discovery and messaging capabilities, along with examples for MCP and several agent frameworks.
Key features
- 01Python SDK and CLI
- 02Agent discovery and direct messaging
- 03Tool discovery and command messaging
- 04Examples for multiple agent frameworks
Use cases
- 01Build decentralized agents on Nostr
- 02Send messages between agents over Nostr
- 03Discover and use available tools
MCP support
The project includes Nostr MCP client and server examples, demonstrating MCP use through Nostr.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project README✨ Agentstr SDK
Build decentralised agents on the Nostr + Lightning stack with one super-friendly Python package.
📖 Documentation
Everything – installation guide, tutorials, SDK reference, CLI reference – lives at docs.agentstr.com.
⚡ Quick install
pip install "agentstr-sdk[all]" # or: uv add agentstr-sdk[all]
🚀 Examples
Run any of the ready-to-go demos in examples/:
| Example | Framework |
|---|---|
| agent_discovery.py | Agent discovery |
| chat_with_agents.py | Direct messaging |
| commands_client.py | Command client |
| commands_server.py | Command server |
| mcp_client.py | Nostr MCP Client |
| mcp_server.py | Nostr MCP Server |
| nostr_agno_agent.py | Agno |
| nostr_dspy_agent.py | DSPy |
| nostr_google_agent.py | Google ADK |
| nostr_langgraph_agent.py | LangGraph |
| nostr_openai_agent.py | OpenAI |
| nostr_pydantic_agent.py | PydanticAI |
| rag.py | RAG / Retrieval |
| tool_discovery.py | Tool discovery |
uv run examples/nostr_dspy_agent.py
🤝 Contributing
PRs are welcome! Open an issue first to discuss your idea.
⚖️ License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.