Nano Agent
Nano Agent MCP server by IndyDevDan that bridges the Model Context Protocol with OpenAI's Agent SDK to enable autonomous agent execution through natural language prompts. The implementation provides a single powerful tool that accepts task descriptions in plain English and executes them using an AI agent with file system access, supporting multiple LLM providers including OpenAI (GPT-5 models), Anthropic (Claude models), and local Ollama models. Features comprehensive file operations (read, write, edit, list directories), multi-provider configuration with automatic API key detection, token tracking and cost calculation, and includes Claude Code integration with hooks for session management, TTS notifications, and transcript logging, making it valuable for developers who want to delegate complex multi-step coding tasks, file manipulation, and project automation to AI agents through conversational interfaces.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/disler/nano-agent
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Nano Agent from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.