Vibe Coding Discovermcp-agent
View on GitHubBuild effective agents using Model Context Protocol and simple workflow patterns
Python framework/SDK for building agents on the Model Context Protocol. Fully implements MCP lifecycle (tools, resources, prompts, OAuth, sampling) and composes Anthropic's effective agent patterns, with optional Temporal-backed durable execution and cloud deployment.
Use Cases
Build agents that connect LLMs to MCP serversCompose map-reduce, orchestrator, router and evaluator-optimizer patternsRun durable, resumable agent workflows on TemporalExpose agents as MCP servers (agent-as-server)Create FastMCP-compatible MCP serversAdd human-in-the-loop signals to agent runsDeploy agents and MCP apps to the cloudInstrument agent traces with OpenTelemetry
Built With
- Language
- Python
- Frameworks
- FastMCP · Temporal · LangChain · OpenAI SDK · Anthropic SDK · Pydantic · FastAPI · CrewAI · OpenTelemetry · uv
Tags
mcp · ai-agents · llm · python · agent-framework · workflows · durable-execution · temporal · orchestrator · multi-agent · mcp-servers · oauth · observability · fastmcp · human-in-the-loop · sdk