By diegouis
Scaffold and extend production Python projects for composite MCP servers, Strands agents with memory, hybrid pgvector search services, and OTEL/Phoenix tracing using proven Provectus patterns.
npx claudepluginhub diegouis/provectus-marketplace --plugin proagent-agentic-stackAdd a new tool server to an existing composite MCP server project.
Add a new LTM namespace to an existing Strands agent project.
Add a new database migration to an existing hybrid search project.
Add a new infrastructure component to an existing project's Pulumi stack.
Add OpenTelemetry tracing with Phoenix to an existing project.
Audit an existing project against Provectus agentic stack patterns and conventions.
Generate a complete pgvector hybrid search MCP server with vector + full-text scoring, migrations, and embeddings.
Generate a complete FastMCP composite server project with tool mounting, dependency injection, and ECS Fargate deployment.
Generate a complete Strands agent project with LTM/STM memory, AgentCore handler, and Bedrock deployment.
Overview of agentic stack capabilities: composite MCP servers, Strands agents with memory, hybrid pgvector search, and OTEL/Phoenix tracing.
Review and audit an existing agentic stack project against Provectus patterns and conventions.
Execute agentic stack operations: scaffold new projects, add components to existing projects, or configure tracing.
FastMCP composite server expert — scaffold projects with mount pattern, tool registration via @server.tool(), Depends() DI, lifespan context, Pydantic settings, multi-stage Docker builds, and Pulumi ECS Fargate stacks.
Hybrid pgvector search expert — scaffold services with weighted vector + full-text scoring, SQL migrations with CONCURRENTLY indexes, GIN/B-tree indexes, backfill triggers, Titan v2 embeddings, SQLAlchemy async bridge, recency boosting.
Strands Agents SDK expert — scaffold agents with LTM/STM via AgentCore Memory, namespace strategies (preferences/facts/summaries), session caching, MCP client integration, BedrockModel, Pulumi AgentCore runtime/endpoint stacks.
OTEL and Phoenix tracing expert — add setup_tracing()/shutdown_tracing() lifecycle, configure gRPC exporters, add custom spans with _tracer.start_as_current_span(), integrate Strands OpenInference processor, Phoenix docker-compose service.
MCP server development helper with tool and resource scaffolding
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Complete toolkit for building Model Context Protocol (MCP) servers in Python using the official SDK with FastMCP. Includes instructions for best practices, a prompt for generating servers, and an expert chat mode for guidance.
Meta-skills that let AI coding agents configure themselves. Manage MCP servers across 10+ agents, hooks, settings, subagents, skills, and plugins for Claude Code, Codex CLI, Cursor, and more.
Build FastMCP 3.x Python MCP servers — covers provider/transform architecture (including CodeMode, Tool Search, and server-level transforms), component versioning, session state, authorization (MultiAuth, PropelAuth, connection-pooled token verifiers), evaluation creation, Pydantic validation, async patterns, STDIO and HTTP transports, nginx reverse proxy deployment, background tasks, Prefab Apps UI, security patterns, client SDK usage, testing, deployment, and migration from FastMCP v2. TypeScript is a legacy reference only and is not updated for v3.
Semantic search for Claude Code conversations. Remember past discussions, decisions, and patterns.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Share bugs, ideas, or general feedback.