claudecodex

fastmcp-engineering

Research-first FastMCP and MCP engineering skills, contracts, and prompts for production MCP servers

0 on GitHubby evgenygurinv0.2.0MITupdated 2 months ago

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin fastmcp-engineering in evgenygurin/fastmcp-engineering. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (58)

  • pydantic-ai-agent-engineering

    Evidence-first engineering of production PydanticAI agents integrated with FastMCP, layered application architecture, deterministic tools, structured outputs, MCP toolsets, dependencies, model providers, retries, limits, streaming and human approval.

  • api-contract-schema-engineering

    Evidence-first API and MCP contract engineering with Pydantic v2 and JSON Schema.

  • api-lifecycle-versioning

    Evidence-first API lifecycle, schema evolution and compatibility engineering for FastMCP/MCP servers.

  • api-tool-engineering

    Evidence-first design of production MCP tools, resources and prompts as stable public APIs.

  • application-architecture-usecases

    Evidence-first layered application architecture for FastMCP services using explicit use cases, dependency inversion and domain boundaries.

  • application-domain-architecture

    Evidence-first design of layered Python application/domain architecture for FastMCP and PydanticAI systems, with explicit use cases, ports, adapters, policies, transaction ownership and dependency direction.

  • architecture-governor

    Enforce layered architecture, dependency direction, responsibility boundaries, and justified complexity for production FastMCP systems.

  • async-event-driven-engineering

    Design asynchronous FastMCP systems with correct lifecycle, cancellation, delivery semantics, idempotency, and backpressure — use for async/background work.

  • github-actions-engineering

    Design secure, reproducible GitHub Actions CI/CD for FastMCP/PydanticAI services — use for workflow, OIDC, artifact, and deployment pipeline design.

  • configuration-environment-engineering

    Evidence-first typed configuration and environment engineering for production FastMCP systems.

  • configuration-dependency-management

    Evidence-first configuration, dependency and reproducible-environment engineering for production Python/FastMCP systems.

  • data-persistence-engineering

    Evidence-first PostgreSQL and persistence engineering for production FastMCP systems.

  • database-persistence-sqlalchemy

    Evidence-first persistence engineering for FastMCP applications using SQLAlchemy 2.x and PostgreSQL/Supabase.

  • database-sqlalchemy-engineering

    Evidence-first database and SQLAlchemy 2.x engineering for production FastMCP systems, including async ORM, transactions, repositories, migrations, concurrency, pooling, query performance and real database verification.

  • sqlalchemy-postgresql-engineering

    Evidence-first database engineering for production Python systems using SQLAlchemy 2.x and PostgreSQL, with explicit transaction ownership, async session discipline, schema/migration design, concurrency, RLS, performance and integration testing.

  • dependency-injection-composition-root

    Evidence-first dependency injection, lifecycle and composition-root engineering for production FastMCP applications.

  • dependency-supply-chain-security

    Evidence-first dependency, software supply-chain and reproducible-build security for FastMCP projects.

  • deployment-operations-engineering

    Evidence-first production deployment and operations engineering for FastMCP systems.

  • packaging-build-deployment

    Evidence-first packaging, container build and production deployment engineering for FastMCP Python services.

  • engineering-governance

    Meta-orchestration and governance for evidence-driven engineering across all project skills.

  • fastmcp-research

    Produce reproducible, version-aware research artifacts for FastMCP projects — use before any framework-sensitive implementation decision.

  • fastmcp-auth

    Design FastMCP authentication and authorization as explicit security boundaries — use for OAuth, JWT, and MCP auth implementation.

  • fastmcp-client-testing

    Build evidence-first FastMCP verification using the official Client, protocol-level integration tests, transport tests, security tests, and deterministic architecture verification.

  • fastmcp-components

    Design FastMCP tools, resources, and prompts as thin MCP adapters — use for MCP component architecture and API version-sensitive implementation.

  • fastmcp-context-di

    Design FastMCP Context and dependency injection without turning request context into a Service Locator, God Object, or hidden application container.

  • fastmcp-lifespan

    Design FastMCP lifecycle management with explicit resource ownership, startup/shutdown ordering, cleanup, composition, cancellation, concurrency, and integration boundaries.

  • fastmcp-middleware

    Design and implement FastMCP middleware for cross-cutting request/component behavior with explicit ordering, context, error, security, performance, and lifecycle boundaries.

  • fastmcp-protocol-compliance

    Build FastMCP servers with explicit MCP specification compliance, separating protocol guarantees from FastMCP behavior and application conventions.

  • fastmcp-providers

    Design and implement FastMCP Providers as component sources/composition boundaries, without confusing them with repositories, services, dependency injection containers, or business-logic layers.

  • fastmcp-tasks

    Design FastMCP background task execution with verified MCP semantics, explicit ownership, idempotency, cancellation, persistence, and failure boundaries.

  • fastmcp-transforms

    Design and implement FastMCP Transforms for systematic component composition and representation changes while preserving clean application/domain boundaries.

  • fastmcp-transports-deployment

    Engineer FastMCP transport and production deployment boundaries with version-specific evidence, explicit session/state semantics, ASGI integration, security, graceful shutdown, scaling, and observability.

  • final-review

    Perform evidence-based final review of a FastMCP change before declaring it complete.

  • pattern-selection

    Select the smallest justified architectural pattern for a concrete problem without cargo-culting design patterns.

  • research-first

    Enforce research-first workflow before any framework-sensitive change — use to prevent implementation based on stale APIs or assumptions.

  • mcp-primitives-engineering

    Evidence-first engineering rules for MCP tools, resources, prompts and advanced protocol primitives in FastMCP.

  • mcp-server-architecture

    Evidence-first FastMCP v3+ server architecture covering MCP boundaries, tools, resources, prompts, middleware, context, lifespan, transports, composition, proxying, auth integration and lifecycle.

  • observability-opentelemetry

    Evidence-first observability engineering for FastMCP systems using OpenTelemetry, structured logs, metrics and traces.

  • observability-diagnostics

    Design production observability for FastMCP systems with trace/log/metric correlation, OpenTelemetry, safe redaction, MCP/agent/tool/database diagnostics and actionable failure taxonomy.

  • observability-operations

    Evidence-first observability, reliability and production operations for FastMCP systems, including traces, metrics, logs, correlation, LLM/tool telemetry, redaction, health, readiness, SLOs and incident diagnostics.

  • observability-telemetry-engineering

    Evidence-first observability and telemetry engineering for production FastMCP systems using OpenTelemetry.

  • performance-capacity-engineering

    Evidence-first performance, capacity and scalability engineering for production FastMCP systems.

  • performance-resource-engineering

    Evidence-first performance engineering for FastMCP and PydanticAI systems, focused on latency, throughput, resource budgets and measurement.

  • mcp-protocol-engineering

    Evidence-first MCP protocol engineering for FastMCP servers and clients, including lifecycle, transports, capabilities, sessions, tools/resources/prompts, errors, compatibility, and protocol testing.

  • pydantic-ai-agent-integration

    Engineer PydanticAI agents behind explicit application boundaries and integrate them with FastMCP without leaking agent state, prompts, model concerns, or provider details into domain logic.

  • pydantic-schema-engineering

    Engineer Pydantic v2 and MCP-facing schemas with explicit contracts, strict validation, JSON Schema compatibility, evolution rules, and separation from domain/ORM models.

  • reliability-resilience-engineering

    Evidence-first reliability and resilience engineering for production FastMCP systems.

  • resilience-reliability-engineering

    Evidence-first reliability engineering for FastMCP, PydanticAI, database and external-service workflows, covering deadlines, retries, idempotency, concurrency, backpressure, degradation and recovery.

  • documentation-evidence-governance

    Evidence-first research governance for version-sensitive FastMCP/MCP/PydanticAI engineering.

  • pydantic-engineering

    Treat Pydantic schemas as executable contracts at system boundaries — use for model validation, serialization, and MCP schema design.

  • security-engineering

    Evidence-first security engineering for production MCP/FastMCP and PydanticAI systems, covering authentication, authorization, OAuth, trust boundaries, tool security, prompt injection, SSRF, secrets, tenancy and supply-chain risk.

  • security-privacy-governance

    Evidence-first security, privacy, secrets and data-governance engineering for FastMCP systems.

  • security-threat-modeling

    Security engineering and threat modeling for production FastMCP systems, covering MCP boundaries, authn/authz, agents, tools, resources, databases, external dependencies and supply chain.

  • sqlalchemy-persistence-architecture

    Engineer SQLAlchemy 2.x persistence behind explicit application transaction boundaries, repositories, unit of work, async lifecycle, concurrency, migrations, and database security.

  • testing-quality-engineering

    Evidence-first testing and quality engineering for production FastMCP systems.

  • testing-tdd-engineering

    Evidence-first testing and TDD engineering for FastMCP, PydanticAI, SQLAlchemy and production Python services.

  • testing-verification-engineering

    Evidence-first testing and verification engineering for production FastMCP systems across unit, integration, contract, protocol, database, agent, security, property, mutation and end-to-end layers.

  • using-fastmcp-engineering

    Use when starting any FastMCP/MCP engineering work - establishes how to find and use fastmcp-engineering skills, requiring skill invocation before ANY response including clarifying questions

Hooks (1)

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" session-start

View source on GitHub

Similar plugins

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

mempalace

claudecodex

AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.

3 skills · 6 commands · 1 MCP server · hooks

MemPalace/mempalace 60,536

Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer

8 skills · 1 MCP server

ChromeDevTools/chrome-devtools-mcp 55,181

gitnexus

claudecodex

Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.

12 skills · 1 MCP server · hooks

abhigyanpatwari/GitNexus 48,482

daisyUI Blueprint MCP server - (Needs paid license)

saadeghi/daisyui 42,821

Maintain fastmcp-engineering?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted