MCP-Nest and nest-mcp

These are competitors offering different approaches to integrating MCP with NestJS—one focused on exposing AI tools/resources through a dedicated module, the other providing broader infrastructure for building MCP servers, clients, and gateways within the NestJS ecosystem.

MCP-Nest
58
Established
nest-mcp
41
Emerging
Maintenance 16/25
Adoption 10/25
Maturity 9/25
Community 23/25
Maintenance 13/25
Adoption 4/25
Maturity 9/25
Community 15/25
Stars: 599
Forks: 104
Downloads:
Commits (30d): 4
Language: TypeScript
License: MIT
Stars: 7
Forks: 4
Downloads:
Commits (30d): 0
Language: TypeScript
License: BSD-3-Clause
No Package No Dependents
No Package No Dependents

About MCP-Nest

rekog-labs/MCP-Nest

A NestJS module to effortlessly create Model Context Protocol (MCP) servers for exposing AI tools, resources, and prompts.

Leverages NestJS decorators and dependency injection to map service methods directly as MCP tools, resources, and prompts with automatic Zod validation and discovery. Supports multiple transports (HTTP+SSE, streamable HTTP, STDIO) with built-in OAuth/guard-based authentication and optional external authorization server integration (Keycloak, Auth0). Enables interactive tool calls with user elicitation, per-tool authorization, and runtime capability registration for enterprise-grade MCP server implementations.

About nest-mcp

btwld/nest-mcp

Build Model Context Protocol (MCP) servers, clients, and gateways using the NestJS ecosystem you already know.

Provides multi-transport MCP support (HTTP, SSE, STDIO) with built-in auth guards, middleware chains, and resilience patterns (rate limiting, circuit breakers, retries). The gateway package enables upstream server aggregation with policy enforcement, response caching, and request/response transformation hooks. Architecture mirrors NestJS patterns: decorators for tools/resources/prompts, dependency injection for client connections, and modular composition across server, client, and gateway layers.

Scores updated daily from GitHub, PyPI, and npm data. How scores work