MCP-Nest

A NestJS module for building and exposing Model Context Protocol (MCP) servers that map NestJS methods to MCP tools (with Zod validation), plus MCP resources and prompt templates. It supports multiple transports (HTTP+SSE, Streamable HTTP, STDIO) and offers guard-based and built-in/external authorization patterns (including OAuth).

Evaluated Mar 30, 2026 (22d ago)
Repo ↗ Ai Ml nestjs mcp model-context-protocol tooling authorization typescript zod oauth
⚙ Agent Friendliness
57
/ 100
Can an agent use this?
🔒 Security
59
/ 100
Is it safe for agents?
⚡ Reliability
31
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
85
Documentation
75
Error Messages
0
Auth Simplicity
45
Rate Limits
10

🔒 Security

TLS Enforcement
70
Auth Strength
70
Scope Granularity
35
Dep. Hygiene
55
Secret Handling
60

README emphasizes guard-based auth, per-tool authorization, and OAuth/built-in/external authorization server options. TLS enforcement and secure-by-default transport configuration are not explicitly detailed in the provided README. Dependency list includes common auth/session middleware; no vulnerability status is provided, so dependency hygiene is scored conservatively. No explicit secret-handling practices are described in the provided content.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
40
Error Recovery
40
AF Security Reliability

Best When

You already have a NestJS codebase and want to reuse it as an MCP server with strong runtime validation (Zod), DI, and optional OAuth/authorization patterns.

Avoid When

When you cannot run/manage a NestJS server process (e.g., pure client-side or serverless constraints without control of the runtime), or when you need a standardized, externally documented HTTP API rather than MCP transport endpoints.

Use Cases

  • Expose existing NestJS business logic as MCP tools to AI agents
  • Serve MCP resources and reusable prompt templates from a NestJS app
  • Build self-hosted MCP servers with consistent DI, validation, and authorization
  • Adopt per-tool authorization and request-context access within MCP handlers
  • Run MCP over multiple transports (HTTP/SSE or stdio) depending on deployment

Not For

  • Teams looking for a managed hosted MCP endpoint (this is an application framework/module)
  • Environments that require a simple unauthenticated local-only tool runner with no NestJS setup
  • Use cases that depend on a documented public REST/GraphQL API surface (the primary interface here is MCP)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Guard-based authentication (NestJS guards) OAuth support (as described in docs references) Built-in authorization server (beta) External authorization server integration (Keycloak/Auth0 mentioned in docs references)
OAuth: Yes Scopes: No

Auth capabilities are described at a feature level (guard-based, OAuth, per-tool authorization, built-in/external authorization server), but the README does not provide concrete scope/claim granularity details.

Pricing

Free tier: No
Requires CC: No

Open-source npm package (MIT) used in your own infrastructure; no SaaS pricing described.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Correct MCP transport configuration is required (HTTP+SSE, streamable HTTP, or stdio).
  • Per-tool authorization/guards may block calls if agent identity/claims are not set up as expected.
  • Tool parameter validation relies on Zod schemas; mismatched inputs may fail validation at runtime.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for MCP-Nest.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered