What is MCP-Nest CLAUDE.md?

A guide for an MCP NestJS package that exposes NestJS application providers as tools, data resources, and prompts for AI clients. MCP is a protocol for connecting AI systems to external tools and information.

Adding MCP tools or resources to NestJS applications, using decorators and authorization rules, supporting HTTP or standard-input/output connections, and maintaining compatibility between protocol revisions.

It explains the package structure and protocol differences so contributors do not use outdated APIs or configure the two supported connection styles incorrectly.

How rekog-labs/MCP-Nest configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to rekog-labs/MCP-Nest. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/rekog-labs/MCP-Nest/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/rekog-labs/MCP-Nest

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/rekog-labs/mcp-nest/claude-md/github.svg)](https://agentmods.dev/instructions/rekog-labs/mcp-nest/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/rekog-labs/mcp-nest/claude-md"><img src="https://agentmods.dev/badge/instructions/rekog-labs/mcp-nest/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/rekog-labs/mcp-nest/claude-md"><img src="https://agentmods.dev/badge/instructions/rekog-labs/mcp-nest/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,103 This file is loaded in full into every session.

When invoked 1,103 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01103	$0.01103
Opus 5.5	$0.00441	$0.00441
Sonnet 5.5	$0.00221	$0.00221
Haiku 4.5	$0.00110	$0.00110

Measured 1mo ago against content hash 3bfe27ec35cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

MCP-Nest CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

What this repo is

This is a NestJS package that lets users expose their existing NestJS providers as MCP tools, resources, and prompts, with DI, guards, pipes, interceptors, and filters applying natively.

Dual-era: one endpoint serves both the 2025-era protocol (initialize handshake, sessions) and the new stateless revision 2026-07-28. Each POST is classified with the SDK's own classifyInboundRequest; modern traffic goes to createMcpHandler, 2025 traffic to the existing wiring. GET/DELETE, statefulMode, enableJsonResponse and sessionIdGenerator are all legacy-era only. See docs/protocol-revisions.md and SPEC-2026-07-28-SUPPORT.md. Do not read LATEST_PROTOCOL_VERSION from the SDK as "the newest revision we speak" — it is 2025-11-25; the modern revision string is not exported and must be written literally.

Packages

packages/mcp-nest → @rekog/mcp-nest (core). McpStrategy (a NestJS CustomTransportStrategy), @McpController, the @Tool/@Resource/@ResourceTemplate/@Prompt decorators, Streamable HTTP + STDIO transports, and per-tool authorization primitives (@ToolScopes/@ToolRoles). Deliberately dependency-light.
packages/mcp-nest-auth → @rekog/mcp-nest-auth (optional). A built-in OAuth authorization server (McpAuthModule): your Nest app itself implements the MCP auth spec — dynamic client registration, consent, token issuance — while federating user login to an IdP (GitHub, Google, Keycloak…). Users who already have an MCP-spec-compliant authz server don't need this package at all; they just expose protected-resource metadata (see docs/external-authorization-server.md).

Layout

docs/ — user-facing guides; docs/README.md is the index. Most docs have a matching runnable project in examples/ under the same name.
examples/<project> — standalone npm projects consuming the published or local packages.
tests/ — unit/integration specs for the packages (bun test).
e2e/ — separate suite driving examples/ with a pinned old MCP client to check backward compatibility.

Read the full file on GitHub · 63 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago Changed · +4 lines · +95 tokens per session 3bfe27ec35cc
2mo ago Changed · +4 lines · +92 tokens per session 701ba541147e
2mo ago First seen · 55 lines · 916 tokens per session scan A cd7fb111c161

Subscribe to this mod's changes

MCP-Nest CLAUDE.md is an instructions file published in the GitHub repository rekog-labs/MCP-Nest (732 stars, last pushed 8d ago), licensed MIT. It adds 1,103 tokens to every session, about $0.0044 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Backend and APIs LLM llms mcp model-context-protocol modelcontextprotocol nestjs

MCP-Nest CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
MCP-Nest CLAUDE.mdrekog-labs/MCP-Nest	Instructions file	732	8d ago	MIT	A	1,103	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

MCP-Nest: Instructions file for Claude Code