Borrowing it
Nothing to install: this file belongs to nestr-dev/nestr-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nestr-dev/nestr-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/nestr-dev/nestr-mcpWrote 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.
[](https://agentmods.dev/instructions/nestr-dev/nestr-mcp/claude-md)<a href="https://agentmods.dev/instructions/nestr-dev/nestr-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nestr-dev/nestr-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.05390 | $0.05390 |
| Opus 5 | $0.02695 | $0.02695 |
| Sonnet 5 | $0.01078 | $0.01078 |
| Haiku 4.5 | $0.00539 | $0.00539 |
Grade A, and why
nestr-mcp CLAUDE.md scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
By default, the MCP endpoint returns responses as SSE streams (`text/event-stream`). For integrations that prefer plain JSON (e.g., curl-based scripts, shell-based AI agents), send `Accept: application/json` **without** How it starts
The opening of the file, as written. The whole thing — 465 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code when working with the Nestr MCP Server.
Project Overview
This is an MCP (Model Context Protocol) server that connects AI assistants (Claude, Cursor, etc.) to Nestr workspaces. It wraps the Nestr REST API and exposes it as MCP tools.
Package: @nestr/mcp
Landing page: https://mcp.nestr.io
Nestr API docs: https://app.nestr.io/api/docs
Development Commands
# Install dependencies
npm install
# Development (stdio transport)
npm run dev
# Development (HTTP server for mcp.nestr.io)
npm run dev:http
# Build TypeScript
npm run build
# Run tests
npm test
# Run tests in watch mode
npm run test:watch
# Test with MCP Inspector
npm run inspect
# Production (stdio)
npm start
# Production (HTTP)
npm run start:http
Testing
Tests use vitest + supertest. Run npm test before pushing — CI runs tests on every PR and on publish.
tests/
http-server.test.ts # HTTP integration tests (supertest against Express app)
helpers/
mock-store.ts # In-memory OAuthStore for tests
unit/
oauth.test.ts # PKCE, constantTimeCompare, validateRedirectUri
http-helpers.test.ts # getAuthToken, escapeHtml, isValidGtmId
tools-helpers.test.ts # compactResponse, enrichHints, stripDescriptionFields
api-client.test.ts # NestrClient with mocked fetch
Key conventions:
- Mock
getStore()fromsrc/oauth/store.jsusing the in-memory mock store — never hit Redis/filesystem in tests - Mock
globalThis.fetchwithvi.stubGlobalfor NestrClient and OAuth proxy tests - The Express app is exported from
src/http.tsand the startup IIFE is guarded byisDirectRunso importing it for tests doesn't start a server src/http.tsexports session helpers (sessions,sweepStaleSessions,SSE_DEAD_IDLE_TIMEOUT_MS) for direct unit testing of the stale-session sweep. Concurrent sessions per (auth token, client name) are intentional — aninitializemust never close another connection's session
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.
- 8d ago First seen · 465 lines · 5,390 tokens per session scan A e826eeae95f3
nestr-mcp CLAUDE.md is an instructions file published in the GitHub repository nestr-dev/nestr-mcp (5 stars, last pushed yesterday), licensed MIT. It adds 5,390 tokens to every session, about $0.0269 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.