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/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.
<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="Reviewed on agentmods" width="80" 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 | $0.06193 | $0.06193 |
| Opus 5.5 | $0.02477 | $0.02477 |
| Sonnet 5.5 | $0.01239 | $0.01239 |
| Haiku 4.5 | $0.00619 | $0.00619 |
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 5d 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 — 493 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.
Hard rule: no PII in commits, PRs or code
Treat every commit message, PR title and description, code comment, test fixture, and issue or review comment as public and permanent. Never put a real person's or customer's identity in one: no names, no company names, no email addresses, no phone numbers, no account, workspace or thread ids belonging to a real user.
This repo is public, so anything pushed here is world-readable the moment it lands. The rule holds in a private repo too. Repos get opened, forks and mirrors keep what you pushed, and a force-push does not reach anyone's existing clone. A private repo is a delay, not a boundary.
Refer to people by role instead: "a customer", "a workspace admin", "the PR author", "a teammate". The specifics belong in the Nestr project, the support thread, or the ticket, which is where the people who need them already look. Link to that rather than restating it.
The same rule covers the work you cite as motivation. "A customer asked for read-only API access" is the right amount of detail for a PR description; naming the customer and their company is not, and it is the most common way this leaks.
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.
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.
- 5d ago Changed · +4 lines · +133 tokens per session 1b84dec7814e
- 8d ago Changed · +6 lines · +200 tokens per session 0f64df43b786
- 15d ago Changed · +1 lines · +21 tokens per session d28c576e2f7b
- 16d ago Changed · +2 lines · +57 tokens per session dc7a9fd8f3e6
- 1mo ago Changed · +3 lines · +89 tokens per session 9e7dbaf3609a
- 1mo ago Changed · +1 lines · +21 tokens per session 0824d1b2de13
- 1mo ago Changed · +1 lines · +22 tokens per session 90b5bcfe1c39
- 1mo ago Changed · +10 lines · +260 tokens per session cebe331a4f32
- 2mo 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 (6 stars, last pushed today), licensed MIT. It adds 6,193 tokens to every session, about $0.0248 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).