What is cortex-mcp CLAUDE.md?

A local MCP server that scans code repositories, builds structured project knowledge, and makes it available to AI coding agents.

Use it to add repositories, scan or sync them, search their knowledge, and provide that context to an agent during coding work.

It prevents agents from repeatedly rediscovering how your repositories are organized and what they contain.

How BUGG1N/cortex-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to BUGG1N/cortex-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.

Copy the file

curl -O https://raw.githubusercontent.com/BUGG1N/cortex-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/BUGG1N/cortex-mcp

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/bugg1n/cortex-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/bugg1n/cortex-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/bugg1n/cortex-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bugg1n/cortex-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bugg1n/cortex-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bugg1n/cortex-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 949 This file is loaded in full into every session.

When invoked 949 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	$0.00949	$0.00949
Opus 5.5	$0.00380	$0.00380
Sonnet 5.5	$0.00190	$0.00190
Haiku 4.5	$0.00095	$0.00095

Measured 2mo ago against content hash 4f247feff5c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cortex-mcp 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 2mo 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 · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CORTEX MCP — Session Protocol

Standalone MCP server. Scans repositories, accumulates knowledge, and exposes it to AI agents.

Identity

Local MCP server (stdio) that acts as portfolio memory for AI agents. Scans repos (local, public/private GitHub), generates structured knowledge (YAML/JSONL), and exposes tools, resources, and prompts via the Model Context Protocol.

Architecture

src/
├── cli.ts              # Entry point — subcommands: init, add, scan, sync, sources, remove, serve
├── config.ts           # Config resolution (flags → yaml → env → auto-detect)
├── server.ts           # MCP Server wiring (stdio transport)
├── types.ts            # TypeScript types (strict, zero any)
├── index.ts            # Barrel export
├── engine/
│   ├── knowledge-engine.ts   # Orchestrator — loads and queries data
│   ├── yaml-parser.ts        # YAML/JSONL parser
│   ├── search-index.ts       # MiniSearch full-text index
│   ├── graph-traversal.ts    # BFS/DFS on the knowledge graph
│   ├── file-reader.ts        # Repository file reader
│   └── file-watcher.ts       # Hot-reload via chokidar
├── mcp/
│   ├── tools/index.ts        # MCP tools (read + write)
│   ├── resources/index.ts    # MCP resources
│   └── prompts/index.ts      # MCP prompts
├── scanner/
│   ├── index.ts              # Repository scanner
│   └── detectors/            # Stack auto-detection
│       ├── package-json.ts   # Node.js / TypeScript
│       ├── python.ts         # Python
│       ├── java.ts           # Java (Maven, Gradle)
│       ├── dotnet.ts         # .NET / C#
│       ├── go.ts             # Go
│       ├── rust.ts           # Rust
│       ├── infra.ts          # Terraform, Kubernetes, Helm
│       ├── docker.ts         # Docker
│       ├── ci.ts             # CI/CD
│       └── git.ts            # Git metadata
├── sources/
│   └── index.ts              # Source manager
└── writer/
    └── index.ts              # Knowledge writer (YAML/JSONL)

Rules

TypeScript strict, zero any
Data 100% in-memory after startup — no external database
Knowledge files: YAML + JSONL in a configurable directory
MCP transport: stdio (JSON-RPC)
File watcher: chokidar, debounce 500ms
Search: MiniSearch with fuzzy prefix, boosted fields (name 3x, desc 2x, tags 1.5x)
Tool results capped at MAX_ITEMS=10
Scanner detectors run in parallel, results deduplicated

Read the full file on GitHub · 99 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.

2mo ago First seen · 99 lines · 949 tokens per session scan A 4f247feff5c0

Subscribe to this mod's changes

cortex-mcp CLAUDE.md is an instructions file published in the GitHub repository BUGG1N/cortex-mcp (6 stars, last pushed 8mo ago), licensed MIT. It adds 949 tokens to every session, about $0.0038 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 2026-08-31.

Memory and context

cortex-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cortex-mcp CLAUDE.mdBUGG1N/cortex-mcp	Instructions file	6	8mo ago	MIT	A	949	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	yesterday	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

cortex-mcp: Instructions file for Claude Code