What is mcp-server CLAUDE.md?

Project guidance for a Clojure library used to build MCP servers, which let AI tools communicate with software through defined requests and responses.

Use it when working on the library's protocols, public API, session management, JSON-RPC layer, transport systems, or request handlers.

It gives an AI coding agent the project's architecture, development conventions, and relevant commands before it changes code.

How RokLenarcic/mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to RokLenarcic/mcp-server. 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/RokLenarcic/mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/RokLenarcic/mcp-server

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

Your own site

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

Per session 936 This file is loaded in full into every session.

When invoked 936 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	$0.00936	$0.00936
Opus 5.5	$0.00374	$0.00374
Sonnet 5.5	$0.00187	$0.00187
Haiku 4.5	$0.00094	$0.00094

Measured 2mo ago against content hash 82772567995e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-server 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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 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 (claude.ai/code) when working with code in this repository.

Project Overview

This is a Clojure library for building MCP (Model Context Protocol) servers. It provides a flexible, lightweight framework that allows developers to choose their own JSON parsers, web servers, and async patterns rather than forcing specific technology choices.

Key Architecture

The library follows a layered architecture:

Core protocols (src/main/org/clojars/roklenarcic/mcp_server/protocol.clj) - Define contracts for content types and responses
Main API (src/main/org/clojars/roklenarcic/mcp_server/core.clj) - Primary public API with helper functions for creating MCP objects
Server management (src/main/org/clojars/roklenarcic/mcp_server/server.clj) - Session management, handler registration, server lifecycle
JSON-RPC layer (src/main/org/clojars/roklenarcic/mcp_server/json_rpc.clj) - JSON-RPC protocol implementation
Transport layer (src/main/org/clojars/roklenarcic/mcp_server/server/) - HTTP, SSE, and stream-based transports
Handlers (src/main/org/clojars/roklenarcic/mcp_server/handler/) - Built-in handlers for MCP operations
JSON implementations (src/main/org/clojars/roklenarcic/mcp_server/json/) - Pluggable JSON serialization adapters

Session Architecture

Sessions are the central abstraction - they're maps stored in atoms that represent client connections. Sessions contain:

Server info and capabilities
JSON serialization implementation
Dispatch table for RPC handlers
Tools, prompts, resources, and completion handlers
Connection-specific context data

Development Commands

Testing

# Run all tests
clj -M:test -m cognitect.test-runner

# Run tests for a specific namespace
clj -M:test -m cognitect.test-runner -n org.clojars.roklenarcic.mcp-server.core-test

# Run a specific test function
clj -M:test -m cognitect.test-runner -v org.clojars.roklenarcic.mcp-server.core-test/request-exchange-test

# Tests are located in test/ directory
# Uses test-check for property-based testing
# Uses matcher-combinators for test assertions

Read the full file on GitHub · 93 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 · 93 lines · 936 tokens per session scan A 82772567995e

Subscribe to this mod's changes

mcp-server CLAUDE.md is an instructions file published in the GitHub repository RokLenarcic/mcp-server (17 stars, last pushed 2mo ago), licensed MIT. It adds 936 tokens to every session, about $0.0037 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.

Building agents

mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-server CLAUDE.mdRokLenarcic/mcp-server	Instructions file	17	2mo ago	MIT	A	936	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	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	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-server: Instructions file for Claude Code