What is mORMot-MCP-Server CLAUDE.md?

Build and development instructions for a Pascal server that implements MCP, the Model Context Protocol used for communication between AI tools and software. The server supports both newer stateless requests and older session-based requests.

Use them to understand the MCP request processor, build the server for Windows, and maintain support for both modern and legacy protocol clients.

They explain the server's protocol-version behavior and how to compile it with Delphi or Free Pascal. This helps developers preserve compatibility while working in a codebase with two supported compiler families.

How JavierusTk/mORMot-MCP-Server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to JavierusTk/mORMot-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/JavierusTk/mORMot-MCP-Server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/JavierusTk/mORMot-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/javierustk/mormot-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/javierustk/mormot-mcp-server/claude-md)

Your own site

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

Per session 2,665 This file is loaded in full into every session.

When invoked 2,665 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	$0.02665	$0.02665
Opus 5.5	$0.01066	$0.01066
Sonnet 5.5	$0.00533	$0.00533
Haiku 4.5	$0.00266	$0.00266

Measured 2mo ago against content hash 69bd15171c00, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mORMot-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 · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 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

mORMot2 MCP Server: a high-performance Model Context Protocol (MCP) server implementing the 2026-07-28 specification (stateless per-request model) with full backward compatibility down to 2024-11-05 (initialize/session model), built on the mORMot2 framework. Pure Pascal, no external dependencies beyond mORMot2. Dual-compiler: Delphi 10.3+ and Free Pascal 3.2+.

Dual-era model: each request's protocol era is resolved from _meta['io.modelcontextprotocol/protocolVersion'] (authoritative) and/or the MCP-Protocol-Version HTTP header. Versions >= 2026-07-28 follow the modern stateless path (no initialize, no sessions, resultType + serverInfo + cache hints on results, server/discover, subscriptions/listen); older versions follow the legacy path unchanged (initialize handshake, Mcp-Session-Id, GET SSE stream, ping, logging/setLevel, resources/subscribe). The era logic lives in src/Core/MCP.RequestProcessor.pas.

Building

# Delphi (command line)
msbuild MCPServer.dproj /p:Config=Release /p:Platform=Win64

# Free Pascal / Lazarus
lazbuild MCPServer.lpi

mORMot2 dependency: Source expected at W:\mORMot2\ (Windows) / ../mORMot2/ (Lazarus relative path). Subfolders used: src/core, src/lib, src/net, src/crypt.

Output: bin/MCPServer.exe (DCU intermediates: $(Platform)/$(Config)/)

Running

MCPServer.exe --transport=stdio          # For Claude Desktop / CLI integration
MCPServer.exe --transport=http           # HTTP + SSE on port 3000
MCPServer.exe --transport=http --port=8080
MCPServer.exe --transport=http --daemon   # Daemon mode (Ctrl+C to stop)

Architecture

Request Flow

Client (JSON-RPC 2.0)
  → Transport (stdio or HTTP+SSE)
    → TMCPRequestProcessor.HandleRequestEx()   [era resolution + validation]
      → TMCPManagerRegistry.GetManagerForMethod()
        → IMCPCapabilityManager.ExecuteMethod()
          → modern-era decoration (resultType, _meta.serverInfo, ttlMs/cacheScope)
            → Response (JSON-RPC 2.0)

Read the full file on GitHub · 139 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 · 139 lines · 2,665 tokens per session scan A 69bd15171c00

Subscribe to this mod's changes

mORMot-MCP-Server CLAUDE.md is an instructions file published in the GitHub repository JavierusTk/mORMot-MCP-Server (22 stars, last pushed 26d ago), licensed MIT. It adds 2,665 tokens to every session, about $0.0107 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.

Languages

mORMot-MCP-Server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mORMot-MCP-Server CLAUDE.mdJavierusTk/mORMot-MCP-Server	Instructions file	22	26d ago	MIT	A	2,665	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

mORMot-MCP-Server: Instructions file for Claude Code