Borrowing it
Nothing to install: this file belongs to danieleteti/mcp-server-delphi. 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/danieleteti/mcp-server-delphi/main/CLAUDE.mdgit clone --depth 1 https://github.com/danieleteti/mcp-server-delphiWrote 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/danieleteti/mcp-server-delphi/claude-md)<a href="https://agentmods.dev/instructions/danieleteti/mcp-server-delphi/claude-md"><img src="https://agentmods.dev/badge/instructions/danieleteti/mcp-server-delphi/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/danieleteti/mcp-server-delphi/claude-md"><img src="https://agentmods.dev/badge/instructions/danieleteti/mcp-server-delphi/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 | $0.04459 | $0.04459 |
| Opus 5.5 | $0.01784 | $0.01784 |
| Sonnet 5.5 | $0.00892 | $0.00892 |
| Haiku 4.5 | $0.00446 | $0.00446 |
Grade A, and why
mcp-server-delphi 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 160 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
MCP (Model Context Protocol) Server for DMVCFramework, using the idiomatic PublishObject JSON-RPC pattern. Allows DMVCFramework applications to expose MCP tools, resources, and prompts via the /mcp endpoint.
- Language: Object Pascal (Delphi 11+)
- Protocol: MCP 2026-07-28 and 2025-03-26 (dual-era, the request decides; see README "Protocol conformance")
- License: Apache 2.0
Build
# Compile the sample application (requires Delphi compiler)
dcc32.exe sample/MCPServerSample.dpr -Esample/bin
# Compile the test server
dcc32.exe tests/testproject/MCPServerUnitTest.dpr -Etests/testproject/bin
The project files can also be opened and built directly in the Delphi IDE.
Tests
tests\build_all.bat # builds testproject, clientproject, agentproject (Win32 Debug; set BDS to override the RAD Studio path)
tests\run_all.bat # starts the test server, then runs every suite and propagates the first failure
Six suites run: the Python HTTP compliance suite, the Python stdio suite, the Python security suite, the Delphi TMCPClient suite over HTTP and over stdio, and the TMCPOpenAIAgent suite driven by an embedded fake LLM.
Last counts: HTTP 200, stdio 160, 2026-07-28 era 69 (HTTP + stdio, tests/test_mcp_modern.py), security 218, TMCPClient 21 each over HTTP and stdio and in the legacy, modern (--era modern) and auto eras, agent 32.
The security suite (tests/test_mcp_security.py) starts the test server itself, on port 8086, once per configuration. The configuration is chosen with flags read by tests/testproject/TestFlagsU.pas (--auth-token, --jwt, --jwt-lax, --auth-elsewhere, --guard-path, --bridge-*, ...).
The stdio suite has a subset for any stdio MCP server: python tests/test_mcp_server_stdio.py --cmd "<server command>" --server-independent. It runs the handshake, framing, error-code and list cases and skips every case that names a tool, resource or prompt of the library's own test server (70 cases against the test server, 34 against tests/logorder/bin/LogOrderProbe.exe). A case that names a tool, resource or prompt must stay out of that subset.
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.
- 13d ago Changed · -6 lines · -206 tokens per session 1d8bc745c2a3
- 17d ago Changed · +59 tokens per session e1523908a8b0
- 25d ago Changed · +68 lines · +2,920 tokens per session 9f5173761173
- 2mo ago First seen · 98 lines · 1,686 tokens per session scan A 01399ae9955e
mcp-server-delphi CLAUDE.md is an instructions file published in the GitHub repository danieleteti/mcp-server-delphi (32 stars, last pushed 13d ago), licensed Apache-2.0. It adds 4,459 tokens to every session, about $0.0178 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.
mcp-server-delphi CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-server-delphi CLAUDE.mddanieleteti/mcp-server-delphi | Instructions file | 32 | 13d ago | Apache-2.0 | A | 4,459 | 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 |