What is ultra-mcp CLAUDE.md?

A project guide for Ultra MCP, a server that lets coding tools use OpenAI, Gemini, Azure OpenAI, and xAI Grok models through one interface, with semantic code search.

Use it when developing, testing, configuring, or running Ultra MCP with Bun, TypeScript, and the MCP Inspector.

It records the commands for installing dependencies, building, testing, configuring API keys, and running the server, reducing setup mistakes.

How RealMikeChong/ultra-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to RealMikeChong/ultra-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/RealMikeChong/ultra-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/RealMikeChong/ultra-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/realmikechong/ultra-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/realmikechong/ultra-mcp/claude-md)

Your own site

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

Per session 5,103 This file is loaded in full into every session.

When invoked 5,103 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	$0.05103	$0.05103
Opus 5.5	$0.02041	$0.02041
Sonnet 5.5	$0.01021	$0.01021
Haiku 4.5	$0.00510	$0.00510

Measured 2mo ago against content hash 84bdf6b7a927, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ultra-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 · 673 lines

How it starts

The opening of the file, as written. The whole thing — 673 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 an MCP (Model Context Protocol) server called "Ultra MCP" that exposes OpenAI, Gemini, Azure OpenAI, and xAI Grok AI models through a single MCP interface for use with Claude Code and Cursor. It also includes built-in vector indexing for semantic code search across your codebase. The project uses TypeScript, Node.js, the Vercel AI SDK, and libsql for vector storage.

Development Commands

# Install dependencies
bun install

# Build TypeScript
bun run build

# Run the MCP server locally (after building)
bun dist/cli.js

# Development mode with TypeScript watch
bun run dev

# Run tests
bun test

# Run tests with UI
bun run test:ui

# Run tests with coverage
bun run test:coverage

# Test with MCP Inspector
bunx @modelcontextprotocol/inspector bun dist/cli.js

# Configure API keys
bunx -y ultra-mcp config
# or after building locally:
bun dist/cli.js config

# Run via bunx (after publishing)
bunx -y ultra-mcp

CLI Commands

The Ultra MCP CLI provides several commands:

Default Command - MCP Server

When run without arguments, Ultra MCP starts as an MCP server using stdio protocol:

# Start MCP server (stdio protocol)
bunx -y ultra-mcp
# or locally:
bun dist/cli.js

config - Interactive Configuration

Configure API keys interactively (similar to rclone):

bunx -y ultra-mcp config
# or locally:
bun dist/cli.js config

Features:

Interactive menu-driven interface
Configure OpenAI, Google Gemini, Azure OpenAI, and xAI Grok API keys
View current configuration (with masked API keys)
Reset configuration
API keys are stored securely in your system's config directory

doctor - Health Check

Check installation and configuration health:

bunx -y ultra-mcp doctor
# or locally:
bun dist/cli.js doctor

# Test connections to configured providers
bunx -y ultra-mcp doctor --test

Read the full file on GitHub · 673 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 · 673 lines · 5,103 tokens per session scan A 84bdf6b7a927

Subscribe to this mod's changes

ultra-mcp CLAUDE.md is an instructions file published in the GitHub repository RealMikeChong/ultra-mcp (277 stars, last pushed 1y ago), licensed MIT. It adds 5,103 tokens to every session, about $0.0204 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.

ultra-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ultra-mcp CLAUDE.mdRealMikeChong/ultra-mcp	Instructions file	277	1y ago	MIT	A	5,103	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

ultra-mcp: Instructions file for Claude Code