What is ibmi-mcp-server CLAUDE.md?

A project guide for an IBM i server and command-line tool in an npm workspaces monorepo. IBM i is an enterprise system platform, and the guide explains the packages, common commands, builds, tests, and checks.

Use it when building, testing, linting, type-checking, or releasing the IBM i MCP server and command-line tool.

It gives contributors one place to understand the repository and use the correct commands without guessing how its two packages fit together.

How IBM/ibmi-mcp-server configures Claude Code

About the project

IBM/ibmi-mcp-server is an MCP server and command-line tool that lets AI agents interact with IBM i systems through YAML-defined SQL tools. It provides access to Db2 for i databases for querying system information, monitoring performance, and performing database operations, while the companion CLI uses the same tool definitions. The catalogue instructions support working with this server and its tools.

IBM/ibmi-mcp-server · 78 stars · on GitHub

Reuse

Borrowing it

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

Clone the repo

git clone --depth 1 https://github.com/IBM/ibmi-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/ibm/ibmi-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/ibm/ibmi-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ibm/ibmi-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/ibm/ibmi-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,101 This file is loaded in full into every session.

When invoked 2,101 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.02101	$0.02101
Opus 5	$0.01051	$0.01051
Sonnet 5	$0.00420	$0.00420
Haiku 4.5	$0.00210	$0.00210

Measured 6d ago against content hash 6234c29b3b95, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ibmi-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 6d 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 · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 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

IBM i MCP Server monorepo — an npm workspaces repo that ships two published packages:

@ibm/ibmi-mcp-server (packages/server/) — MCP server binary (ibmi-mcp-server). Production-grade MCP server enabling AI agents to interact with IBM i via Db2 for i. Uses Mapepire (WebSocket-based SQL gateway).
@ibm/ibmi-cli (packages/cli/) — the ibmi command-line interface. Depends on @ibm/ibmi-mcp-server (exact-pinned) and calls its tool logic directly for fast local execution without MCP protocol overhead.

Both packages co-version: a single v* git tag releases both with the same version.

Common Commands

All commands run from the repo root (npm workspaces handle the dispatch):

# Build
npm run build              # Compile TypeScript to dist/
npm run rebuild            # Clean and rebuild

# Test
npm test                   # Run all tests (Vitest)
npm run test:watch         # Watch mode
npm run test:coverage      # With coverage report

# Quality
npm run lint               # ESLint
npm run typecheck          # TypeScript type checking
npm run format             # Prettier formatting
npm run validate           # Validate YAML tool configurations

# Run
npm run start:http         # HTTP transport (port 3010, recommended for dev)
npm run start:stdio        # Stdio transport (for MCP Inspector)
npm run inspector          # Launch MCP Inspector UI

# YAML Tools
npm run list-toolsets                       # List available toolsets
npm run validate                            # Validate tool YAML files

# Release
npm run release:patch      # Patch version bump
npm run release:minor      # Minor version bump

Run the server with npx

npx -y @ibm/ibmi-mcp-server@latest --transport http --tools /path/to/tools.yaml

Architecture

Core Pattern: "Logic Throws, Handler Catches"

Every tool follows strict two-file separation:

Read the full file on GitHub · 251 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.

6d ago First seen · 251 lines · 2,101 tokens per session scan A 6234c29b3b95

Subscribe to this mod's changes

ibmi-mcp-server CLAUDE.md is an instructions file published in the GitHub repository IBM/ibmi-mcp-server (78 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,101 tokens to every session, about $0.0105 per session on Opus 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.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

ibmi-mcp-server: Instructions file for Claude Code