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

Per session 2,085 This file is loaded in full into every session.

When invoked 2,085 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	$0.02085	$0.02085
Opus 5.5	$0.00834	$0.00834
Sonnet 5.5	$0.00417	$0.00417
Haiku 4.5	$0.00209	$0.00209

Measured 1mo ago against content hash 7d1f341d6192, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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 · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 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 · 250 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.

1mo ago Changed · -1 lines · -16 tokens per session 7d1f341d6192
2mo 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 (89 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,085 tokens to every session, about $0.0083 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.

ibmi-mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ibmi-mcp-server CLAUDE.mdIBM/ibmi-mcp-server	Instructions file	89	yesterday	Apache-2.0	A	2,085	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

ibmi-mcp-server: Instructions file for Claude Code