Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/ibm/ibmi-mcp-server/agents-mdgit clone --depth 1 https://github.com/IBM/ibmi-mcp-serverWrote 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/ibm/ibmi-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/ibm/ibmi-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/ibm/ibmi-mcp-server/agents-md.svg" alt="Measured on agentmods" 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 | $0.00892 | $0.00892 |
| Opus 5 | $0.00446 | $0.00446 |
| Sonnet 5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
ibmi-mcp-server AGENTS.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 4d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Mission & Outcomes
This project exists to make it easy to build MCP tools and agents for IBM i systems. Prioritize ergonomics, observability, and safe Db2 for i defaults. Every change should simplify tool creation, expand IBM i coverage, or harden reliability for downstream agent builders.
Architecture & Modules
npm workspaces monorepo. Two published packages:
@ibm/ibmi-mcp-server(packages/server/) — MCP server runtime. Bootstraps frompackages/server/src/index.ts, wiring the core server inpackages/server/src/mcp-server/server.tsand IBM i extensions inpackages/server/src/ibmi-mcp-server/. Transports live inpackages/server/src/mcp-server/transports/(stdio plus streamable HTTP via Hono). Each tool follows the mandate: pure logic inlogic.ts, registration and error handling inregistration.ts. YAML-driven data access flows throughpackages/server/src/ibmi-mcp-server/services/whereSourceManagerbuilds Mapepire pools andSqlSecurityValidatorenforces read-only guardrails. Observability is centralized inpackages/server/src/utils/telemetry/and context-aware logging helpers underpackages/server/src/utils/internal/. A publicexportssurface lives atpackages/server/src/public/(tools,services,context,formatting) and is the stable contract consumed by the CLI.@ibm/ibmi-cli(packages/cli/) — theibmicommand-line interface. Depends on@ibm/ibmi-mcp-serverat an exact-pinned version, imports tool logic via the@ibm/ibmi-mcp-server/{tools,services,context,formatting}subpaths, and invokes.logic()directly (no MCP protocol overhead for local use).
Both packages co-version: a single v* git tag releases a matched pair. See RELEASING.md.
SQL Tooling Workflow
Declare SQL tools in YAML under tools/ (performance.yaml, sys-admin.yaml) with sources, tools, and toolsets. The server hydrates them via TOOLS_YAML_PATH, validates queries, and loads requested toolsets (--toolsets). Prefer YAML statements for standard IBM i services like QSYS2.SYSTEM_STATUS; use dynamic executeSql only when strictly necessary and document it. Mirror new toolsets in docs/ and seed mocks in packages/server/tests/fixtures/.
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.
- 4d ago First seen · 35 lines · 892 tokens per session scan A 7717ad6024dd
ibmi-mcp-server AGENTS.md is an instructions file published in the GitHub repository IBM/ibmi-mcp-server (78 stars, last pushed 8d ago), licensed Apache-2.0. It adds 892 tokens to every session, about $0.0045 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.
Other instructions, from other repositories
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
plan-forge database.instructions.md
Database patterns for .NET — Dapper/EF Core, parameterized queries, migration strategy.
llm-safe-sql AGENTS.md
AGENTS.md instructions for hyuga611/llm-safe-sql, covering notes for coding agents, what this project is, rules that are not style preferences, where things are and before you say you are done.
pg-dash CLAUDE.md
Claude Code instructions for indiekitai/pg-dash, covering pg-dash claude.md, 项目结构, 构建与测试, 发版纪律（强制） and 发版检查清单（每次 npm publish 前必须按序执行）.
shop-ce AGENTS.md
AGENTS.md instructions for o3-shop/shop-ce, covering agent notes for o3-shop (shop-ce), docker setup, running tests and database.
jdbc-driver CLAUDE.md
Claude Code instructions for keboola/jdbc-driver, covering claude.md, project overview, build & test commands, jdbc driver and vscode sqltools extension.