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.
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 skills add IBM/ibmi-mcp-server --skill ibmi-mcp-tool-buildergit 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/skills/ibm/ibmi-mcp-server/ibmi-mcp-tool-builder)<a href="https://agentmods.dev/skills/ibm/ibmi-mcp-server/ibmi-mcp-tool-builder"><img src="https://agentmods.dev/badge/skills/ibm/ibmi-mcp-server/ibmi-mcp-tool-builder/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/skills/ibm/ibmi-mcp-server/ibmi-mcp-tool-builder"><img src="https://agentmods.dev/badge/skills/ibm/ibmi-mcp-server/ibmi-mcp-tool-builder.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 | $0.00127 | $0.02539 |
| Opus 5.5 | $0.00051 | $0.01016 |
| Sonnet 5.5 | $0.00025 | $0.00508 |
| Haiku 4.5 | $0.00013 | $0.00254 |
Grade A, and why
ibmi-mcp-tool-builder 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 5d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IBM i MCP Tool Builder
Build YAML-defined SQL tools for the IBM i MCP Server. Every tool is a parameterized Db2 for i statement plus metadata the LLM sees. The workflow is: understand → discover → prototype & test → write YAML → validate → start server.
Bundled files (paths relative to this skill directory):
| File | Purpose |
|---|---|
scripts/validate-tools.mjs |
Validates YAML tool files against the schema plus binding/reference checks |
assets/sql-tools-config.json |
The tool JSON schema (copy of the server's sql-tools-config.json) |
references/yaml-reference.md |
Field reference, parameter rules, and SQL patterns. Read it before writing YAML |
1. Understand the request
Pin down before writing SQL:
- What question should the tool answer, and who calls it (an agent, an ops dashboard)?
- Which inputs the caller should control → parameters. Everything else is fixed in the SQL.
- Read-only or write? Default to read-only. Write tools need explicit user approval (see §3).
- Which file and toolset it belongs to. Ask; default to
tools-tmp/<domain>.yaml.
If an existing tools YAML file in the workspace already covers the area, extend it instead of creating a new one.
2. Discover the right SQL service
Prefer IBM i SQL services (QSYS2.*, SYSTOOLS.*, SYSIBMADM.*) over querying system files directly.
Never invent tables, columns, or function arguments. Verify every name on the system.
Switch to IBM i Developer mode (Premium Package for i; mode ID ibm-i-developer, use
switch_mode) to get these tools:
| Tool | Use it for |
|---|---|
search_sql_examples |
IBM-provided examples for a service, e.g. QSYS2.ACTIVE_JOB_INFO |
search_ibm_i_docs_with_rag |
Service docs, parameter meanings, release/PTF requirements |
get_schema_info |
Resolve a library/schema name (system vs SQL name) |
get_file_info |
Object/file metadata |
execute_sql_statement |
Run discovery and test queries (§3) |
Useful discovery queries for execute_sql_statement:
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 217 lines · 127 tokens per session scan A 17b86b85b385
ibmi-mcp-tool-builder is a skill published in the GitHub repository IBM/ibmi-mcp-server (92 stars, last pushed yesterday), licensed Apache-2.0. It adds 127 tokens to every session and 2,539 once invoked, about $0.0005 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 2026-11-11.
ibmi-mcp-tool-builder compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ibmi-mcp-tool-builderIBM/ibmi-mcp-server | Skill | 92 | yesterday | Apache-2.0 | A | 127 | Claude Code, Codex |
| create-prprisma/orm | Skill | 48k | yesterday | Apache-2.0 | A | 47 | Claude Code, Codex |
| schema-explorationlangchain-ai/deepagents | Skill | 31k | today | MIT | A | 57 | Claude Code, Codex |
| atlas-mssqlariga/atlas | Skill | 8.8k | today | Apache-2.0 | A | 163 | Claude Code |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | today | MIT | A | 115 | Claude Code, Codex |
| nornicdb-cypher-queriesorneryd/NornicDB | Skill | 931 | today | MIT | A | 79 | Claude Code, Codex |
| dsqlawslabs/agent-plugins | Skill | 943 | 2d ago | Apache-2.0 | A | 246 | Claude Code |