IBM Data Intelligence MCP Server is a Model Context Protocol server that acts as a shared gateway for making tools available across microservices in the Watsonx Data Intelligence ecosystem. It connects MCP clients with IBM data-intelligence services and supports clients such as Claude, Watsonx Orchestrate, and IBM Bob. The catalogue lists five skills for working with the server.
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/data-intelligence-mcp-server --skill data-qualitygit clone --depth 1 https://github.com/IBM/data-intelligence-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/data-intelligence-mcp-server/data-quality)<a href="https://agentmods.dev/skills/ibm/data-intelligence-mcp-server/data-quality"><img src="https://agentmods.dev/badge/skills/ibm/data-intelligence-mcp-server/data-quality/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/data-intelligence-mcp-server/data-quality"><img src="https://agentmods.dev/badge/skills/ibm/data-intelligence-mcp-server/data-quality.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 | $0.00169 | $0.02485 |
| Opus 5.5 | $0.00068 | $0.00994 |
| Sonnet 5.5 | $0.00034 | $0.00497 |
| Haiku 4.5 | $0.00017 | $0.00248 |
Grade A, and why
data-quality 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 22d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Data Quality Pipeline Guide
Overview
Use this skill when the user wants to generate a Data Quality (DQ) pipeline for their datasets. The pipeline is implemented as a Metadata Enrichment (MDE) job scoped to DQ-specific enrichment objectives. The skill guides the user through project setup, connection configuration, metadata import, and DQ enrichment execution. All phases and steps should be presented to the user as a TODO list so they can follow along and understand which phase/step is being run.
Example user queries:
- "Generate a DQ pipeline for my sales data"
- "Run data quality checks on my Postgres tables"
- "Create a DQ pipeline for the Finance project"
- "Analyze quality and generate constraints for my datasets"
- "Check data quality on our Oracle schemas"
- "How good is my data?"
- "Validate my tables and score completeness"
- "Analyze data quality for the tables in my BANK database"
General Instructions
- If the user must make a choice, always display an options list.
- If multiple choices are possible, display them in a checklist format.
- Always give the user the option to write their own choice.
- Always try not to interrupt the user too much — batch questions where possible.
- When moving from one step to another, inform the user and proceed.
- Error handling: If any tool call fails, display the error message to the user and ask whether to retry with adjusted parameters, skip the step, or abort the pipeline.
Phase 0: Intent Detection
Always start by determining the user's intent and what data they want to run DQ on.
- If the user provides a project name, carry it into Phase 1.
- If the user provides a connection name, carry it into Phase 2.
- If the user states that data is already imported into a project, skip to Phase 3 (DQ Enrichment).
- If intent is ambiguous (e.g. "check my data quality" with no project or connection mentioned), ask:
- "Which project should we run the DQ pipeline in? And do you already have a data connection set up, or do we need to configure one?"
- Proceed once the user clarifies.
What ships with it
2 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.
- 22d ago First seen · 244 lines · 169 tokens per session scan A 0c57a1b669d1
data-quality is a skill published in the GitHub repository IBM/data-intelligence-mcp-server (20 stars, last pushed 9d ago), licensed Apache-2.0. It adds 169 tokens to every session and 2,485 once invoked, about $0.0007 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 2026-09-25.
Other skills, from other repositories
alloydb-basics
Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB Model Context Protocol (MCP) tools for automated database operations. Use when creating, configuring, or administering AlloyDB databases. Do NOT use for general PostgreSQL instances (e.g. Cloud SQL) or other GCP databases.
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
db-repair
Auto-fix gbrain's Postgres access so the brain stays available. When any gbrain command or MCP tool result carries a GBRAINDBACCESS marker (or an operator reports the brain database is down), run the hardcoded gbrain db-repair ladder: diagnose, apply the safe tier, verify. The action is ALWAYS the hardcoded command …
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…
volcengine-rds-postgresql
A tool for operating PostgreSQL databases hosted by Volcano Engine's managed database service. PostgreSQL is a relational database used to store structured application data.
analyzing-insights-across-teams
Analyze PostHog insights, dashboards, or teams beyond the current project by querying the prod Postgres replicas synced into the dogfood data warehouse (US project 2, "PostHog App + Website"). Use when asked to analyze insights across all teams or projects, another team's insights, or fleet-wide insight/dashboard…