Skip to main content
MCP server CX Codex

pipeverify — Claude Code MCP server: what it does, how to install

pipeverify — a Claude Code MCP server that checks data pipeline changes and returns a verdict of pass, review or block.

Apache-2.0 ★ 5 updated 2026-11-16

Install into Claude Code · Platform CLI All methods and platforms ↓
claude mcp add pipeverify -- uvx pipeverify
Open on GitHub

What pipeverify does

The tool compares tables before and after a modification to catch hidden row drops, duplicate keys, and silent metric shifts. AI coding agents and CI workflows call it on every pull request to verify that job success matches data correctness. It reads Parquet files, DuckDB tables, dbt models, and Snowflake databases directly.

SQL database sources require the additional driver package installed via pip install "pipeverify[sql]". On Windows, run the tool as python -m pipeverify if the executable is not recognized.

What it helps with

  • compare table snapshots before and after a data change
  • evaluate pipeline modifications with pass, review or block
  • check dbt models against production on pull requests
  • detect lost rows and unexpected key duplicates in tables

Example prompts for the agent

  • Compare tables in before/orders.parquet and after/orders.parquet using key order_id
  • Run the pipeline verification using config file pipeverify.yml
  • Check data changes in DuckDB warehouse using pipeverify

How to install pipeverify

Platform CLI

claude mcp add pipeverify -- uvx pipeverify

uvx runs the command named after the package; if the README names another one, use uvx --from pipeverify <command>

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about pipeverify

How to install pipeverify in Claude Code?

Run the command claude mcp add pipeverify -- uvx pipeverify in your terminal.

What does pipeverify do?

It compares two table snapshots and returns a verdict on whether the data change is safe: PASS, REVIEW, or BLOCK.

What is needed for SQL database support?

SQL sources require installing dependencies with pip install "pipeverify[sql]" along with the database driver.

Similar MCP servers

All MCP servers for Data and databases →
dex Exmergo, Inc. The dex plugin for Claude Code and Codex explores data warehouses, maintains dbt models, and tracks schema drift. CX Codex ★ 1,596repo stars migrating-dbt-project-across-platforms dbt-labs migrating-dbt-project-across-platforms guides dbt project migrations across data platforms using dbt Fusion real-time compilation. Catches SQL dialect issues early and verifies logic using unit tests. CX Codex +1 531installs data-warehouse-experimentation rampstackco The data-warehouse-experimentation Claude Code skill explains how to run A/B tests in a data warehouse without vendor platforms. It covers user assignment, metric calculation, and statistical analysis. CX Codex +1 283installs orionbelt-semantic-layer ralforion orionbelt-semantic-layer — an MCP server that compiles YAML models into SQL for BigQuery, Snowflake, DuckDB and five more dialects. An agent defines metrics and dimensions once, then asks questions in plain language. CX Codex +1 ★ 104repo stars zomato-ai-data-engineering-pipeline reason-machines zomato-ai-data-engineering-pipeline is a Claude Code skill for building a food delivery batch pipeline across S3, Snowflake, dbt, and Airflow, with OpenAI for review enrichment and text-to-SQL. CX Codex +1 128installs Valuein — SEC EDGAR Fundamentals & Smart-Money Data valuein Valuein — SEC EDGAR Fundamentals & Smart-Money Data — MCP server for Claude Code and Codex supplies point-in-time US fundamentals from SEC filings and verifies numerical lineage against filed disclosures. CX Codex +1 ★ 5repo stars

Project sponsors

Companies that keep this analytics open