Catalog Cli Pro

io.github.BWB03Published by GitHub account BWB03v1.0.0Updated Oct 24, 2026

Amazon catalog auditing tool. 13 quality checks for your listings.

VerifiedSTDIODesktop onlyData & Analytics Business & Commerce

Server details

Identifier: io.github.BWB03/catalog-cli-pro
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account BWB03 for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.BWB03%2Fcatalog-cli-pro.svg)](https://sourceweft.com/mcp/io.github.BWB03%2Fcatalog-cli-pro?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Local MCP server that lets an assistant audit Amazon Category Listing Report spreadsheets with 14 quality checks and compare live Seller Central listings.

What you can do: Scan a CLR spreadsheet with all built-in checks and get a summary of issues by SKU and severity, or run a single named check such as missing attributes, bullet quality, or title length and prohibited characters. List available queries and inspect their request and response schemas. Fetch a live Seller Central listing for an ASIN and diff it against a matching CLR row. Output can be narrowed with field masks, limits and pagination.
When to use it: Useful when you work with Amazon Seller Central catalogs and want an assistant to triage listing quality from a downloaded Category Listing Report, or to check whether a live listing still matches the report. Suited to sellers and catalog managers rather than general development work.
Requirements: Runs as a local stdio process; the README lists Python 3.10+ and the mcp package, though the manifest points to an npm package. A Category Listing Report file (.xlsm or .xlsx) is needed for audits. The manifest declares a required CATALOG_API_KEY secret; the README also mentions a Seller Central cookie passed via --cookie, --cookie-file or CATALOG_SELLER_CENTRAL_COOKIE for live listing lookups. Network access is needed for Seller Central fetches and the hosted API.

Before you install

The Seller Central cookie is a live session credential; the README says it stays local, but it grants access to your seller account, so treat it as sensitive. Live listing fetches contact Amazon on your behalf. The hosted API is a paid subscription ($9.99/mo) and requires CATALOG_API_KEY. Scans read local spreadsheet files, so point it only at files you intend to share with the assistant.

Installation

In SourceWeft

Open Catalog Cli Pro in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Catalog CLI

[PyPI version] [License: MIT]

Agent-native Amazon catalog auditing tool

The first AI-agent-friendly Amazon catalog analysis tool. Query your CLRs with structured input, integrate via MCP server, and automate catalog audits.

Hosted API available at api.catalogcli.com — persistent storage, unlimited scans, and API access for $9.99/mo. Learn more

What's New in v2.3

Seller Central AJAX lookup - Fetch Amazon's live Seller Central listing JSON with catalog listing fetch <asin>
Live listing vs CLR diff - Compare Amazon's current listing fields against your Category Listing Report with catalog listing diff <asin> <clr-file>
Agent-ready Seller Central tools - New MCP tools catalog_seller_listing_fetch and catalog_seller_listing_diff
Local cookie auth - Use --cookie, --cookie-file, or CATALOG_SELLER_CENTRAL_COOKIE; Seller Central cookies stay local

v2.2 Title Readiness

Amazon title readiness - mobile-title-readiness flags titles over 75 characters for Amazon's mobile title update
Rewrite-ready output - Returns first-75-character title segments, overflow text, significant terms, item highlight status, and recommended next actions
Agent workflow friendly - Aliases title-75 and amazon-title-75 make it easy to call from Claude, MCP clients, and automation workflows
14 built-in checks - Adds a title triage workflow while keeping the classic 200-character long-titles check unchanged

v2.0 Agent Foundations

Shared core architecture - Business logic separated into catalog/core/, powering both CLI and MCP
MCP server - catalog mcp launches a stdio MCP server with 4 tools, ready for Claude Desktop and any MCP client
JSON input - --json and --stdin flags for structured agent input
Schema introspection - catalog schema --format json returns full request/response schemas
Field masks - --fields sku,severity,details to reduce output size
Pagination - --limit and --offset for controlling result size
NDJSON streaming - --format ndjson for line-by-line streaming of large results
Input hardening - Pydantic validation rejects path traversal, injection, and malformed input
Environment variables - CATALOG_CLI_DEFAULT_FORMAT=json for headless/CI use
Backward compatible - All v1.x commands work unchanged

Features

Agent-Native - CLI + MCP server as equal citizens, JSON/NDJSON output, schema introspection
Fast - Query 1000+ SKU catalogs in seconds
Extensible - Plugin system for custom queries
Comprehensive - 14 built-in catalog health checks
Intent Optimized - COSMO-inspired shopper intent coverage for bullets

Installation

Or install from source:

Quick Start

For Humans

bash

# Run all catalog checkscatalog scan my-catalog.xlsx
# Detailed resultscatalog scan my-catalog.xlsx --show-details
# Run specific checkcatalog check intent-bullets my-catalog.xlsx
# Audit titles for Amazon's 75-character mobile title updatecatalog check mobile-title-readiness my-catalog.xlsx
# List available queriescatalog list-queries

# Run all catalog checkscatalog scan my-catalog.xlsx
# Detailed resultscatalog scan my-catalog.xlsx --show-details
# Run specific checkcatalog check intent-bullets my-catalog.xlsx
# Audit titles for Amazon's 75-character mobile title updatecatalog check mobile-title-readiness my-catalog.xlsx
# List available queriescatalog list-queries

For AI Agents

bash

# JSON output with field mask and limitcatalog scan my-catalog.xlsx --format json --fields sku,severity,details --limit 20
# Title rewrite triage for agentscatalog check mobile-title-readiness my-catalog.xlsx --format json \  --fields sku,details,title_char_count,mobile_visible_title,overflow_title,all_significant_terms
# Structured JSON inputcatalog scan --json '{"file": "my-catalog.xlsx", "queries": ["missing-attributes"], "limit": 10}'
# Piped inputecho '{"file": "my-catalog.xlsx"}' | catalog scan --stdin --format json
# NDJSON streaming for large resultscatalog scan my-catalog.xlsx --format ndjson
# Schema introspection (discover queries, params, response shapes)catalog schema --format json
# Fetch live Seller Central listing JSON for an ASINCATALOG_SELLER_CENTRAL_COOKIE='session-id=...' catalog listing fetch B000TEST01 --format json
# Compare live Seller Central JSON with a CLR rowcatalog listing diff B000TEST01 my-catalog.xlsx --sku SKU-123 --format json

# JSON output with field mask and limitcatalog scan my-catalog.xlsx --format json --fields sku,severity,details --limit 20
# Title rewrite triage for agentscatalog check mobile-title-readiness my-catalog.xlsx --format json \  --fields sku,details,title_char_count,mobile_visible_title,overflow_title,all_significant_terms
# Structured JSON inputcatalog scan --json '{"file": "my-catalog.xlsx", "queries": ["missing-attributes"], "limit": 10}'
# Piped inputecho '{"file": "my-catalog.xlsx"}' | catalog scan --stdin --format json
# NDJSON streaming for large resultscatalog scan my-catalog.xlsx --format ndjson
# Schema introspection (discover queries, params, response shapes)catalog schema --format json
# Fetch live Seller Central listing JSON for an ASINCATALOG_SELLER_CENTRAL_COOKIE='session-id=...' catalog listing fetch B000TEST01 --format json
# Compare live Seller Central JSON with a CLR rowcatalog listing diff B000TEST01 my-catalog.xlsx --sku SKU-123 --format json

MCP Server (for Claude Desktop, CLR Pro, etc.)

Add to Claude Desktop config:

MCP tools: catalog_scan, catalog_scan_summary, catalog_check, catalog_seller_listing_fetch, catalog_seller_listing_diff, catalog_list_queries, catalog_schema

Available Queries

Attribute Audits

missing-attributes - Find mandatory attributes missing from listings
missing-any-attributes - Find all missing attributes (required + conditional)
new-attributes - Find unused template fields that might add value

Content Quality

intent-bullets - Score bullet points against shopper intent coverage
bullet-prohibited-content - Find bullet points with prohibited chars, emojis, claims, or placeholders
bullet-formatting - Check bullet formatting (capitalization, length, punctuation)
bullet-awareness - Soft violations in bullets (excessive caps, problematic chars)
mobile-title-readiness - Find titles over 75 characters and prepare rewrite inputs
long-titles - Find titles exceeding 200 characters
title-prohibited-chars - Find titles with prohibited characters
prohibited-chars - Find prohibited characters in title/brand

Catalog Structure

product-type-mismatch - Find mismatched product types and item keywords
missing-variations - Find products that should be variations but aren't

CLI Commands

`catalog scan`

Run all queries on a CLR file.

bash

catalog scan <clr-file> [OPTIONS]
Options:  --format [terminal|json|csv|ndjson]  Output format (default: terminal)  --output PATH                        Output file path  --show-details / --no-details        Show detailed results  --include-fbm-duplicates             Legacy: include repeated exact-SKU rows  --json TEXT                          JSON request body  --stdin                              Read JSON request from stdin  --queries TEXT                       Comma-separated query names  --fields TEXT                        Comma-separated field mask  --limit INTEGER                      Max issues to return  --offset INTEGER                     Skip first N issues

catalog scan <clr-file> [OPTIONS]
Options:  --format [terminal|json|csv|ndjson]  Output format (default: terminal)  --output PATH                        Output file path  --show-details / --no-details        Show detailed results  --include-fbm-duplicates             Legacy: include repeated exact-SKU rows  --json TEXT                          JSON request body  --stdin                              Read JSON request from stdin  --queries TEXT                       Comma-separated query names  --fields TEXT                        Comma-separated field mask  --limit INTEGER                      Max issues to return  --offset INTEGER                     Skip first N issues

`catalog check`

Run a specific query.

bash

catalog check <query-name> <clr-file> [OPTIONS]
Options:  --format [terminal|json|csv|ndjson]  Output format (default: terminal)  --output PATH                        Output file path  --show-details / --no-details        Show detailed results  --json TEXT                          JSON request body  --stdin                              Read JSON request from stdin  --fields TEXT                        Comma-separated field mask  --limit INTEGER                      Max issues to return  --offset INTEGER                     Skip first N issues

catalog check <query-name> <clr-file> [OPTIONS]
Options:  --format [terminal|json|csv|ndjson]  Output format (default: terminal)  --output PATH                        Output file path  --show-details / --no-details        Show detailed results  --json TEXT                          JSON request body  --stdin                              Read JSON request from stdin  --fields TEXT                        Comma-separated field mask  --limit INTEGER                      Max issues to return  --offset INTEGER                     Skip first N issues

`catalog listing fetch`

Fetch Amazon's live Seller Central listing JSON for an ASIN.

Requires a logged-in Seller Central cookie from your own browser session. Pass it with --cookie, --cookie-file, or the CATALOG_SELLER_CENTRAL_COOKIE environment variable.

bash

catalog listing fetch <asin> [OPTIONS]
Options:  --format [terminal|json]  Output format (default: terminal)  --output PATH             Output file path  --cookie TEXT             Seller Central Cookie header value  --cookie-file PATH        File containing the Cookie header value  --timeout FLOAT           HTTP timeout in seconds  --json TEXT               JSON request body  --stdin                   Read JSON request from stdin

catalog listing fetch <asin> [OPTIONS]
Options:  --format [terminal|json]  Output format (default: terminal)  --output PATH             Output file path  --cookie TEXT             Seller Central Cookie header value  --cookie-file PATH        File containing the Cookie header value  --timeout FLOAT           HTTP timeout in seconds  --json TEXT               JSON request body  --stdin                   Read JSON request from stdin

`catalog listing diff`

Compare Amazon's live Seller Central listing JSON with a matching CLR row.

Rows match by --sku when provided. Otherwise Catalog CLI looks for Product Id Type = ASIN and Product Id = <asin> in the CLR.

bash

catalog listing diff <asin> <clr-file> [OPTIONS]
Options:  --sku TEXT                Optional SKU to match in the CLR  --format [terminal|json]  Output format (default: terminal)  --output PATH             Output file path  --cookie TEXT             Seller Central Cookie header value  --cookie-file PATH        File containing the Cookie header value  --timeout FLOAT           HTTP timeout in seconds  --json TEXT               JSON request body  --stdin                   Read JSON request from stdin

catalog listing diff <asin> <clr-file> [OPTIONS]
Options:  --sku TEXT                Optional SKU to match in the CLR  --format [terminal|json]  Output format (default: terminal)  --output PATH             Output file path  --cookie TEXT             Seller Central Cookie header value  --cookie-file PATH        File containing the Cookie header value  --timeout FLOAT           HTTP timeout in seconds  --json TEXT               JSON request body  --stdin                   Read JSON request from stdin

`catalog schema`

Show schema for queries, params, and response shapes.

`catalog list-queries`

List available queries.

`catalog mcp`

Start the MCP server (stdio transport).

`catalog setup-claude`

Configure Claude Code to use Catalog CLI as an MCP tool server.

bash

# Free (local) — data stays on your machinecatalog setup-claude
# Pro (hosted API) — persistent storage, unlimited scanscatalog setup-claude --pro --api-key YOUR_KEY
# Per-project instead of globalcatalog setup-claude --project

# Free (local) — data stays on your machinecatalog setup-claude
# Pro (hosted API) — persistent storage, unlimited scanscatalog setup-claude --pro --api-key YOUR_KEY
# Per-project instead of globalcatalog setup-claude --project

After setup, restart Claude Code and try: "Scan my-catalog.xlsx and tell me the biggest issues"

Example JSON Output

json

{  "timestamp": "2026-03-05T10:30:00Z",  "marketplace": "US",  "is_us_marketplace": true,  "total_queries": 14,  "total_issues": 47,  "total_affected_skus": 23,  "results": [    {      "query_name": "missing-attributes",      "description": "Find mandatory attributes missing from listings",      "total_issues": 12,      "affected_skus": 8,      "issues": [        {          "row": 7,          "sku": "ABC-123",          "field": "brand",          "severity": "required",          "details": "Missing required field: brand",          "product_type": "HAIR_STYLING_AGENT",          "extra": {}        }      ]    }  ]}

{  "timestamp": "2026-03-05T10:30:00Z",  "marketplace": "US",  "is_us_marketplace": true,  "total_queries": 14,  "total_issues": 47,  "total_affected_skus": 23,  "results": [    {      "query_name": "missing-attributes",      "description": "Find mandatory attributes missing from listings",      "total_issues": 12,      "affected_skus": 8,      "issues": [        {          "row": 7,          "sku": "ABC-123",          "field": "brand",          "severity": "required",          "details": "Missing required field: brand",          "product_type": "HAIR_STYLING_AGENT",          "extra": {}        }      ]    }  ]}

Agent Integration

Via CLI (subprocess)

python

import subprocess, json
result = subprocess.run(    ['catalog', 'scan', 'my-catalog.xlsx', '--format', 'json',     '--fields', 'sku,severity,details', '--limit', '20'],    capture_output=True, text=True)data = json.loads(result.stdout)

import subprocess, json
result = subprocess.run(    ['catalog', 'scan', 'my-catalog.xlsx', '--format', 'json',     '--fields', 'sku,severity,details', '--limit', '20'],    capture_output=True, text=True)data = json.loads(result.stdout)

Via Python (direct import)

python

from catalog.core import execute_scan, ScanRequest
request = ScanRequest(    file="my-catalog.xlsx",    queries=["missing-attributes", "intent-bullets"],    fields=["sku", "severity", "details"],    limit=20,)response = execute_scan(request)

from catalog.core import execute_scan, ScanRequest
request = ScanRequest(    file="my-catalog.xlsx",    queries=["missing-attributes", "intent-bullets"],    fields=["sku", "severity", "details"],    limit=20,)response = execute_scan(request)

Via MCP

Add the MCP server to any MCP client (Claude Desktop, CLR Pro, etc.) and call catalog_scan, catalog_check, catalog_seller_listing_fetch, catalog_seller_listing_diff, catalog_list_queries, or catalog_schema.

Intent-Based Bullet Optimization

The intent-bullets query evaluates bullet points against COSMO-inspired shopper intent coverage:

Audience / need fit: Who it is for, preferences, or problem state
Function / use case: The job, activity, event, or use flow
Context / compatibility: Where, when, or what it works with
Decision evidence: Specs, attributes, trust signals, or differentiators
All bullets: Checked for intent coverage, length, vague marketing, ALL CAPS

Scores 1-5 with actionable suggestions. The old rufus-bullets query name still works as a deprecated compatibility alias.

Extending with Custom Queries

python

from catalog.query_engine import QueryPlugin
class MyCustomQuery(QueryPlugin):    name = "my-custom-check"    description = "My custom catalog check"
    def execute(self, listings, clr_parser):        issues = []        for listing in listings:            if some_condition:                issues.append({                    'row': listing.row_number,                    'sku': listing.sku,                    'field': 'FieldName',                    'severity': 'warning',                    'details': 'Issue description',                    'product_type': listing.product_type                })        return issues

from catalog.query_engine import QueryPlugin
class MyCustomQuery(QueryPlugin):    name = "my-custom-check"    description = "My custom catalog check"
    def execute(self, listings, clr_parser):        issues = []        for listing in listings:            if some_condition:                issues.append({                    'row': listing.row_number,                    'sku': listing.sku,                    'field': 'FieldName',                    'severity': 'warning',                    'details': 'Issue description',                    'product_type': listing.product_type                })        return issues

Requirements

Python 3.10+
openpyxl
click
rich
pydantic
mcp

How to Get Your CLR

Go to Amazon Seller Central > Catalog > Category Listing Report
Click Generate Report
Download the .xlsm or .xlsx file
Run catalog CLI on it

Free vs Pro

	Open Source CLI	Free API	Pro API ($9.99/mo)
14 quality audits	Yes	Yes	Yes
Scans	Unlimited (local)	2 lifetime	Unlimited
Catalogs stored	—	1	Unlimited
Results persistence	—	7 days	Permanent
API access	—	Yes	Yes
Rate limit	—	10 req/min	100 req/min
Claude Code integration	Local MCP	—	Hosted MCP
Variation Creator	—	—	Coming soon

Get started at catalogcli.com | API Docs

Contributing

This is an open-source project. Contributions welcome!

Add new query plugins
Improve parsing logic
Enhance output formats
Build integrations

License

MIT License - Free to use, modify, and distribute.

Author

Built by Brett Bohannon (@BWB03)

Related Projects

amazon-catalog-auditor-skill - OpenClaw skill for agent workflows
clr-auditor - Original CLR auditing tool
amazon-tool - Amazon variation creator

Agent-native Amazon catalog tool. Built for the future of catalog management.

Source: README.md at commit 1207f6e

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v1.0.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts