MCP Servers with a describe_table tool

Every MCP server Pod knows of that exposes a describe_table tool.

8 servers, ordered by decision readiness and adoption — GitHub stars and npm downloads where available, then reported issue volume. Pod has connected to 6 of them; the rest are publisher-reported and unverified.

Anchor

Anchor gives Claude shared artifacts — it can create files and organize them in folders. Read and write files in HTML, Markdown (MD), JSON, CSV and more, design typed tables and query them with SQL. Claude can move files around, make copies and keep everything organized. Every file, table, and folder created is neatly shareable with your team, while Anchor handles storage, permissions, and versioning. Log in once, no API keys, no setup, and let Claude do its magic, only ever touching what you can access.

15 tools reported — Live, but requires authorization before it will list tools. Publisher lists 15 tools.

Collation MCP Server

Collation sets up and manages a dedicated data warehouse for your investment data, then connects Claude directly to it. Your portfolios, positions, transactions, and performance data stay in your own warehouse — Claude queries it in place so you get answers without exporting or moving anything. Ask questions in plain language and Claude will run SQL against your warehouse, pull up dashboards, and reuse your saved queries. Key capabilities:

Run SQL and explore tables across your own data warehouse Calculate time-weighted returns (TWR) for any portfolio or period Access and build on your saved queries and dashboards Browse schema and documentation to understand what's available

Built for wealth managers, analysts, and operations teams who want fast, accurate answers from investment data they fully own and control.

15 tools reported — Live, but requires authorization before it will list tools. Publisher lists 15 tools.

DataSelf MCP+

DataSelf MCP+ connects AI assistants to your DataSelf SQL Server data warehouse, enabling users to explore business data and KPIs using natural language—without writing SQL or Python.

Unlike a basic database connector, DataSelf MCP+ provides access to curated, governed, business-friendly models that consolidate data from multiple operational systems. Rich metadata supplies essential business context, while purpose-built star and galaxy schemas, optimized indexing, and efficient table relationships accelerate queries and reduce unnecessary data retrieval, processing, and AI-token usage. This shared foundation delivers consistent, trustworthy answers across AI assistants—including Claude, Copilot, Gemini, and ChatGPT—and analytics platforms such as Power BI, Tableau, and Excel.

Users authenticate through Microsoft OAuth 2.0, with access limited to their authorized DataSelf entities and data.

Capabilities

Confirm the authenticated user List accessible companies, divisions, and data warehouses Discover available tables, views, schemas, and models Retrieve table and field metadata Run read-only SQL SELECT queries and return results Reject writes, DDL, and multi-statement requests

5 tools reported — Live, but requires authorization before it will list tools. Publisher lists 5 tools.

Loam Data

Loam is the database for Claude. Add the business data you already have, then ask questions in plain English and get answers grounded in real rows.

Upload CSV, Excel, Parquet, TSV, and JSON files, or connect supported data sources. Claude can use Loam to analyze revenue, pipeline, campaigns, operations, and other business data without relying on pasted snapshots or prebuilt dashboards.

Ask questions such as: • Which region had the highest revenue last quarter? • What changed most between this month’s export and last month’s? • Which products have the highest return rate?

You stay in control. When connecting Claude, you choose the Loam account it will use. Loam checks that account’s current permissions whenever Claude asks a question, so Claude can access only the data that account is allowed to use.

Loam is built for founders and teams that want useful answers from their business data without waiting for a data team.

16 tools reported — Live, but requires authorization before it will list tools. Publisher lists 16 tools.

Optilogic

Make faster, better tactical decisions within the supply chain you have today and design the supply chain you need for tomorrow. Optilogic connects Claude to a platform that does both. Work with a live digital twin of your current supply chain powered by agentic AI that combines mathematical optimization, simulation, and demand modeling to support decisions across the full horizon, from day-to-day operational response to long-term network, transportation, inventory, and production strategies.

• Run what-if scenario analysis on network design and sourcing models
• Analyze demand at the SKU and location level, and trace how it's served across your network
• Answer strategic and tactical routing questions to drive cost savings and service level improvements
• Place safety stock across your full network and see what it costs to hit a given service level
• Score risk across your network: single-source dependencies, demand/facility/supplier concentration, geographic exposure, capacity, and transport-time risk, so you know where to focus before a disruption
• Model the impact of tariff scenarios
• Design and compare network strategy across sourcing, manufacturing, distribution, and nearshoring scenarios
• Stress-test a plan against real-world variability such as demand swings, delayed lead times, and capacity shocks
• Compare multiple scenarios, sensitivity analysis at-scale, with output and critical insights auto-generated
• Translate optimization model outputs into decision-ready formats for planners, finance, and executives

Best for: S&OP/IBP leaders, network design teams, transportation teams, supply chain modelers and analysts, operational planners as well as executives who want a straight answer to a "what if" question without needing modeling expertise.

Requires a free or paid Optilogic account. You will be redirected to Optilogic to sign in and authorize access. Your data and models stay secure and isolated in your own account.

37 tools reported — Live, but requires authorization before it will list tools. Publisher lists 37 tools.

Rippit

Find out what your customers are actually telling you. Rippit reads every support ticket, call, and chat transcript in full - not summaries - so you can surface the themes driving your volume, quantify what they’re costing you, and back every finding with the customer’s own words.

23 tools reported — Live, but requires authorization before it will list tools. Publisher lists 23 tools.

citytracker.ai

This provides access to the data tracked by CityTracker.ai, which is overwhelmingly public data obtained via NYC or NY State public data portals.

4 tools reported — Publisher-reported; not verified by Pod.

Microsoft Dataverse

Connect AI assistants to Microsoft Dataverse to query, create, update, delete, and search data in Dataverse.

11 tools reported — Publisher-reported; not verified by Pod.

For agents

This page has a Markdown and a JSON twin. Pod is also queryable over MCP at https://api.askpod.ai/mcp/read.