"Writing about MCP" matching MCP servers:

Enables asking natural-language questions about three published data builds (housing, flights, and a fictional bank), with the agent finding tables, writing SQL, and re-verifying every number against the warehouse before returning an answer.

An MCP server that connects Claude to Teradata GCFR operational reporting, enabling natural-language queries about stream status, process history, loads, transforms, errors, SLA, and data lineage without writing SQL.

Gives AI agents governed context about a data warehouse — table meaning, ownership, lineage, freshness, and PII flags — plus read-only, row-limited, PII-protected querying across DuckDB, Snowflake, and Databricks. Guardrails enforced at parsing, connection, and result layers keep agents from writing, running away, or leaking personal data.

Enables Claude Desktop to connect directly to Elasticsearch clusters for intelligent log analysis through natural language queries. Users can ask questions about their logs in plain English and get actionable insights without writing complex Elasticsearch queries.

An MCP server that gives models semantic context about a data warehouse, including table meaning, units, lineage, and health, to reduce guessing.

Enables AI agents to answer analytical questions about an online store's SQLite database through specialized read-only tools, without any risk of modifying the underlying data.

Enables Claude to run read-only SQL queries against the DWH.facturas table in SQL Server, including discovering its columns and asking natural-language questions about invoice data.

Lets AI assistants like Cursor and Claude safely explore your database and answer questions about your data in plain English.

MCP server for AppFolio property management data, providing six catalog-backed tools to discover, describe, and run reports (Reporting API) and call endpoints (Database API) for reading and writing property management records.

Enables users to answer California drinking water questions about public water systems, SAFER risk/violation status, source-water chemistry, school lead sampling, and latest tap/treated-water results by ZIP code or water system ID, using curated Databricks Gold views over State Water Board open data.

MCP server to ask research questions about real-world datasets and get actual database records back, with auto-registration and trial credit.

Enables Claude to answer business questions about stock, orders, customer balances, overdue orders and KPIs from live ERP data using fixed, parameterized read-only queries, with bounded results and every call logged to an audit trail.

Provides read-only Arknights intelligence over MCP, enabling structured queries about stages, enemies, operators, and modules with region tagging and evidence-backed analysis. It uses versioned SQLite snapshots and never fetches upstream data at query time.

FactQL is the harness around the model: ask a question about your data and it runs the query, checks the result before you see an answer, and declines instead of guessing when it can't verify. Every answer ships with the query that ran, the rows it returned and the lineage behind it.

MCP server for Azure Cosmos DB enabling listing accounts, databases, containers, running SQL queries, and reading/writing/deleting documents.

A static, read-only MCP server that exposes a database knowledge base (schema, relationships, workflows, and reasoning patterns) so Claude Code / Copilot can reason about a database without a live connection.

Enables reading and writing the rollekino.fi film archive, including search, film details, stats, and reviews with personal 1-10 ratings alongside IMDb and Metascore.

Enables answering statistical questions about a large Goodreads dataset in BigQuery using aggregate-only tools, with built-in guards and caveats that prevent users from getting misleading numbers from known data defects.

MCP server for Durable energy trading analytics that connects Claude Desktop to Snowflake data, enabling natural-language queries about spreads, constraints, generators, and prices.

Enables LLMs to answer small business finance questions about spending, sales trends, cash flow projections, and profitability using a local SQLite database.

Enables reading and writing WiseGrid sheets, including listing sheets, paginating rows, adding and updating records, and running reports, all from an MCP client with API key authentication.

Gives language models a working connection to Apache Jena Fuseki: SPARQL queries and updates, whole named-graph reads and writes over the Graph Store Protocol, bulk RDF loading from a sandboxed directory, and dataset administration such as listing, creating, backing up and compacting datasets. Named graphs are also exposed as MCP resources, and a read-only mode hides the seven writing tools.

Exposes a governed semantic layer to AI agents so they select metrics and dimensions from a closed, engineer-declared vocabulary instead of writing SQL. Validates every typed call against the contract, rejects out-of-contract requests with structured errors and suggestions, and returns query rows together with the compiled SQL and dbt lineage for auditing.

Exposes five protocol-level tools to any MCP host: converting Chinese/English descriptions into booru tags and retrieving safe-rated illustrations with a graceful relaxation ladder, looking up defense team compositions from a local arena service, querying a read-only local SQLite memory store, and probing local service availability. Returns structured fields such as relaxed, attempt, score, and rating so hosts can retry or reason about results instead of guessing.

Enables an LLM to answer questions about Colombian public procurement from the SECOP II electronic contracts open dataset on datos.gov.co, with typed queries that are built into SoQL by the server. A column allowlist and local entity directory keep personal-data fields unreachable and resolve institution names to NITs, so users get aggregate contract figures without writing queries themselves.

Enables answering natural-language questions in Spanish about a PostgreSQL auto parts inventory — which parts fit a vehicle, prices, stock per branch and sales movements — through four read-only tools exposed over stdio to an MCP client such as Claude Code. Writes are prevented by multiple independent security layers, including a read-only database role.

Enables AI agents to query years of Spotify listening history stored in a music-warehouse Worker, answering questions about individual plays, top artists and tracks, daily counts, era stats, and Wrapped-style summaries, plus live now-playing and Spotify top data when the Worker's Spotify grant is active. It runs locally over stdio using a read-only token and exposes fourteen read-only tools.

An MCP server that caches your GitHub starred repositories in a local SQLite database and lets you search, list, and retrieve details about them through any MCP client (Claude Desktop, Cursor, VS Code, etc.), with automatic freshness checks via GitHub's ETag mechanism.

A Model Context Protocol server that lets LLM clients answer business questions in natural language over a Databricks dataset without writing SQL by hand.

A basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across chats.

The official Model Context Protocol (MCP) server for SeaTable, built and maintained by SeaTable GmbH. It lets AI agents interact with data in your bases — reading, writing, searching, linking, and querying rows through a focused set of tools. The server intentionally focuses on data operations, not schema management (creating/deleting tables or columns), keeping the tool set lean and safe for auto

A database-agnostic MCP server that enables natural language queries to your database through Claude or Copilot, automatically writing and executing SQL.

A universal resource server that enables AI models to mount local folders, scrape web pages into Markdown, and query SQLite databases without writing code. It features a real-time TUI dashboard and persistent configuration for managing diverse knowledge sources.

A read-only Model Context Protocol server that lets an AI agent answer questions about unit balances, overdue fees and common-area bookings for the signed-in user. Row Level Security and a read-only database role scope every answer to that person's building and unit, so staff, residents and other tenants see only what they are allowed to see.

Agent-native semantic layer, letting AI agents query databases through specifying intent instead of writing SQL, then compiling structured queries into correct, dialect-aware SQL. Dynamic and expressive, supporting multi-stage queries, time-shifts, and complex join schemas.

A private location archive with an MCP server, letting an agent answer questions about your past stays, trips, cities, and travel stats from data in your own Postgres.

Enables AI agents to list metrics and dimensions, inspect definitions, and run governed metric queries against Apache Iceberg tables through a semantic layer, without writing SQL or accessing raw rows or columns outside their role.

Enables MCP clients to interact with a Mudbase project by listing and querying collections, reading and writing documents, searching across the project, and managing files in storage.

Provides governed, deterministic SQL tools over DuckDB for querying sales pipeline data, returning verified results with full source traces. Enables trustworthy natural-language queries about Q1 2026 sales data.

Data-first MCP server for reading and writing spreadsheets (.xlsx, .csv, .ods) - cell-level ops + DuckDB SQL engine.