"Informational MCP Servers with Croissant Dataset Format Support" matching MCP servers:

MCP server that gives Claude programmatic access to a local En Croissant chess opening trainer, enabling conversational opening prep by reading its SQLite database, PGN files, and Lichess API. It supports repertoire review, due cards, and opponent statistics directly from chat.

Enables an AI assistant to search real card data, check legality and points, validate or save decks, pull rulings, and review tournament meta for TCG Advanced and Genesys. It exposes tools for card search, archetype lookup, deck validation, meta snapshots, and optional turn-1 line search.

Enables version-controlled golden dataset management and semantic evaluation for RAG/LLM pipelines using TF-IDF cosine similarity, without requiring an LLM API key.

Enables querying JSON/JSONL social datasets in Claude Desktop via MCP tools, using DuckDB as the backend database.

Enables AI clients to explore and analyze CSV datasets via tools for dataset overview, statistical summaries, missing value analysis, duplicate detection, correlation analysis, and outlier detection.

Enables AI assistants to work with Chapel code, including compiling, linting, and accessing educational primers.

MCP server for generating negative-space print supports for 3D models (STL/OBJ/STEP) via the negative.support API.

Enables an AI agent to act as first-line customer support on top of Microsoft Dynamics 365 / Dataverse, reading incoming synced emails, looking up contacts and published knowledge articles, and drafting HTML-safe replies or escalating to a human as a Case. Runs draft-only by default with safeguards against prompt injection, duplicate replies, and unsafe recipients.

Manages the state of a chess game for LLMs/agents without suggesting moves, providing tools to create/reset game, add moves, get status, and check legality.

Provides customer lookup, transaction history, knowledge-base search, and ticket management tools to any MCP client.

Enables Claude to manage customers and support tickets through database-backed CRUD tools, contextual customer and knowledge resources, and a reusable ticket-triage prompt.

A production-ready TypeScript MCP (Model Context Protocol) server for Cisco Support APIs with comprehensive security and dual transport support. This extensible server provides access to multiple Cisco Support APIs including Bug Search, Case Management, and End-of-Life information.

Enables agents to run support workflows across Gmail, Linear, Stripe, Slack, Notion and other apps — turning support email into tracked bugs with drafted replies, handling refunds end to end, and replying in-thread once issues are fixed.

MCP server for AI-native L1 support: triages tickets, answers from a knowledge base, escalates to L2 via Telegram/GitHub, and manages feedback, with a LangGraph workflow and safety guardrails.

An MCP server that enables LLMs to automate browser interactions using Playwright to fetch real-time Israeli weather data.

Enables local, deterministic management and search of point-of-sale support data—branches, terminals, incidents, and incident history—with read-only queries and mutating tools over stdio using simulated SQLite data.

Six local CPU MCP tools for Markdown/HTML-to-PDF conversion, PDF text extraction, safe SVG-to-PNG rendering, and PDF link and chapter inspection. Linux/WSL2; no GPU, hosted inference API, or model download required.

Enables exploratory data analysis and machine learning on CSV datasets with tools for profiling, missing values, correlation, plotting, model training, and prediction.

This MCP server enables users to interact with and analyze the dair-ai/emotion dataset from Hugging Face containing labeled Twitter messages. It provides tools to sample data, search text, and perform statistical analysis on emotion distributions.

Enables searching and retrieving Knowledge Base articles from the Broadcom Support Portal for products like VMware, Tanzu, and Cybersecurity. Users can perform documentation searches and fetch specific articles in Markdown format via the SearchUnify API.

A minimal MCP server that exposes a run_command tool over stdio, enabling command execution within a Docker container.

Enables AI assistants like Cursor to manage customer support tickets in SQLite through MCP tools, supporting creation, retrieval, search, and updates via natural language.

Provides access to Deutsche Bahn's timetable data through MCP, enabling real-time train schedules, station search, and change tracking for German railway stations.

Evaluate cryptocurrency Shariah compliance under AAOIFI standards. Real-time Halal/Haram screening and scholarly justifications for 820+ assets.

Protects AI support tools with Descope JWT authentication and scope-based authorization, enabling secure customer support operations like refunds with granular access control.

Enables LLMs to read and write local user data, generate fake users via sampling, and interact with structured prompts and resources.

An MCP server that integrates Alibaba's DashScope platform, providing AI chat tools and resource access through both standard stdio and a web-based interface. It allows users to interact with DashScope large models within the Model Context Protocol ecosystem using TypeScript.

Enables language models to fetch weather forecasts for Israeli cities by automating a real browser with Playwright to interact with weather2day.co.il, including entering a city, selecting it from autocomplete, and extracting the forecast content.

Exposes the customer-support tool registry over stdio so Claude Desktop or Claude Code can look up customers and orders, track shipments, search help-center articles, update shipping addresses, issue policy-checked refunds and escalate to a human. It reuses the same pydantic validation, ownership and refund policy, approval gate and audit logging as the HTTP agent, with the customer identity taken from server configuration rather than the model.

Enables fetching weather forecasts for Israeli cities by controlling a headless browser via Playwright, instead of using a conventional weather API.