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

Validates MLCommons Croissant dataset metadata (JSON-LD) for schema compliance, as a stateless MCP server.

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 AI agents to turn raw or loosely formatted screenplay text into professionally structured screenplay blocks and typeset plain text on fixed CJK or Latin character grids, with deterministic scene analysis, shootability diagnostics, and Fountain conversion. It runs locally with no account, key, quota, or network calls.

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.

An MCP server for the Hugging Face Dataset Viewer API that enables searching, fetching, and filtering datasets on the Hugging Face Hub. It allows users to explore schemas, perform full-text searches, and analyze dataset statistics through natural language.

Enables querying, filtering, and summarizing datasets from the jayjex Data Vault without downloading files.

Enables AI clients to list, inspect, triage, and update support tickets via MCP tools, with a mocked dataset designed for swapping in real ticket sources later.

Enables dataset curation by removing duplicate entries, rebalancing class distributions, and detecting and removing poisoned or malicious entries.

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

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 interaction with the Hugging Face Dataset Viewer API, allowing users to browse, search, filter, and analyze datasets hosted on the Hugging Face Hub.

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.

Enables an ElevenLabs support agent to call support tools over MCP, including Discord ticket flows, post-call webhook handling, and knowledge-base syncing.

Unified MCP server for discovering open datasets across Hugging Face, Zenodo, and Kaggle, with ranked search results and one-click Colab starter code generation.

Enables AI assistants to search, read, and explore thousands of public datasets from Chile's open government data portal (datos.gob.cl) without requiring an API key.

Enables collection, enhancement, and quality scoring of authentic Amharic datasets, with integration for AI models like Gemini and Qwen.

Enables AI harnesses to maintain a persistent memory layer backed by a local SQLite file, providing MCP tools to add, search, deprecate, and synchronize facts without deleting history.

Enables an AI operator to create consent-based remote support sessions on Windows PCs, run PowerShell commands, and upload or download files through an audited, self-terminating MCP relay.

Provides offline access to a static snapshot of 28 Superteam Earn bounty listings with full description text, enabling instant listing lookup, keyword search, and reward/deadline stats without any network calls at runtime.

An MCP server that searches HuggingFace/Kaggle for datasets, detects their domain, and generates a matching preprocessing script. It turns natural-language dataset queries into runnable, domain-aware preprocessing pipelines.

Enables natural language querying and semantic search over a bilingual customer support ticket dataset using SQL and embeddings.

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.

MCP server for Google Cloud Support API v2. Provides tools for managing Google Cloud support cases through AI assistants.

A local stdio MCP server that brings scattered tickets, transactions, and current policies together so a model can retrieve evidence, assess cases, and prepare reply and escalation drafts. All writes stay local and pending human review, with no ability to send messages, move money, change accounts, or publish content.

Enables read-only lookup of support tickets and ticket lists through two tools, returning only bounded fields like ID, status, title and note. Tenant filtering and argument validation confine every read to the configured organization, with denied access and upstream failures surfaced as explicit results.

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