"Créer des systèmes de prompt pour les modèles de langage (LLM)" matching MCP servers:

MCP server to interact with Cleyrop work data: browse, search, read file content, and manage files/folders.

A governed MCP server enabling LLM agents to query BigQuery, inspect GCS, trigger Airflow DAGs, and run data-quality checks with built-in security guardrails like allow-lists, cost ceilings, and audit trails.

Local MCP server for the Jedox OLAP platform enabling LLM clients to interact with Jedox databases, dimensions, cubes, cells, and rules via natural language.

Enables AI agents to safely query and explore Apache Impala clusters with read-only SQL, metadata, statistics, cluster overview, and analysis prompt templates.

Enables LLM clients to access scheduling data, KPIs, routes, and trigger optimization algorithms via MCP.

Enables users to convert structured data into Token-Oriented Object Notation (TOON) to reduce LLM token usage and costs by up to 70%. It provides tools for encoding, decoding, and analyzing data formats like JSON, CSV, and XML to optimize prompt efficiency.

Converts JSON data to TOON (Token-Oriented Object Notation) format and back, reducing token usage by 30-60% for more efficient LLM applications.

An MCP server for data reconciliation between MySQL and Snowflake, enabling LLM agents to validate data integrity during migrations and ETL processes.

It interacts with the Kaggle API to provide tools for searching and downloading datasets, and a prompt for generating EDA notebooks.

Enables LLM agents to load, explore, and analyze CSV and Excel files using DuckDB, with tools for SQL querying, statistical analysis, expense optimization, and anomaly detection.

JSON repair & validation MCP server for AI agents: fixes malformed JSON (trailing commas, truncation, etc.) and validates/coerces against a JSON Schema, with deterministic free tier and paid LLM-fallback.

Exposes Iceberg-backed ontology objects, links, and actions as typed MCP tools for LLM agents, enabling governed data access and operations without raw SQL.

MCP server for analyzing China's 福彩3D lottery data with deterministic math engines, forward-testing, and safety checks. Enables data import, statistical testing, coverage optimization, risk control, and optional LLM interpretation.

A Model Context Protocol (MCP) server that keeps the books for your personal and business finances using double-entry accounting — driven entirely from an LLM.

Enables MCP tools to exchange large outputs by reference, keeping bulky data out of LLM context while allowing direct piping between tools.

Provides a runtime-only MCP server and REST API for datasets, connections, flows, pipelines, and cron scheduling, without server-side LLM execution or entity-authoring admin UI, enabling clients to operate and manage these resources programmatically.

Deterministic bank-statement parsing for AI agents: messy CSV/OFX exports to clean, categorized ledger rows. In-memory only, no storage, no external calls, no LLM in the loop.

Enables LLM agents to interact with Apache Zeppelin notebooks via the Zeppelin REST API, supporting operations like listing, searching, editing, and running notebooks.

Enables LLM clients to analyze and interact with Power BI (.pbix) files, providing access to data models, DAX measures, Power Query code, table relationships, and data contents through natural language.

An MCP server that exposes Azure Data Factory operations as tools any LLM can call — trigger pipelines, monitor runs, inspect datasets, and get factory health summaries through natural language.