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

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.

Centralized gateway for multiple AWS Bedrock models through the Model Context Protocol (MCP), enabling AI agents to interact with 15+ Bedrock models like Nova, Claude, Llama, and Mistral.

Estimates GPU requirements, training/inference costs, and cloud-vs-on-prem TCO for AI workloads using deterministic calculators.

An MCP server that gives LLM agents full access to Amazon DynamoDB, supporting table management, querying, scanning, and item CRUD operations.

Enables LLM agents to control NVIDIA Run:AI infrastructure by dynamically searching and executing over 426 Run:AI APIs through MCP tools.

MCP server for AWS S3 and compatible object stores, enabling LLM clients to browse buckets and fetch objects.

Enables LLM-powered tools to manage Databricks permissions, credentials, and Git credentials via the MCP protocol.

MCP server for interacting with QUADS infrastructure systems via API, enabling resource management and automation through LLM applications.

Enables LLM clients to query AWS CloudWatch Logs and Alarms through MCP tools.

An open-source Model Context Protocol (MCP) server for the Open Telekom Cloud (OTC) Price Calculator API. Expose OTC pricing data to Claude and other LLM clients with full observability.

Enables LLM clients to interact with Azure cost analysis, budget tracking, forecasting, and resource optimization across multiple subscriptions.

A read-only MCP server that lets an LLM inspect an AWS account — list EC2 instances, S3 buckets, IAM users, and cost — with a structural guarantee against any mutations.

Enables LLM clients to run Akamai edge diagnostics (DNS, MTR, curl, error analysis, etc.) and manage support cases via the Model Context Protocol.

Enables AI assistants to execute AWS CLI commands and retrieve service documentation through the Model Context Protocol. It supports Unix pipes for output filtering and provides pre-defined prompt templates for common cloud management tasks.

Enables AI assistants to execute AWS CLI commands and access AWS documentation, resources, and prompt templates through the Model Context Protocol with support for Unix pipes and secure Docker-based deployment.

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.

Provides read-only access to the Cloudera CDP Public Cloud control plane, allowing users to list and describe environments, datahubs, datalakes, DW clusters, virtual warehouses, DE services, ML workspaces, and IAM users via natural language. It uses the installed cdp CLI and supports profiles.

Enables LLM agents to manage Okta organizations through the Okta Admin Management APIs, supporting user provisioning, group management, and more via natural language.

Enables AI assistants to interact with the Databricks platform through 263 tools and 8 prompt templates, covering Unity Catalog, SQL, Compute, Jobs, Pipelines, and more.

Enables LLM clients to browse and manage VCF Automation projects, catalog items, and deployments through MCP tools, including provisioning, day-2 actions, and deleting infrastructure.