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

**ColdState Knowledge Search MCP Server** https://github.com/daniel-coldstate/coldstate-mcp Semantic search over 64.6M knowledge entries — the structured alternative to web search APIs and web scraping for LLM agents. No crawling, no rate limits, sub-3s responses. Cloud-hosted at services.coldstate.ai

The world's first named AI prompt quality score. Score, optimize, and compare LLM prompts before they hit any model. Free tier available. Built on PEEM, RAGAS, G-Eval, and MT-Bench frameworks. x402-native on Base.

LLM caching proxy (x402 USDC on Base) - exact + semantic cache. Free health.

Public MCP server for the LLM Search Engine

Unstructured document processing for LLM pipelines. Upload as PDF/DOCX/TXT any supported files, extract structured data (PII-redacted), build LLM-ready datasets, and search/export results — all via MCP tools (document.process, job.status, job.result, dataset.build, dataset.search, dataset.export).

MCP server for German & EU law. Verified, citable legal context for any LLM. Daily updates from official sources, hosted in Germany

MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.

Connect LLM tools to your Algolia account with user-scoped access for internal workflows.

Illumora Craft — evidence-augmented prompt compile for agents via remote MCP (OAuth) or local stdio.

Marketing intelligence API for AI agents. Real campaign data, not LLM guesses.

MCP server providing AI security tools: prompt injection detection, PII scanning, and RAG input validation. Works with Claude, Cursor, and any MCP-compatible client.

Cost-optimized LLM model routing recommendations for autonomous AI agents

NeuralBrain MCP Server - RAG, Vector Memory, LLM Routing, Agent Identity, x402 Payments

Multi-LLM AI Research & Analysis — smart routing, consensus analysis, due diligence reports

MCP memory server with shared team workspaces, typed knowledge chunks (decision, finding, convention, state, question, reference), role-based access, and cross-tool support for Claude, Cursor, and Codex. The only MCP memory server built for engineering teams. Features automatic deduplication, two-layer retrieval (LLM KB selection + hybrid vector/BM25/RRF fusion), a web dashboard with knowledge graph visualization, and attribution tracking. Zero server-side LLM costs.

Manage, version, and publish LLM prompts with blocks, variables, and evaluations.

Semantic memory for AI agents. Store, recall, and forget memories with entity extraction and fact-based retrieval. Self-hostable, privacy-first, works with any LLM.