"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

Event-sourced world model for multi-LLM agents: propose, validate, and read a shared state.

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

Semantic search over MINDSET's brand strategy topic database, plus its system prompt.

Cross-LLM persistent memory: store context once, recall it from any AI model.

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.

Self-hosted AI prompt library: prompts, collections, tags, teams, chains. 29 MCP tools for agents.

Graph-native persistent memory for AI agents — 33 MCP tools, zero-LLM writes.

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.