AI & ML MCP servers
Agents calling other models: embeddings, image generation, transcription, and specialized inference. Useful when one assistant orchestrates and the heavy lifting happens in purpose-built models behind these servers.
What engineers use them for
- Generate embeddings and query vector stores
- Hand off transcription or image work mid-task
- Chain a specialist model into a larger workflow
- Evaluate outputs with a second model as judge
Highest-graded right now
Graded on maintenance, completeness, and reliability. The formula is public →Ai Netcafe
23 agent tools + a measured per-call model cost dataset.
Claude Flow
AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Codebase Memory
Codebase knowledge graph for AI agents — 159 languages, sub-ms queries, 99% fewer tokens.
Serena MCP: the IDE for your agent
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.
Agent Skills Search Server
Search and discover Agent Skills from the skills.sh registry.
Mockserver
Mock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.
agent-deviceNew
Let AI agents inspect, control, and debug real iOS, Android, desktop, and TV apps
