AI / ML servers let models interact with ai / ml systems through the MCP protocol. Each entry carries an editorial score, security notes, and per-client connection configs.
Knowledge graph plus vector memory engine for AI agents, exposed as an MCP server with V2 session-aware memory tools (remember, recall, forget, improve) and classic V1 ingestion pipelines (cognify, codify). 100 commits on main in the last 30 days, top cadence in this batch. Three transports (stdio, SSE, Streamable HTTP). 16,965 GitHub stars and a published Apache-2.0 licence.
The most active server in this batch and one of the highest-momentum projects in the entire directory. 100 commits in the last 30 days, 31 releases shipped in 9 weeks since first commit, and a peer-style arXiv preprint backing the architecture. Indexes the Linux kernel (28M LOC, 75K files) in 3 minutes, answers structural queries in under 1ms, and ships as a single static C binary with zero dependencies. SLSA Level 3 attestation bundles ship with every release. Designed for AI coding agents that need persistent code intelligence across sessions: tree-sitter AST parsing across 66 languages plus LSP-style hybrid type resolution for Go, C, and C++. The arXiv preprint (2603.27277) reports the trade-off: 83% answer quality versus 92% for a file-exploration agent, achieved at 10x fewer tokens across 31 real-world repositories. The pitch is the cost-quality curve, slightly lower raw quality at dramatically lower token cost, which matters when agents work in large repositories session after session.
LLM observability platform exposing prompts, projects, traces, spans, sessions, datasets, and experiments through MCP. 100 commits on main in the last 30 days. Published to npm as @arizeai/phoenix-mcp, current 4.0.8. Elastic License 2.0: free to use, host, and modify; downstream commercial competing products are restricted.
Knowledge graph plus vector memory engine for AI agents, exposed as an MCP server with V2 session-aware memory tools (remember, recall, forget, improve) and classic V1 ingestion pipelines (cognify, codify). Three transports: stdio, SSE, Streamable HTTP. 16,965 GitHub stars, Apache-2.0.
High-performance code intelligence MCP server for AI coding agents. Indexes a codebase into a queryable knowledge graph in milliseconds, with 14 MCP tools spanning structural search, call-chain tracing, impact analysis, dead-code detection, and Cypher queries. Single static C binary, 66 languages via tree-sitter, zero runtime dependencies.
LLM observability platform exposing prompts, projects, traces, spans, sessions, datasets, and experiments through MCP. Published to npm as @arizeai/phoenix-mcp, current 4.0.8 (2026-04-29). 9,496 stars on parent monorepo, Elastic License 2.0.
Official Qdrant vector database MCP server. Acts as a semantic memory layer on top of Qdrant: store information with metadata, retrieve via similarity search. Two tools, very small surface area, exceptionally maintained by the Qdrant team. Configurable embedding provider (fastembed default), supports remote and local Qdrant clusters.
Official AWS Labs MCP server for Amazon Bedrock AgentCore: agent runtime, memory, gateway, identity, and observability. Tools fetch curated AgentCore documentation and surface deployment guides for runtime, memory, and gateway resources. Apache-2.0 within awslabs/mcp monorepo (8,924 parent stars).
Vapi.ai voice AI server SDK with MCP server module. Manage voice assistants, trigger outbound calls, and inspect call transcripts. 118 GitHub stars and 14 commits on main in the last 30 days.
Official W&B MCP server for Weights & Biases Models and Weave. Query experiments, runs, sweeps, models, traces, evaluations through MCP. 50 GitHub stars and 13 commits on main in the last 30 days.
Official AWS Labs MCP for Bedrock Knowledge Base retrieval: discover knowledge bases, query with natural language, filter by data source, and rerank results. Apache-2.0 within awslabs/mcp monorepo. Tight tool surface focused on RAG over AWS-managed KBs.
Official ElevenLabs MCP server. Wraps the full ElevenLabs API surface: text-to-speech, voice cloning, speech-to-text, dubbing, sound effect generation, audio isolation, voice design. MIT-licensed, distributed via PyPI as elevenlabs-mcp. Free tier with 10,000 credits per month.
MCP server for Fal.ai. Generate images, videos, music, and audio with the Fal.ai 600+ model catalog from inside agents. 43 GitHub stars and 1 commit on main in the last 30 days.
Official AWS Labs MCP for SageMaker HyperPod cluster management: deployment, node management, lifecycle operations on EKS-orchestrated or Slurm-orchestrated clusters. Read-only by default; --allow-write and --allow-sensitive-data-access flags gate destructive operations.
MLflow MCP server for ML experiment tracking. Query experiments, runs, registered models, and model versions with advanced filtering. 10 GitHub stars and 30 commits on main in the last 30 days. Tier 2 by stars.
Official Pinecone MCP for developer workflows. Lets coding assistants search Pinecone documentation, list and configure indexes, generate code informed by index data, and upsert/query records during dev iteration. Apache-2.0, npm-distributed as @pinecone-database/mcp.
We score a new ai / ml MCP the week it ships. Get the update, plus any re-scores when a server changes enough to move its rating. One email per week maximum.
// Tagged mcp-category-ai-ml · Unsubscribe any time