Amazon SageMaker AI MCP
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.
“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. 2 commits on the server path in the last 30 days, the lowest cadence in this batch; Tier 2 placement reflects the cadence.”
INSTALL THIS SERVER
{
"mcpServers": {
"awslabs.sagemaker-ai-mcp-server": {
"command": "uvx",
"args": [
"awslabs.sagemaker-ai-mcp-server@latest"
],
"env": {
"AWS_PROFILE": "default",
"AWS_REGION": "us-east-1"
}
}
}
}
{
"mcpServers": {
"awslabs.sagemaker-ai-mcp-server": {
"command": "uvx",
"args": [
"awslabs.sagemaker-ai-mcp-server@latest"
],
"env": {
"AWS_PROFILE": "default",
"AWS_REGION": "us-east-1"
}
}
}
}
{
"mcpServers": {
"awslabs.sagemaker-ai-mcp-server": {
"command": "uvx",
"args": [
"awslabs.sagemaker-ai-mcp-server@latest"
],
"env": {
"AWS_PROFILE": "default",
"AWS_REGION": "us-east-1"
}
}
}
}
{
"mcpServers": {
"awslabs.sagemaker-ai-mcp-server": {
"command": "uvx",
"args": [
"awslabs.sagemaker-ai-mcp-server@latest"
],
"env": {
"AWS_PROFILE": "default",
"AWS_REGION": "us-east-1"
}
}
}
}
{
"mcpServers": {
"awslabs.sagemaker-ai-mcp-server": {
"command": "uvx",
"args": [
"awslabs.sagemaker-ai-mcp-server@latest"
],
"env": {
"AWS_PROFILE": "default",
"AWS_REGION": "us-east-1"
}
}
}
}
6 TOOLS AVAILABLE
OUR ASSESSMENT
- Apache-2.0 licence.
- Official AWS Labs maintenance with 8,924 parent-repo stars.
- Read-only default with explicit --allow-write opt-in.
- Stack Protection guards against cross-tool CloudFormation stack mutation.
- Configurable AWS profile and region via standard environment variables.
- 2 commits on the server path in the last 30 days, lowest cadence in this batch.
- HyperPod is the only SageMaker surface covered; full SageMaker control-plane operations live elsewhere.
- File system access is broad (the README documents this as a security consideration): the server can read and write any path the host user can.
- Designed for local stdio use; HTTP transport carries additional risk per the README.
The server defaults to read-only mode. Open --allow-write only for sessions where cluster mutation is intended. Open --allow-sensitive-data-access only when access to sensitive HyperPod data is required. Run under a dedicated AWS profile with HyperPod-scoped IAM permissions. The host file system is accessible to the server; scope the agent filesystem accordingly. The README warns against network exposure of this server.
ML platform teams running SageMaker HyperPod for distributed training jobs; AWS shops where training infrastructure runs inside SageMaker for compliance and IAM unification with the rest of the AWS workload; operators who want a guarded MCP entry point for HyperPod cluster operations (read-only by default; explicit flags for write paths).
TECHNICAL DETAILS
ADOPTION METRICS
// Reading this8,924 stars on the awslabs/mcp parent monorepo. 2 commits on the SageMaker AI server path in the last 30 days.
// Reading thisFifth-ranked in ai-ml. Tier 2 cadence; Tier 1 vendor signal.
SOURCES & VERIFICATION
We don't take any single directory's word for it. Before scoring, we cross-reference 4 public MCP sources, install the server ourselves against the clients we cover, and record when we last re-verified.
The same server, 4 different lenses. We reconcile these signals into our editorial score, which is why our number sometimes diverges from a directory-aggregate star count.
| Source | Their rating | Their star count | Their downloads | Last synced |
|---|---|---|---|---|
| AutomationSwitch This page | 3.9editorial | 8,924 | — | MAY 1, 2026 |
| PulseMCP | — unrated | unavailable | unavailable | MAY 1, 2026 |
| MCP.so | — unrated | unavailable | unavailable | MAY 1, 2026 |
| Glama | — unrated | unavailable | unavailable | MAY 1, 2026 |
| Official MCP Registry | — unrated | unavailable | unavailable | MAY 1, 2026 |
// Counts are directory-reported; we don't adjust them. Discrepancies usually come from different snapshot times or star-caching.
OTHER AI / ML MCP SERVERS
Cognee MCP
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.
Codebase Memory MCP
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.
Arize Phoenix MCP
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.
Qdrant MCP Server
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.
Amazon Bedrock AgentCore MCP
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).
ElevenLabs MCP
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.
DISCUSS YOUR
MCP REQUIREMENTS.
Evaluating a server, scoping an internal deployment, or working out whether MCP is the right fit at all. Start the conversation and we will point you at the right piece of the ecosystem.