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).
“Official AWS Labs MCP server for Amazon Bedrock AgentCore: agent runtime, memory, gateway, identity, and observability. Tools fetch curated AgentCore documentation, retrieve documents by URI, and surface deployment guides for runtime, memory, and gateway resources. 13 commits on the server path in the last 30 days within the awslabs/mcp monorepo. Apache-2.0 official-vendor signal.”
INSTALL THIS SERVER
{
"mcpServers": {
"awslabs.amazon-bedrock-agentcore-mcp-server": {
"command": "uvx",
"args": [
"awslabs.amazon-bedrock-agentcore-mcp-server@latest"
]
}
}
}
{
"mcpServers": {
"awslabs.amazon-bedrock-agentcore-mcp-server": {
"command": "uvx",
"args": [
"awslabs.amazon-bedrock-agentcore-mcp-server@latest"
]
}
}
}
{
"mcpServers": {
"awslabs.amazon-bedrock-agentcore-mcp-server": {
"command": "uvx",
"args": [
"awslabs.amazon-bedrock-agentcore-mcp-server@latest"
]
}
}
}
{
"mcpServers": {
"awslabs.amazon-bedrock-agentcore-mcp-server": {
"command": "uvx",
"args": [
"awslabs.amazon-bedrock-agentcore-mcp-server@latest"
]
}
}
}
{
"mcpServers": {
"awslabs.amazon-bedrock-agentcore-mcp-server": {
"command": "uvx",
"args": [
"awslabs.amazon-bedrock-agentcore-mcp-server@latest"
]
}
}
}
5 SELECTED TOOLS
OUR ASSESSMENT
The amazon-bedrock-agentcore-mcp-server lives in the awslabs/mcp monorepo and ships as a Python package via uv. The tool surface is documentation-and-guidance focused: search_agentcore_docs and fetch_agentcore_doc cover the curated AgentCore documentation set; manage_agentcore_runtime, manage_agentcore_memory, and manage_agentcore_gateway return deployment guides covering CLI workflow, code patterns, and troubleshooting steps. AWS Labs maintains the parent monorepo with 77 commits across all servers in the last 30 days; the AgentCore server itself shows 13 commits on its path.
- 13 commits on the server path in the last 30 days inside the awslabs/mcp monorepo.
- Apache-2.0 licence.
- Official AWS Labs maintenance with 8,924 parent-repo stars.
- Tool surface targets practitioner workflows: documentation search, full document fetch, and curated deployment guides for runtime, memory, and gateway resources.
- Consistent uv-based install across all awslabs/mcp servers.
- Five-client config coverage (Claude Desktop, Claude Code, Cursor, VS Code, Windsurf) supported by the awslabs/mcp install instructions.
- Tool surface is documentation and guidance, distinct from runtime control plane operations against a live Bedrock account; for actual AgentCore deployment use the Bedrock CLI or AWS console.
- Requires an AWS account with Bedrock AgentCore access (currently in preview in some regions).
- Monorepo structure means version pinning is at the package level (awslabs.amazon-bedrock-agentcore-mcp-server), distinct from the parent repo git tags.
The server fetches public AgentCore documentation and returns deployment guidance text. It carries no AWS credentials and makes no calls to live Bedrock APIs. The security boundary is confined to outbound HTTP fetches against curated AgentCore documentation URLs.
Teams deploying agents on Amazon Bedrock AgentCore who want documentation-aware assistance directly inside Cursor, Claude Code, or VS Code; operators evaluating AgentCore Runtime, Memory, or Gateway who want a guided walkthrough generated on demand; AWS shops running production agents and looking for an official-vendor MCP source for AgentCore deployment patterns.
TECHNICAL DETAILS
RECORDED ADOPTION METRICS
Saved directory snapshots. Record last checked MAY 1, 2026. The review date above does not refresh these figures.
// Recorded note8,924 stars on the awslabs/mcp parent monorepo. 13 commits on the AgentCore server path in the last 30 days carry the editorial weight.
// Recorded noteThird-ranked in ai-ml. Official AWS Labs vendor signal balances against documentation-only tool surface.
SOURCES & RECORDED CHECKS
These are the directory listings and check details held in this record. Client compatibility, directory listings and installation testing are separate signals. Recorded client names describe the scope of a check; they do not establish a security assessment or a recurring test schedule.
The same server, 5 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 | 4.4editorial | 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 |
| Smithery | — 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.
HeyGen Hyperframes
Write HTML, render video. Built for agents. HeyGen's framework that turns HTML templates into video output via MCP. 16,400 GitHub stars and 100 commits on main in the last 30 days.
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.
Mastra
TypeScript framework for building AI-powered applications and agents, with built-in MCP server support. From the team behind Gatsby. 23,680 GitHub stars and 100 commits on main in the last 30 days.
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.