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.
“TypeScript framework for building AI-powered applications and agents, with built-in MCP server support. From the team behind Gatsby. 23,680 stars and 100 commits on main in the last 30 days.”
INSTALL THIS SERVER
{
"mcpServers": {
"mastra": {
"command": "npx",
"args": [
"-y",
"@mastra/cli",
"mcp"
]
}
}
}
{
"mcpServers": {
"mastra": {
"command": "npx",
"args": [
"-y",
"@mastra/cli",
"mcp"
]
}
}
}
{
"mcpServers": {
"mastra": {
"command": "npx",
"args": [
"-y",
"@mastra/cli",
"mcp"
]
}
}
}
{
"mcpServers": {
"mastra": {
"command": "npx",
"args": [
"-y",
"@mastra/cli",
"mcp"
]
}
}
}
{
"mcpServers": {
"mastra": {
"command": "npx",
"args": [
"-y",
"@mastra/cli",
"mcp"
]
}
}
}
6 TOOLS AVAILABLE
OUR ASSESSMENT
- 23,680 GitHub stars.
- 100 commits on main in the last 30 days.
- Built by the Gatsby team.
- TypeScript-first agent framework.
- Built-in MCP server (no separate package).
- Workflow and eval primitives included.
- License NOASSERTION at inspection (no SPDX-recognised LICENSE file at repo root); Apache-2.0 declared in package.json.
- Framework lock-in versus running standalone tools as MCPs.
- Mastra Cloud is a paid product for hosted runtime.
Local Mastra runtime requires no authentication. Hosted Mastra Cloud requires MASTRA_API_KEY. Agent invocations execute whatever the framework allows; review the agent prompt path before exposing to production.
TypeScript teams building agent applications who want their Mastra runtime exposed to other agents via MCP; multi-agent systems where one Claude/GPT instance orchestrates Mastra-defined agents; eval-driven dev where the framework owns the eval loop.
TECHNICAL DETAILS
ADOPTION METRICS
// Reading this23,680 stars on mastra-ai/mastra. 100 commits on main in the last 30 days.
// Reading thisPairs with Codebase Memory, Cognee, Arize Phoenix, W&B, Langfuse, Pinecone, Qdrant, AWS Bedrock, ElevenLabs, Fal.ai, Vapi, MLflow in ai-ml. Mastra owns the TypeScript-agent-framework slot.
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 | 4.6editorial | 23,680 | — | MAY 8, 2026 |
| PulseMCP | — unrated | unavailable | unavailable | MAY 8, 2026 |
| MCP.so | — unrated | unavailable | unavailable | MAY 8, 2026 |
| Glama | — unrated | unavailable | unavailable | MAY 8, 2026 |
| Smithery | — unrated | unavailable | unavailable | MAY 8, 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).
Engram
Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5 backend, MCP server, HTTP API, CLI, and TUI. 3,341 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.