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.
INSTALL THIS SERVER
{
"mcpServers": {
"hyperframes": {
"command": "npx",
"args": [
"-y",
"hyperframes"
],
"env": {
"HEYGEN_API_KEY": "YOUR_HEYGEN_KEY"
}
}
}
}
{
"mcpServers": {
"hyperframes": {
"command": "npx",
"args": [
"-y",
"hyperframes"
],
"env": {
"HEYGEN_API_KEY": "YOUR_HEYGEN_KEY"
}
}
}
}
{
"mcpServers": {
"hyperframes": {
"command": "npx",
"args": [
"-y",
"hyperframes"
],
"env": {
"HEYGEN_API_KEY": "YOUR_HEYGEN_KEY"
}
}
}
}
{
"mcpServers": {
"hyperframes": {
"command": "npx",
"args": [
"-y",
"hyperframes"
],
"env": {
"HEYGEN_API_KEY": "YOUR_HEYGEN_KEY"
}
}
}
}
{
"mcpServers": {
"hyperframes": {
"command": "npx",
"args": [
"-y",
"hyperframes"
],
"env": {
"HEYGEN_API_KEY": "YOUR_HEYGEN_KEY"
}
}
}
}
6 SELECTED TOOLS
OUR ASSESSMENT
heygen-com/hyperframes is HeyGen's framework for rendering HTML templates as video. Tool surface covers render submission, template discovery, preview generation, render-job status tracking, render listing, and export. Pairs with Fal.ai (image/video gen) and Vapi (voice AI) in ai-ml; Hyperframes covers the HTML-to-video slot uniquely.
- 16,400 GitHub stars.
- 100 commits on main in the last 30 days.
- HeyGen official maintenance.
- Apache-2.0 license.
- HTML-to-video pipeline is unique among ai-ml MCPs.
- HeyGen account required; render time and credits cost money at scale.
- render_video carries per-second compute cost; agent prompt path needs review.
- HTML-to-video output limits depend on plan tier.
HEYGEN_API_KEY is account-scoped. Use a dedicated workspace for agent flows. render_video can submit any HTML; review the agent prompt path to avoid rendering content with embedded credentials or PII.
Marketing-video pipelines where the agent generates HTML and renders to video; product demo flows where the agent assembles slides programmatically; localization where the agent translates copy and re-renders the video.
TECHNICAL DETAILS
RECORDED ADOPTION METRICS
Saved directory snapshots. Record last checked MAY 9, 2026. The review date above does not refresh these figures.
// Recorded note16,400 stars on heygen-com/hyperframes. 100 commits on main in the last 30 days.
// Recorded notePairs with Fal.ai, Vapi, ElevenLabs, Pinecone, Qdrant, Mastra, Engram in ai-ml. Hyperframes owns the HTML-to-video slot.
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 | 4.6editorial | 16,400 | — | MAY 9, 2026 |
| PulseMCP | — unrated | unavailable | unavailable | MAY 9, 2026 |
| MCP.so | — unrated | unavailable | unavailable | MAY 9, 2026 |
| Glama | — unrated | unavailable | unavailable | MAY 9, 2026 |
| Smithery | — unrated | unavailable | unavailable | MAY 9, 2026 |
| Official MCP Registry | — unrated | unavailable | unavailable | MAY 9, 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.
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.
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).
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.