cerase-media MCP
Provides multimodal understanding tools including OCR, image description, audio transcription, UI screenshot analysis, and screenshot comparison via async tools on a multimodal endpoint.
README
cerase-media MCP
First-party multimodal understanding (M-MEDIA-1 = the merge of the former
cerase-ocr + cerase-transcriber): five async tools over the
multimodal tool-model alias through cerase-litellm, billed per-agent.
The last two (analyze_ui, compare_screenshots) are the UX/UI screenshot
pair added by M-CERASE-MEDIA-UX — same multimodal endpoint, specialised
prompts, no extra dependency.
| Tool | Question it answers | Returns |
|---|---|---|
ocr |
what is WRITTEN in this image? | {text, model} |
describe_image |
what does this image SHOW? | {description, model} |
transcribe |
what does this audio say? | {text, model} |
analyze_ui |
what's in this UI screenshot? — structured audit of layout, typography, colours, interactive elements, text, visual errors, accessibility, consistency | {analysis, model} |
compare_screenshots |
what changed between two screenshots? — before/after visual diff (layout / text / style / new / removed / regressions) | {diff, model} |
Image input is accepted three ways (pick one): path (a file under
CERASE_TOOL_WORKSPACE_ROOT), image_url, or image_base64.
compare_screenshots takes the two-image variants (path1/image1_url/
image1_base64 and path2/…).
Async by design: the tools are ~100% LLM-wait, so concurrent requests run on parallel I/O lanes inside the single runner container (no per-modality queue). ffmpeg (audio normalisation) runs as an async subprocess.
Env: LITELLM_BASE_URL, LITELLM_MASTER_KEY (scoped service key),
CERASE_MULTIMODAL_ALIAS (default multimodal),
CERASE_TOOL_WORKSPACE_ROOT (path-traversal guard root).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.