Tiramisu Ai Mcp Server

Created By
rocnubie15 days ago
A Model Context Protocol server that exposes the canonical Tiramisu AI knowledge surface — official site information, pricing, FAQ, official links — to MCP-compatible AI clients such as Claude Desktop, Cursor, Windsurf, and Continue. Read-only, no API keys, no quota, ~50 ms cold start.
Overview

Tiramisu AI MCP Server

MCP server for Tiramisu AI

License: MIT Zero Config Node Stdio Transport Read Only MCP

A Model Context Protocol server that exposes the canonical Tiramisu AI knowledge surface — official site information, pricing, FAQ, official links — to MCP-compatible AI clients such as Claude Desktop, Cursor, Windsurf, and Continue. Read-only, no API keys, no quota, ~50 ms cold start.

Official website: https://tiramisuai.com

✨ About Tiramisu AI

Tiramisu AI is a web-based creative platform that brings together text-to-video generation, image-to-video conversion, image creation, and photo editing tools under a single interface. Rather than routing work across multiple specialized services, users can describe a scene in plain text and receive a video clip, animate a still photograph, generate original images from prompts, or swap backgrounds — all without leaving the platform. The service offers a free tier with daily credits and no watermarks, making it accessible for experimentation before committing to a paid plan. Both casual creators and professional teams will find the workflow familiar: upload or describe, choose a model, generate, and export.

Key Features

  • Multi-model video generation: Access to a curated set of video models — including Kling, Veo 3, Minimax Hailuo, Pixverse, Seedance, Wan 2.5, and others — selectable from a single dashboard without separate accounts or API keys per provider.
  • Text-to-video and image-to-video: Generate short video clips from written descriptions or animate existing photos with realistic motion, with output lengths ranging from a few seconds on the free tier up to 20 seconds on premium plans.
  • Image generation and editing: Over 15 image models available for creating visuals from prompts, alongside practical editing tools for background removal, background replacement, and face swapping.
  • Export quality tiers: Free accounts receive 720p MP4 exports; premium plans add 1080p and 4K options along with batch processing for higher-volume workflows.
  • API access: Developers can integrate generation capabilities into their own applications through an API, removing the need to build model infrastructure from scratch.
  • No-watermark free tier: Daily free credits produce clean outputs, which is less common among comparable platforms that restrict watermark removal to paid subscribers.

Use Cases

  • Social media content production: Create short-form video clips for Instagram Reels, TikTok, or YouTube Shorts directly from text descriptions or product photos, without video editing software.
  • E-commerce product visualization: Animate catalog images to show products in motion, or generate lifestyle imagery around static product shots to enrich listings and ads.
  • Marketing asset creation: Produce video drafts and image variations for campaigns without waiting on external creative vendors, then refine in-platform before handoff.
  • Prototype and concept demos: Developers and product teams can generate quick visual mockups or animated concept clips to communicate ideas before committing to full production.
  • API-driven content pipelines: Integrate Tiramisu AI's generation endpoints into automated workflows — for example, dynamically producing video summaries or image assets at scale for a content-heavy application.

Who Is It For

Tiramisu AI suits a broad range of users who need AI-generated visual content without managing separate model subscriptions or building their own generation stack. Content creators working across YouTube, TikTok, or Instagram will find the free tier practical for regular output. Marketing managers and social media teams benefit from the ability to produce and iterate on assets quickly inside one tool. E-commerce operators can use image-to-video features to make product pages more engaging. Developers who want to add video or image generation to their own products can access the same models through the API rather than negotiating individual provider agreements. The platform scales from individual hobbyist use up to team-level batch workflows.

Tools

get_site_overview

Return the canonical site overview so an agent has authoritative product context. (Tiramisu AI)

Input: no parameters. Returns: text/markdown.

get_pricing

Return the canonical pricing entry point for Tiramisu AI.

Input: no parameters. Returns: text/markdown.

Return the canonical list of official links for Tiramisu AI (website, support, docs when available).

Input: no parameters. Returns: text/markdown.

Resources

  • site://tiramisu-ai/overview — Public site overview.
  • site://tiramisu-ai/pricing — Canonical pricing entry point.
  • site://tiramisu-ai/faq — Short FAQ generated from public site metadata.
  • site://tiramisu-ai/links — Canonical URLs to share with users.

Prompts

tell_me_about_tiramisu_ai

Summarize what the site is, who it's for, and how it works. — Tiramisu AI

walk_me_through_tiramisu_ai

Tour the official site with citations. — Tiramisu AI

Installation

Install via Smithery

npx -y @smithery/cli install tiramisu-ai-mcp --client claude

(Replace claude with cursor, windsurf, or continue for those clients.)

Install from source

git clone https://github.com/rocnubie/tiramisu-ai-mcp.git
cd tiramisu-ai-mcp
pnpm install

Then add to your MCP client config (claude_desktop_config.json for Claude Desktop, mcp.json for Cursor / Windsurf / Continue):

{
  "mcpServers": {
    "tiramisu-ai-mcp": {
      "command": "node",
      "args": [
        "/absolute/path/to/tiramisu-ai-mcp/src/index.mjs"
      ]
    }
  }
}

Debug with MCP Inspector

npx @modelcontextprotocol/inspector node src/index.mjs

Development

pnpm install
pnpm start                 # run the server over stdio

License

MIT

Server Config

{
  "mcpServers": {
    "tiramisu-ai-mcp": {
      "command": "node",
      "args": [
        "/absolute/path/to/tiramisu-ai-mcp/src/index.mjs"
      ]
    }
  }
}
Project Info
Created At
15 days ago
Updated At
15 days ago
Author Name
rocnubie
Star
-
Language
-
License
-
Category
Tags

Recommend Servers

View All
GovQL
@Alex Stout

# govql-mcp-server An MCP (Model Context Protocol) server for [GovQL](https://govql.us) — gives AI clients like Claude Desktop, Claude Code, and Cursor direct access to the US Congressional GraphQL API at [api.govql.us/graphql](https://api.govql.us/graphql) without bespoke HTTP wiring. For the design rationale (why FastMCP-Python, the passthrough+curated philosophy, roadmap through v0.4), see [design.md](https://github.com/govql/govql/blob/main/mcp-server/docs/design.md). ## What you can do with it Ask an agent questions like: - *"How did Vermont's two senators vote on the most recent nomination?"* - *"Which legislators in the 118th Congress switched parties during their service?"* - *"Compare Senator Sanders' voting record to Senator Murkowski's on cloture votes in the most recent Congress."* The agent picks the right tool, writes the GraphQL query against the live schema, and parses the response — no manual API wrangling. ## Install The server runs as a per-client subprocess over stdio. Pick your client: ### Claude Desktop Edit `claude_desktop_config.json` (Settings → Developer → Edit Config): ```json { "mcpServers": { "govql": { "command": "uvx", "args": ["govql-mcp-server"] } } } ``` Restart Claude Desktop. The `govql` tools appear in the tools panel. ### Claude Code Add to `.mcp.json` in your project (or `~/.mcp.json` for global): ```json { "mcpServers": { "govql": { "command": "uvx", "args": ["govql-mcp-server"] } } } ``` ### Cursor Settings → MCP → Add Server. Use the same `command` / `args` as above. ### Other clients Any MCP-compatible client that supports stdio servers will work. The command is `uvx govql-mcp-server` with no required arguments. ## Tools | Tool | Purpose | |---|---| | `execute_graphql` | Run any GraphQL query against the GovQL endpoint. Returns the result plus an `last_ingest` timestamp so the agent can reason about data freshness. | | `list_types` | Returns the names and kinds of every type in the GovQL schema. Optional `kind` filter (`"OBJECT"`, `"INPUT_OBJECT"`, `"ENUM"`, etc.) to narrow further. Start here when you don't know what's queryable. | | `describe_type` | Returns one type's full details — fields, arg signatures, input fields, enum values. Call after `list_types` to learn the shape of a specific type before writing a query. | ## Configuration All env vars are optional — the package is zero-config for end users. | Env var | Default | Purpose | |---|---|---| | `GOVQL_ENDPOINT` | `https://api.govql.us/graphql` | Endpoint to query. Override to point at a local dev stack. | | `GOVQL_TIMEOUT_MS` | `30000` | Per-request HTTP timeout. | | `LOG_LEVEL` | `INFO` | Logging level. Logs go to stderr only (stdout is reserved for the MCP transport). | ## Limits (enforced by the upstream API) - Max query depth: 10 - Max query complexity: ~10 billion points (`first: N` multiplies child cost by N — keep page sizes reasonable on deeply nested queries) - Rate limit: 100 requests / 60 s per source IP A depth or complexity violation surfaces as a GraphQL `errors` entry in the tool response so the agent can adjust and retry. ## Data freshness Every `execute_graphql` response includes a `last_ingest` ISO timestamp. Vote data refreshes hourly; legislator data refreshes daily. ## Status Version 0.1.0 ships three foundational tools: a GraphQL passthrough (`execute_graphql`) and two narrow schema-discovery tools (`list_types`, `describe_type`). Curated higher-level tools (`find_legislator`, `get_voting_record`, `compare_voters`, etc.) are planned for subsequent releases — see [design.md](https://github.com/govql/govql/blob/main/mcp-server/docs/design.md) for the roadmap. ## Links - [GovQL project site](https://govql.us) - [GraphQL API](https://api.govql.us/graphql) - [Source / issues](https://github.com/govql/govql)

17 hours ago