Slidev MCP

Render Slidev Presentation

render_slides

Render a Slidev presentation from markdown and return its hosted URL.

IMPORTANT: Before calling this tool, you MUST call get_theme with the theme name you plan to use. Each theme has unique layouts, components, and frontmatter options. Apply the theme's specific features in your markdown to produce high-quality slides that match the theme's design.

If the user has not specified a theme, call list_themes to pick one. If you are unfamiliar with Slidev markdown syntax, call get_slidev_guide.

Images must be remote URLs or base64-encoded inline. Local file paths are not supported.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "markdown": "<markdown>",
      "theme": "<theme>"
    },
    "name": "render_slides"
  }
}

Input Schema

Name	Required	Description	Default
`uuid`	No	UUID of an existing presentation to update in-place (same URL). Omit to create a new presentation.
`theme`	Yes	Theme name (e.g. 'seriph', 'default', 'neocarbon'). Read slidev://themes/installed for the full list of available themes.
`markdown`	Yes	Full Slidev markdown including frontmatter. Use layouts, components, and features specific to the chosen theme.
`color_schema`	No	Color scheme: 'light' (default), 'dark', or 'auto'. Controls whether slides render in light or dark mode.	light

Schema Changelog

Changes observed during successful MCP inspections.

First observedMar 31, 2026

TDQS

A4.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly=false, destructive=false, idempotent=false), and the description adds real behavioral context beyond them: the tool publishes to a hosted URL, image sources are restricted to remote URLs or base64 (local paths fail), and the theme must be read before rendering to get valid output. It does not explain what happens to a re-render without a uuid versus with one, though the schema hints at it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded one-line purpose, then a clearly delineated prerequisite block, then two short conditional sentences and a constraint sentence. Every line carries actionable information; nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, but the description explicitly states the return value (hosted URL), and it covers the prerequisite chain, content constraints, and theme dependency for a 4-parameter tool. An agent has everything needed to invoke it correctly on the first attempt.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so 3 is the baseline; the description goes slightly beyond by constraining the markdown parameter's content (remote or base64 images only, theme-specific layouts/components expected) and by tying the theme parameter to a prerequisite lookup. The uuid in-place update behavior is left entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (render), resource (Slidev presentation from markdown), and outcome (hosted URL), which cleanly separates it from siblings like export_slides and screenshot_slides that act on already-rendered decks. An agent can tell what this does without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit conditional routing: call get_theme with the planned theme first (mandatory), call list_themes if no theme was specified, call get_slidev_guide if syntax is unfamiliar. These are concrete when-to-use rules naming the sibling tools, not implied guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Slidev MCP tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.