Skip to main content
Glama
deenesjakoruzh
agenticdecks

deckrun-mcp

by agenticdecks
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

Deckrun MCP Server

PyPI awesome-mcp-servers

Note: The hosted Deckrun endpoints (free.agenticdecks.com, deckrun-mcp-free.agenticdecks.com, api.agenticdecks.com) are provisioned per engagement — see Access & Availability. The pip install deckrun-mcp package and local-execution paths documented below work immediately against your own deployment. For hosted access, open an Access Request — we respond within one business day.

MCP server for Deckrun by Agentic Decks — generate presentation PDFs, narrated videos, and audio from Markdown. Built for AI agents and IDEs.

Deckrun is a document execution engine: your AI writes the content, Deckrun renders it into pixel-perfect branded PDFs, narrated MP4 videos, and MP3 audio — from a single Markdown source. No slide editor, no video tool, no audio studio.

Install: pip install deckrun-mcp

Quickstart — no install needed

The HTTP transport is hosted and ready. Add one JSON snippet to your IDE.

VS Code (GitHub Copilot Chat — v1.99+)

.vscode/mcp.json in your project (this file is included in the repo):

{
  "servers": {
    "deckrun": {
      "type": "http",
      "url": "https://deckrun-mcp-free.agenticdecks.com/mcp/"
    }
  }
}

Cursor

.cursor/mcp.json in your project:

{
  "mcpServers": {
    "deckrun": {
      "url": "https://deckrun-mcp-free.agenticdecks.com/mcp/"
    }
  }
}

Google Antigravity (Gemini CLI)

~/.gemini/antigravity/mcp_config.json:

{
  "mcpServers": {
    "deckrun": {
      "serverUrl": "https://deckrun-mcp-free.agenticdecks.com/mcp/"
    }
  }
}

Claude Code (terminal)

~/.claude/settings.json:

{
  "mcpServers": {
    "deckrun": {
      "type": "http",
      "url": "https://deckrun-mcp-free.agenticdecks.com/mcp/"
    }
  }
}

Related MCP server: mcp-ToseaAI

Stdio install (Claude Desktop and other stdio-only clients)

pip install deckrun-mcp

Claude Desktop — ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "deckrun": {
      "command": "python",
      "args": ["/path/to/deckrun_mcp.py"]
    }
  }
}

Paid tier — add the API key:

{
  "mcpServers": {
    "deckrun": {
      "command": "python",
      "args": ["/path/to/deckrun_mcp.py"],
      "env": { "DECKRUN_API_KEY": "dk_live_..." }
    }
  }
}

Get your API key at agenticdecks.com after subscribing.

Tools

Free tier (no key required)

Tool

Description

get_slide_format

Fetch the live slide format spec — layout tags, syntax rules, example Markdown

generate_slide_deck

Convert Deckrun Markdown → PDF. Returns a public URL (90-day expiry)

Paid tier (DECKRUN_API_KEY set)

All free tools plus:

Tool

Description

generate_video

Markdown → narrated MP4 (async, returns job_id)

generate_audio

Slide notes → MP3 narration (async, returns job_id)

check_job

Poll async job status until complete or failed

get_account

Plan name, render units used/remaining, active add-ons

validate_markdown

Lint Deckrun Markdown and get a pre-flight RU estimate

list_themes

List available slide/document themes (system + custom)

list_voices

List available narration voices — id, name, tier, language

Example prompt

Once configured, ask your AI:

"Create a 6-slide deck on the future of edge computing"

The AI will call get_slide_format to learn the syntax, write the Markdown, call generate_slide_deck, and reply with a clickable PDF link.

HTTP endpoints

Tier

MCP endpoint

Free

https://deckrun-mcp-free.agenticdecks.com/mcp/

Paid

https://deckrun-mcp.agenticdecks.com/mcp/

Discovery: GET <endpoint> returns server metadata as JSON.

Links

Available Tools

2 tools
generate_slide_deckA

Convert Deckrun Markdown into a PDF slide deck. Call get_slide_format first to learn the correct Markdown format. Then call this tool with the completed Markdown. Returns: url (public PDF, 90-day expiry), slug, slides (count), warnings (non-fatal notices to self-correct), schema_version. Limits: max 10 slides, 50 KB Markdown. Slides separated by --- on its own line.

ParametersJSON Schema
NameRequiredDescriptionDefault
markdownYesComplete slide deck in Deckrun Markdown format. Must start with a title slide using <!-- <title-slide /> -->.

TDQS

A4.8/5.0
Behavior4/5

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

No annotations provided, so description carries full burden. Discloses return values (url with expiry, slug, slides count, warnings, schema_version) and non-fatal notices. Could mention whether operation is destructive, but creation is implied.

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?

Concise, well-structured sentences. Front-loads main action, then details prerequisites, return fields, and limits. No wasted words.

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?

Complete for a simple tool with one parameter and no output schema. Covers prerequisites, limits, return values, and warnings. No gaps.

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

Parameters5/5

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

Schema coverage 100% with one parameter. Description adds crucial formatting constraint (must start with title slide using specific comment) and reiterates limits beyond 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?

Clearly states it converts Deckrun Markdown into a PDF slide deck, distinct from sibling get_slide_format which teaches the format.

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?

Explicitly instructs to call get_slide_format first, provides limits (max 10 slides, 50 KB), and explains return fields including warnings.

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

get_slide_formatA

Fetch the authoritative Deckrun slide format specification. Call this first to learn all layout tags, Markdown syntax, and rules before writing slides. Returns JSON with layout_tags, surface_syntax, example_markdown, and limits.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.3/5.0
Behavior3/5

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

No annotations provided, so description must bear full burden. It states the tool returns JSON with specific fields, but does not explicitly declare it as read-only or side-effect-free, nor mention any auth or rate limits. The nature of the tool is apparent, but some behavioral detail is missing.

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?

Two sentences, front-loaded with action and purpose. Every sentence provides essential information with no redundancy or waste.

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?

Given no output schema, the description fully specifies the return structure (layout_tags, surface_syntax, example_markdown, limits). This is complete for a simple format-fetching tool with zero parameters.

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?

No parameters exist (0 params, 100% schema coverage). Baseline is 4. The description adds value by listing the return fields (layout_tags, surface_syntax, etc.), which helps the agent interpret the output beyond the empty 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?

The description clearly states the tool fetches the authoritative Deckrun slide format specification, with specific verb 'Fetch' and resource 'slide format specification'. It distinguishes from sibling 'generate_slide_deck' by indicating this is a preliminary step.

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

Usage Guidelines4/5

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

Explicitly says 'Call this first to learn... before writing slides', providing clear when to use. Does not explicitly state when not to use or mention alternatives aside from the implied sibling tool.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 2 tool updatesv1.1.1
    • First observedgenerate_slide_deck
    • First observedget_slide_format
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.4/5.0
Disambiguation5/5

The two tools have completely distinct purposes: one provides the format specification, the other generates the slide deck. No overlap in functionality.

Naming Consistency5/5

Both tool names follow a consistent verb_noun pattern: 'generate_slide_deck' and 'get_slide_format'. Conventions are uniform.

Tool Count3/5

With only 2 tools, the server feels minimal. While it covers the core workflow (get format, generate), the count is low for a full-featured service, but not extreme.

Completeness3/5

The tool set covers the essential flow: fetch format then generate. However, it lacks tools for managing or revising decks, leaving notable gaps for repeated use.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/agenticdecks/deckrun-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server