MCP.Market

Renderball MCP server

online · 100% uptime
by renderball.com·com.renderball/renderball·v1.1.0

Designed, animated, editable presentations your AI writes on Renderball. No account needed to try.

B81/100grade B
What users say
No reviews yet
Be the first
Safety scan
B81/100

full report

Adoption
Growing

0 stars

Reviews

Write one

Nobody has reviewed Renderball yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Renderball tools (8, 3 write)

write = sends, deletes, buys or posts
  • create_deckwrite actionFree

    Start a new presentation from a brief, the brand as YOU know it (name, and only the colours, fonts and logo you actually have — never guess a colour) and your outline. With the outline the reply carries the WRITING BRIEF, so the whole deck is two calls: this, then submit_deck. Without an account it also returns a guest_token to pass on later calls and deck_url, the one link to give the user.

  • deck_statusFree

    Whether a submitted deck is still importing, ready (with the editor link), or failed (with the reason).

  • get_briefFree

    The writing brief for a deck whose outline is already saved.

  • list_decksFree

    The user's Renderball documents, newest first, with editor links. Needs an account (a key).

  • see_deckFree

    The deck's rendered pages as images, page 1 first — look at them for overlapping or clipped text, odd spacing or an element off its page, then fix the file and submit_deck again. Available once the deck has been submitted.

  • share_deckFree

    Turn on the public link for a deck and return it.

  • submit_deckwrite actionFree

    Send the complete deck file you wrote. Renderball checks it against the brief, repairs small slips, renders every page and opens it in the editor. Returns 'ready' with the editor_url, or 'importing' — then poll deck_status.

  • write_outlinewrite actionFree

    Save the page-by-page outline you wrote for a deck. Returns the WRITING BRIEF: the exact instructions for writing the deck file (format, brand facts, truth rules). Follow it, then call submit_deck.

Public scan report

scanner v0.1.10 · 2026-10-03 · same rubric, same numbers if you re-run it

1 high
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 796ms20/20
  • Tool poisoning8 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 3 write-action tools with no auth3/15
  • Maintenancelast push 18 days ago15/15
  • Maintainer identityendpoint served from the registry-verified namespace domain8/10

Findings (1)

  • highWrite-action tools reachable without authenticationauth.open-write
Overall 81/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Renderball compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
81/100
higher than 62% of 48,255 servers
Tools
8
the typical server has 7
Tools that change things
38%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
149 ms
faster than 73% of 30,031 servers

What its tools let an agent do: 4 read · 2 create · 1 change · 1 send or post

Install Renderball in Claude Code, Cursor or VS Code

claude mcp add --transport http renderball https://renderball.com/api/mcp
Add to Cursor

What the publisher says

From the Renderball repository's README, as published. We do not edit it. Read it on GitHub

Renderball for your AI

Renderball turns a deck your AI writes into a designed, animated, editable presentation. This repository holds the files that plug Renderball into the tools an AI runs in. The product itself lives at https://renderball.com.

Install

Skill — Claude Code, Codex, Cursor, Gemini CLI and any agent that reads skills:

npx skills add agarces1999/renderball-skills

Claude Code and Cowork plugin:

/plugin marketplace add agarces1999/renderball-skills /plugin install renderball@renderball

Gemini CLI extension:

gemini extensions install https://github.com/agarces1999/renderball-skills

MCP server, any client: https://renderball.com/api/mcp — setup at https://renderball.com/docs/agents. No key needed to try; a key from https://renderball.com/account lifts the guest limits.

Agent toolkit for the Vercel AI SDK, the OpenAI Agents SDK or any tool loop: the @renderball/agent-toolkit package on npm, source in packages/agent-toolkit.

No setup at all

An AI that can make web requests needs none of the above: the recipe at https://renderball.com/for-ai (also /llms.txt) is three steps, and the deck comes back as one link.

What is here

This repository is generated from Renderball's product repository by a sync script; changes are made there and published here. MIT licensed.

Nothing above is checked by us. What we check is on the safety report.

Renderball: common questions

Is Renderball MCP server safe?
Mostly: it is graded B (81/100). Read the Renderball safety report
How do I install Renderball?
It runs remotely at renderball.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Renderball need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Renderball maintained?
The last commit was 50 days ago (2026-09-15). The latest release is v1.1.0.
Is Renderball up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does Renderball compare with other MCP servers?
safety score 81/100 (higher than 62% of 48,255 servers); tools 8 (the typical server has 7); tools that change things 38% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.