powerpoint-engineSAFE
MCP server + manifest for the PowerPoint Engine API — generate & edit .pptx from AI agents (hosted, OAuth 2.1).
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Generate and edit real PowerPoint (.pptx) files from an AI agent, over the Model Context Protocol. Backed by the hosted [PowerPoint Engine API](https://powerpointengine.io) — no local PowerPoint, Office, or GPU required.
- Endpoint:
https://powerpointengine.io/api/mcp/mcp(Streamable HTTP) - Auth: OAuth 2.1 (browser authorize, PKCE, dynamic client registration)
- Website: https://powerpointengine.io · Docs: https://powerpointengine.io/docs
Install
Claude Code
claude mcp add --transport http powerpoint-engine https://powerpointengine.io/api/mcp/mcp
Then run /mcp and authorize in the browser (one click).
Other MCP clients
Point your client at the Streamable HTTP endpoint above. On first use it will open the browser OAuth flow; discovery is at https://powerpointengine.io/.well-known/oauth-protected-resource.
Tools
Markup rules
- A single
# Titleline sets the deck title. - Each
## Headingstarts a new slide. ### Heading+ are sub-headings;-/*are bullets.- Fenced code blocks, links,
**bold**, and inline code are cleaned up.
Themes: corporate, modern, minimal, vibrant.
What makes it different
- Structure-preserving edits: send your own
.pptxtemplate and replace
text/numbers while keeping the exact layout, fonts, and branding — the thing most generators break.
- Native editable charts from data (column/bar), not images.
- Zero setup: one hosted endpoint, OAuth, credit-based pricing (1 credit =
up to 10 slides). Free tier returns watermarked files; Pro remov
a96d980fa364OBSERVED · 2026-10-13Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
streamable-http
Gates applied: no_behavioural_pass.
a96d980fa364full audit observations/trust-audit/mcp-server/skippdot__powerpoint-engine-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-13 | a96d980fa364 | SAFE | B | 89 | first audit |
Questions
What is the powerpoint-engine MCP server?
MCP server + manifest for the PowerPoint Engine API — generate & edit .pptx from AI agents (hosted, OAuth 2.1).
Is powerpoint-engine safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does powerpoint-engine need?
No credential environment variables were found in its source, so it appears to need none.
How does powerpoint-engine run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (a96d980fa364), read on 2026-10-13. The repository is watched and re-audited when it changes.