SlideForge
https://api.slideforge.dev/mcp ↗
Description
Generate reliable, editable PowerPoint from agent workflows — real .pptx files, not web previews. A structured slide intent (or a plain brief) renders deterministically in ~50ms–1.5s. Built for agents: REST + MCP at full parity, one price, no LLM in the render path. - **Structured intent or brief**: Send a typed slide intent (a form + fields) or just a natural-language brief — both render to deterministic, editable PowerPoint. - **Fast, deterministic render**: Sub-second to ~1.5s per slide, predictable layout, no model in the hot path. - **150+ slide patterns**: KPIs, comparisons, roadmaps, risk registers, OKR trackers, decision tables, timelines, funnels, quadrants, and more — picked automatically from your brief. - **Decks in parallel**: Multi-slide decks fan out as parallel jobs with a contact sheet and partial-failure isolation. - **Code mode**: Caller-supplied python-pptx runs in a sandbox — the escape hatch for layouts outside the catalog. - **Translation**: Localize an existing
What our measurements say
SlideForge is a remote MCP server published at api.slideforge.dev. It has been probed 6 times since 9/10/2026. It answered in 6 of them (100.0%), a near-uninterrupted record. Median response time is 587 ms, a delay an agent will notice. It offers a narrow, focused set of 7 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Agent readability score
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
Agent readability score
Strengths
- Tool names clearly indicate their primary function (e.g., 'create_slide', 'translate_deck').
- Descriptions provide context for when tools should be used (e.g., 'plan_slide' for pre-rendering).
Weaknesses
- Parameter definitions are often ambiguous (e.g., 'variant=/prior_id=' without type or requirement details).
- Some descriptions truncate mid-sentence (e.g., 'type=schema + family -> a compact...').
- No explicit error handling or constraint documentation in tool descriptions.
browse_catalog— Parameter 'family' and 'q' lack type and requirement clarity.plan_slide— Truncated description omits critical details about 'next_action' handling.create_deck— Ambiguous 'slides' parameter schema for parallel slide generation.translate_deck— No mention of error cases for unsupported language scripts.upload_asset— Asset type constraints (e.g., 'max 5MB') are not explicitly called out.
Verdict
Event narrative
Risk: medium
- 2026-09-10T21:16:35.016Z — Era changed from auth-gated to legacy · Server transitioned to legacy mode, which may indicate reduced security features but stable operations
- 2026-09-11T09:28:19.138Z — Compliance score increased from null to 100 · Achieved full compliance with security standards in legacy era
Advice
Schema compliance
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
- tools/list schema valid
- inputSchema is valid JSON Schema
- Smoke test not run this round
- Cold-start: cold 32ms → warm 32ms (penalty 0ms)
Availability history
Event log
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
- Server build: — → 5.0.0
- Supported versions: — → 2025-03-26
- Era changed: Auth-gated → Legacy
- Added to watch — era: Auth-gated
Get your badge
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/smartdatabrokers-slideforge)<a href="https://mcpmetrics.io/servers/smartdatabrokers-slideforge"><img src="https://mcpmetrics.io/badge/smartdatabrokers/slideforge/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to see