# Presentations.AI MCP server > Presentations.AI's hosted MCP server lets an agent draft an outline, generate an on-brand slide deck from a prompt, notes or a document, export it as PPTX or PDF and share it, spending Presentations.AI credits. - Canonical: https://www.anchorterminal.com/tools/presentations-ai-mcp - Pricing: https://www.anchorterminal.com/tools/presentations-ai-mcp#pricing - Reviews: https://www.anchorterminal.com/tools/presentations-ai-mcp#reviews - Markdown: https://www.anchorterminal.com/tools/presentations-ai-mcp.md (~3,650 tokens) - Slim: https://www.anchorterminal.com/tools/presentations-ai-mcp.min.md (~1,080 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/presentations-ai-mcp.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key) - DNS: dig +short TXT presentations-ai-mcp.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.. and .vs.. under the zone, and the same under grade.letme.dev) - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) - Updated: 2026-11-08 ## Overview **Grade E · 38.5/100 · rank #1357 of 1510 · #16 in Design workspaces & canvases · not agent-ready · confidence medium** ## Assessment Presentations.AI's MCP server turns a prompt or document into an on-brand deck in a few documented tools, with OAuth 2.1 and costs named on each tool. There's no status page, limits or error docs, and its terms and data handling weren't readable here. ## Facts | Field | Value | | --- | --- | | Vendor | Presentations.AI (https://www.presentations.ai) | | Kind | MCP server | | Category | Design workspaces & canvases (https://www.anchorterminal.com/categories/design) | | Transport | Streamable HTTP | | Endpoint | `https://api.presentations.ai/mcp` | | Auth | OAuth · OAuth 2.1 with PKCE and dynamic client registration, or an API key (pai_live_...) as an Authorization: Bearer header. | | Pricing | Freemium (Freemium) · Free to try; outlines cost 10 credits a slide and decks spend credits. whoami reports the plan and credit balance (checked 2026-11-07). | | x402 | No · No x402, MPP or L402 on the MCP docs or pricing page (checked 2026-11-07). | | Licence | MIT (repository); hosted service under Presentations.AI's terms | | MCP registry name | `ai.presentations/presentations-ai` | | Source | https://github.com/slidecraft-in/presentations-ai-mcp-server | | Docs | https://github.com/slidecraft-in/presentations-ai-mcp-server | | llms.txt | not found | | Surface listed | The hosted MCP server at api.presentations.ai/mcp, read from presentations.ai and the public slidecraft-in/presentations-ai-mcp-server repository on 7 November 2026. Only an MCP initialize was sent, which asked for sign-in | | Capabilities | docs.slides, design.create, document.export | | Tags | official, hosted, mcp, remote-mcp, oauth, api-key, freemium, mcp-registry | | JSON | https://www.anchorterminal.com/api/v1/tools/presentations-ai-mcp.json | ## Score breakdown (methodology v0.7, October 2026 research run) Assessed 2026-11-07 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 15 | 3.0 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 52 | 8.4 | | Agent ergonomics | 13% | 16.2 | 60 | 9.8 | | Security & auth | 14% | 17.5 | 41 | 7.2 | | Payments & pricing | 10% | 12.5 | 20 | 2.5 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 55 | 4.8 | | Transparency & trust (editorial 25, provenance 38) | 7% | 8.8 | 32 | 2.8 | | Negative events | up to −15 | up to −15 | none recorded | 0 | | **Total** | | | | **38.5 → E** | ### Why each score - Reliability 15 (checked 2026-11-07): No status page found (0). No history (5). No limits found (0). No retry guidance (0). No SLA (0). Not labelled beta (10). 0 + 5 + 0 + 0 + 0 + 10 = 15. - Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes. - Schema & documentation 52 (checked 2026-11-07): The repository's README documents every tool; schemas not read without sign-in (18 of 25). No llms.txt read (0). Descriptions say what each tool spends (16 of 20). Inputs typed in the source; not verified (8 of 15). README examples; errors not documented (5 of 15). Tag v1.1.0 on 3 November 2026, no changelog (5 of 15). 18 + 0 + 16 + 8 + 5 + 5 = 52. - Agent ergonomics 60 (checked 2026-11-07): A handful of tools (25). Outline first, then a deck (10 of 20). No documented errors (3 of 20). Credit-spending tools named, and share_deck flagged as making a public link (10 of 20). OAuth or a key, and an npm package for local use (12 of 15). 25 + 10 + 3 + 10 + 12 = 60. - Security & auth 41 (checked 2026-11-07): OAuth 2.1 with PKCE, or a live API key (22 of 30). No read-only mode; credit spends and public sharing are named in the docs (8 of 20). Documents fed in are untrusted; no guidance (3 of 15). No audit log (0). SECURITY.md with a reporting route (8 of 20). 22 + 8 + 3 + 0 + 8 = 41. - Payments & pricing 20 (checked 2026-11-07): No machine payment protocol (0). Credit costs per slide in the README; plan prices not read (5 of 20). Free to try (15 of 20). A person signs up (0). 0 + 5 + 15 + 0 = 20. - Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored. - Maintenance & community 55 (checked 2026-11-07): Tag v1.1.0 and registry update on 2 and 3 November 2026 (30). Fewer than three releases found in 90 days (0). Issues not read (0). Official registry entry ai.presentations/presentations-ai (15). CI and link checks in the repository (10). 30 + 0 + 0 + 15 + 10 = 55. Registry presence read from Anchor Terminal's own daily import of the official MCP registry (/api/v1/registry.json, 6 November 2026), not the registry's API. - Transparency & trust 32 (checked 2026-11-07): MIT repository, copyright 2026 Presentations.AI; service terms not read (20 of 30). Data handling not read (5 of 30). No deprecation policy (0). Subprocessors not found (0). 20 + 5 + 0 + 0 = 25. Fix list, everything this grade says the listing lacks, the biggest gain first (15 items). What it covers is at https://www.anchorterminal.com/fixes/presentations-ai-mcp.md (JSON https://www.anchorterminal.com/fixes/presentations-ai-mcp.json). The whole list for a coding agent comes from `POST https://www.anchorterminal.com/api/v1/fix-list` with `{"listing": "presentations-ai-mcp", "plan": "read"}`, free while the beta runs ### What we couldn't check - Plan prices, terms and privacy not read - People, ownership and investors not researched ### Sources - README, licence, SECURITY.md, tags, shallow clone: (seen 2026-11-07) - home page: (seen 2026-11-07) - lead, awesome-remote-mcp-servers pull request #3700: (seen 2026-11-07) ## Score history Every move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/presentations-ai-mcp/history.json - 2026-11-07: graded 38.5 E (methodology 0.7) ## Who's behind it (provenance 38/100, checked 2026-11-07) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | Presentations.AI | 20/20 | | Domain age | presentations.ai, no registry record we could read | 0/15 | | Endpoint on the vendor's domain | api.presentations.ai | 15/15 | | Terms of service | not found | 0/10 | | Privacy policy | not found | 0/10 | | Status page | not found | 0/10 | | Changelog | not found | 0/10 | | security.txt | not found | 0/10 | | People named | not researched yet | n/a | | Support route | help pages | 5/5 | Not looked up: RDAP isn't requested under the 1 November 2026 rules. The repository's MIT licence names Presentations.AI (2026). ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service**. We found no terms of service published for this product, so there is nothing to read and the check scores 0. **Privacy policy**. We found no privacy policy published for this product, so there is nothing to read and the check scores 0. ## Humans behind the project (researched 2026-11-07 from public pages, not part of the grade) ### Key people - No people named yet. - Note: People, ownership and investors weren't researched in this batch (7 November 2026, leads from the awesome-remote-mcp-servers pull requests). ### Getting support - Help: https://github.com/slidecraft-in/presentations-ai-mcp-server - Sources: https://github.com/slidecraft-in/presentations-ai-mcp-server ## Live (updated 2026-11-08 00:43 UTC) - Right now: up, HTTP 401, 233 ms, checked 2026-11-08 00:43 UTC (mcp-initialize on `https://api.presentations.ai/mcp`, asks for auth) - Uptime 24h 100.0% (61 probes) · 30 days 100.0% (61 probes) · p50 170 ms · p95 421 ms - Always current: https://www.anchorterminal.com/api/v1/live/presentations-ai-mcp.json ## Probe metrics Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score. ## Strengths - Outline-then-deck flow with credits named per tool - OAuth 2.1 with PKCE, or an API key - Open repository with CI and a security policy - Exports to PPTX and PDF ## Weaknesses - No status page, limits or error docs - share_deck creates a public link - Terms and data handling not read ## Before you call it (notes for agents) 1. Call whoami to check credits before generating 2. Draft an outline and confirm it before create_presentation 3. Ask before share_deck, which makes a public link ## Connect Claude Code: ```bash claude mcp add presentations-ai --transport http https://api.presentations.ai/mcp ``` MCP client configuration: ```json { "mcpServers": { "presentations-ai": { "url": "https://api.presentations.ai/mcp" } } } ``` Through letme: https://letme.dev/presentations-ai-mcp (letme picks it for design.create, the top-graded tool for the job, letme picks it for docs.slides, the top-graded tool for the job, letme picks it for document.export, the top-graded tool for the job). letme answers with the pick and how to call it direct. How it works: https://www.anchorterminal.com/letme/index.md ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | Impeccable | B | 69.6 | 236 | same category (Design workspaces & canvases) | no | https://www.anchorterminal.com/tools/impeccable.md | | Framelink MCP for Figma | B | 66.1 | 387 | same category (Design workspaces & canvases) | no | https://www.anchorterminal.com/tools/framelink-figma-mcp.md | | Figma API + MCP | B | 63.4 | 517 | same category (Design workspaces & canvases) | no | https://www.anchorterminal.com/tools/figma-mcp.md | | Magic Patterns | B | 63.4 | 519 | same category (Design workspaces & canvases) | no | https://www.anchorterminal.com/tools/magic-patterns.md | | Miro API + MCP | B | 62.1 | 575 | same category (Design workspaces & canvases) | no | https://www.anchorterminal.com/tools/miro.md | | UXKIN | C | 57.4 | 798 | same category (Design workspaces & canvases) | no | https://www.anchorterminal.com/tools/uxkin-agent.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - OAuth 2.1 with PKCE and dynamic registration, or an API key (source: ) - create_outline spends 10 credits a slide (source: ) - #16 of 18 in Best design workspace and canvas APIs for AI agents: https://www.anchorterminal.com/best/design/index.md - All 133 design comparisons: https://www.anchorterminal.com/compare/design/index.md ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on presentations.ai or one of its subdomains, or the README at the root of github.com/slidecraft-in/presentations-ai-mcp-server. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "presentations-ai-mcp", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html Presentations.AI MCP server on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![Presentations.AI MCP server on Anchor Terminal](https://www.anchorterminal.com/badges/presentations-ai-mcp.svg)](https://www.anchorterminal.com/tools/presentations-ai-mcp) ``` Plain link: ```html Presentations.AI MCP server on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Presentations.AI MCP server is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/presentations-ai-mcp-dark.png - Light: https://www.anchorterminal.com/assets/share/presentations-ai-mcp-light.png --- Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp