# Flamigo (remote · api.flamigo.ai)

Turn notes into slides, edit presentations, compare designs, and export HTML or PowerPoint.

- Trust score: 77/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `api.flamigo.ai`: 77/100 (this document), [markdown](https://verifymcp.io/servers/ai-flamigo-presentation/api.md), [page](https://verifymcp.io/servers/ai-flamigo-presentation/api)

## Channel facts

- Endpoint: `https://api.flamigo.ai/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `0.1.2`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 56/100
  - AI-judged instruction clarity (fair).
  - Context-footprint check failed: tool/resource definitions use about 2103 tokens (~123/item across 17 items; 17 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 84/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 43% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 17 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Flamigo MCP server?

Flamigo is a hosted endpoint at https://api.flamigo.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ai-flamigo-presentation 'https://api.flamigo.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-flamigo-presentation": {
      "url": "https://api.flamigo.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-flamigo-presentation": {
      "type": "http",
      "url": "https://api.flamigo.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-flamigo-presentation]
url = "https://api.flamigo.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-flamigo-presentation": {
      "type": "remote",
      "url": "https://api.flamigo.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-flamigo-presentation --url 'https://api.flamigo.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-flamigo-presentation:
    url: "https://api.flamigo.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-flamigo-presentation": {
      "Transport": "http",
      "Url": "https://api.flamigo.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-flamigo-presentation -t streamable-http -u 'https://api.flamigo.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-flamigo-presentation": {
      "type": "http",
      "url": "https://api.flamigo.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 77, +1)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-20 (score 76, 0)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-19 (score 76, +1)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-18 (score 75, 0)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-17 (score 75, +1)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-16 (score 74, 0)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-15 (score 74, +1)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-14 (score 73, 0)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

## MCP tools (17)

### `list_presentations` (~15 tokens)

List the authenticated user's presentations.

Output parameters:

- `presentations` (array)
- `resource_uri` (string)

### `upload_image` (~120 tokens)

Upload an existing image to this presentation's Supabase Storage folder. Use the returned public URL as an image src in the slide DSL. After HTTP 429, wait and retry with the same operation_id and arguments.

Input parameters:

- `image_data` (string, required): Base64 data URI for a PNG, JPEG or WebP image, up to 10 MiB and 20 megapixels.
- `operation_id` (string, required): Account-wide operation ID, 1–128 characters after trimming. Reuse only for an identical retry.
- `presentation_id` (string, required)

Output parameters:

- `path` (string)
- `url` (string)

### `create_presentation` (~174 tokens)

Create an empty presentation. Select color_preset_id and font_preset_id from flamigo://themes by type. Defaults: color-navy-white, font-modern. IDs are preset slugs.

Input parameters:

- `color_preset_id`
- `font_preset_id`
- `illustration_instruction`: Deck-wide style for new illustrations. Choose a medium, palette, mood, and level of detail that suit the topic and audience. Each slide supplies its subject and composition. Existing illustrations ar…
- `operation_id` (string, required): Account-wide operation ID, 1–128 characters after trimming. Reuse only for an identical retry.
- `presentation_style`
- `source_content` (string)
- `title` (string, required)

Output parameters:

- `presentation`
- `resource_uri` (string)
- `web_url` (string)

### `update_presentation` (~227 tokens)

Update metadata, source, presentation_style, illustration_instruction, or independent color_preset_id/font_preset_id from flamigo://themes. Ask the user whether to refresh existing HTML after a style change. Omitted or null values leave selections unchanged. Uses the presentation revision. Does not render HTML; returns theme_changed and slides_to_refresh with slide revisions and the theme refresh flag.

Input parameters:

- `color_preset_id`
- `expected_revision` (integer, required): Revision of the target presentation.
- `font_preset_id`
- `illustration_instruction`: Deck-wide style for new illustrations. Choose a medium, palette, mood, and level of detail that suit the topic and audience. Each slide supplies its subject and composition. Existing illustrations ar…
- `operation_id` (string, required): Account-wide operation ID, 1–128 characters after trimming. Reuse only for an identical retry.
- `presentation_id` (string, required)
- `presentation_style`
- `source_content`
- `title`

Output parameters:

- `presentation`
- `resource_uri` (string)
- `slides_to_refresh` (array)
- `theme_changed` (boolean)

### `create_slide` (~74 tokens)

Create a slide, optionally after an existing slide.

Input parameters:

- `after_slide_id`
- `expected_revision` (integer, required): Revision of the target presentation.
- `operation_id` (string, required): Account-wide operation ID, 1–128 characters after trimming. Reuse only for an identical retry.
- `presentation_id` (string, required)

Output parameters:

- `presentation_revision` (integer)
- `resource_uri` (string)
- `slide`

### `update_slide` (~113 tokens)

Supply at least one update: complete slide DSL or background_image_url.

Input parameters:

- `background_image_url`: HTTPS URL to set the background, empty string to remove it, or null/omitted to keep it.
- `dsl`
- `expected_revision` (integer, required): Revision of the target slide.
- `operation_id` (string, required): Account-wide operation ID, 1–128 characters after trimming. Reuse only for an identical retry.
- `presentation_id` (string, required)
- `slide_id` (string, required)

Output parameters:

- `resource_uri` (string)
- `slide`

### `draft_outline` (~93 tokens)

Draft a presentation-level narrative outline from the saved source.

Input parameters:

- `direction` (string)
- `expected_revision` (integer, required): Revision of the target presentation.
- `max_pages` (integer): Maximum slide count; sparse source material may produce fewer.
- `operation_id` (string, required): Account-wide operation ID, 1–128 characters after trimming. Reuse only for an identical retry.
- `presentation_id` (string, required)

Output parameters:

- `outline` (array)
- `presentation_revision` (integer)
- `resource_uri` (string)

### `generate_slides_from_dsl` (~122 tokens)

Replace all slides in the presentation with the supplied complete slide DSL objects. Existing slides and their checkpoints are deleted. This clears the previous generation batch. Read /slides and render every page with has_html=false.

Input parameters:

- `expected_revision` (integer, required): Revision of the target presentation.
- `operation_id` (string, required): Account-wide operation ID, 1–128 characters after trimming. Reuse only for an identical retry.
- `presentation_id` (string, required)
- `slides` (array, required): All pages in display order. Page numbers are assigned from 1.

Output parameters:

- `presentation_revision` (integer)
- `resource_uri` (string)
- `slides` (array)

### `generate_slides_from_outline` (~107 tokens)

Generate DSL from the reviewed outline, using its sentences as source material when the saved source is empty. Replace all slides and their checkpoints. Render each new slide afterward.

Input parameters:

- `complexity` (string)
- `expected_revision` (integer, required): Revision of the target presentation.
- `operation_id` (string, required): Account-wide operation ID, 1–128 characters after trimming. Reuse only for an identical retry.
- `outline` (array, required)
- `presentation_id` (string, required)

Output parameters:

- `generation_id` (string)
- `phase` (string)
- `presentation_revision` (integer)
- `resource_uri` (string)
- `slide_count` (integer)
- `status` (string)

### `render_slide` (~110 tokens)

Render a slide. Automatically reuse a saved layout when possible or create one when needed. Set apply_project_theme to refresh its theme. Returns the HTML resource_uri, including on replay.

Input parameters:

- `apply_project_theme` (boolean)
- `expected_revision` (integer, required): Revision of the target slide.
- `operation_id` (string, required): Account-wide operation ID, 1–128 characters after trimming. Reuse only for an identical retry.
- `presentation_id` (string, required)
- `slide_id` (string, required)

Output parameters:

- `page_no` (integer)
- `resource_uri` (string)
- `revision` (integer)
- `slide_id` (string)

### `redraw_slide` (~86 tokens)

Redesign the whole slide layout from its saved content and render a new preview, replacing any manual layout.

Input parameters:

- `expected_revision` (integer, required): Revision of the target slide.
- `operation_id` (string, required): Account-wide operation ID, 1–128 characters after trimming. Reuse only for an identical retry.
- `presentation_id` (string, required)
- `slide_id` (string, required)

Output parameters:

- `page_no` (integer)
- `resource_uri` (string)
- `revision` (integer)
- `slide_id` (string)

### `generate_slide_dsl` (~109 tokens)

Replace the target slide content with newly generated DSL and clear its saved layout and HTML. Render it afterward.

Input parameters:

- `complexity` (string)
- `content` (string, required)
- `expected_revision` (integer, required): Revision of the target slide.
- `layout` (string)
- `operation_id` (string, required): Account-wide operation ID, 1–128 characters after trimming. Reuse only for an identical retry.
- `presentation_id` (string, required)
- `slide_id` (string, required)

Output parameters:

- `resource_uri` (string)
- `slide`

### `get_generation_status` (~51 tokens)

Read generation batch progress. Direct DSL imports have idle status. Use has_html in /slides to find missing previews and layout_content_current in slide detail to find stale previews.

Input parameters:

- `presentation_id` (string, required)

Output parameters:

- `presentation`
- `slides` (array)

### `save_checkpoint` (~83 tokens)

Save the current slide design as a restorable checkpoint.

Input parameters:

- `expected_revision` (integer, required): Revision of the target slide.
- `label` (string)
- `operation_id` (string, required): Account-wide operation ID, 1–128 characters after trimming. Reuse only for an identical retry.
- `presentation_id` (string, required)
- `slide_id` (string, required)

Output parameters:

- `checkpoint`
- `resource_uri` (string)
- `slide_revision` (integer)

### `restore_checkpoint` (~81 tokens)

Restore a saved checkpoint with revision protection.

Input parameters:

- `checkpoint_id` (string, required)
- `expected_revision` (integer, required): Revision of the target slide.
- `operation_id` (string, required): Account-wide operation ID, 1–128 characters after trimming. Reuse only for an identical retry.
- `presentation_id` (string, required)
- `slide_id` (string, required)

Output parameters:

- `checkpoint`
- `resource_uri` (string)
- `slide_revision` (integer)

### `generate_slide_alternatives` (~193 tokens)

Generate up to five variant combinations using the slide’s saved theme, preserving geometry and background. Waits for newly created choices; reuses existing choices unless fresh=true. May return pending choices from another request: read resource_uri for status. Preview ready candidates using preview_resource_uri, then apply_slide_alternative. Requires configured Redis and a preview matching the current slide and layout. No LLM calls or generation credits. Choices expire. Replaying operation_id returns the original snapshot; read resource_uri for current status.

Input parameters:

- `expected_revision` (integer, required): Revision of the target slide.
- `fresh` (boolean): Request a new batch after the current batch finishes. An in-progress batch is always reused.
- `operation_id` (string, required): Account-wide operation ID, 1–128 characters after trimming. Reuse only for an identical retry.
- `presentation_id` (string, required)
- `slide_id` (string, required)

Output parameters:

- `base_revision` (integer)
- `candidates` (array)
- `expires_at` (number)
- `id` (string)
- `resource_uri` (string)

### `apply_slide_alternative` (~127 tokens)

Apply a ready design choice with the batch's base_revision as expected_revision. Preserves slide content and saves the selected design and HTML. Expired choices or changes to the slide/theme require generating a new set.

Input parameters:

- `batch_id` (string, required)
- `candidate_id` (string, required)
- `expected_revision` (integer, required): base_revision returned by the candidate batch.
- `operation_id` (string, required): Account-wide operation ID, 1–128 characters after trimming. Reuse only for an identical retry.
- `presentation_id` (string, required)
- `slide_id` (string, required)

Output parameters:

- `page_no` (integer)
- `resource_uri` (string)
- `revision` (integer)
- `slide_id` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-flamigo-presentation/api#diagnostics

## Score history

- 2026-11-21: 77
- 2026-11-20: 76
- 2026-11-19: 76
- 2026-11-18: 75
- 2026-11-17: 75
- 2026-11-16: 74
- 2026-11-15: 74
- 2026-11-14: 73
- 2026-11-13: 73
- 2026-11-12: 72
- 2026-11-11: 36
- 2026-11-10: 36
- 2026-11-09: 36
- 2026-11-08: 36

## Common questions

### What is the Flamigo MCP server?

Flamigo is an MCP server listed in the public MCP registry as ai.flamigo/presentation. Turn notes into slides, edit presentations, compare designs, and export HTML or PowerPoint. This page covers its hosted endpoint (https://api.flamigo.ai/mcp).

### Is the Flamigo MCP server safe to use?

Flamigo scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Flamigo MCP server expose?

Flamigo exposes 17 tools: list_presentations, upload_image, create_presentation, update_presentation, create_slide, and 12 more. Their descriptions and schemas cost roughly 1,885 tokens of context every time the server is loaded.

### Does the Flamigo MCP server require authentication?

Yes. Flamigo asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Flamigo MCP server still maintained?

Flamigo is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Flamigo MCP server?

VerifyMCP ran 13 checks on Flamigo, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://api.flamigo.ai/mcp
- Website: https://flamigo.ai/wiki/mcp
- Changelog RSS feed: https://verifymcp.io/servers/ai-flamigo-presentation/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-flamigo-presentation/api/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ai-flamigo-presentation/api.json
- HTML version of this page: https://verifymcp.io/servers/ai-flamigo-presentation/api
