# Framesail MCP server

Source: https://glimind.com/server/mcp-registry%2Fcom.framesail%2Fframesail
Registry id: `mcp-registry/com.framesail/framesail`
Status: live (checked 2026-11-22T13:00:29.066Z)

## Verdict

Framesail MCP server answered 98.88% of Glimind's liveness checks over 30 days, better than 16% of MCP servers, with 279 ms median handshake and 14 outages in 90 days. Its agent-readiness grade is A (92/100) across 28 tools, costing an agent about 9,700 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 98.88% | 16% of MCP servers |
| Median handshake latency | 279 ms | 43% of MCP servers |
| p95 handshake latency | 400 ms | — |
| Checks in 30 days | 6,858 | — |
| Outages, 90 days | 14 | — |
| Median recovery | 4 min | — |
| Agent-readiness score | 92/100 (A) | 65% of MCP servers |
| Tools | 28 | — |
| Tool-list size for an agent | ~9,700 tokens | 14% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "framesail-mcp-server": {
      "type": "http",
      "url": "https://api.framesail.com/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http framesail-mcp-server https://api.framesail.com/mcp
```

## Tools (28)

- `account_edit`: The account's default model and settings for one kind of generation, used when neither the call nor the item's prompt editor names one. voice_block needs provid
- `assets_edit`: Add a character, environment or object that Analyze Script missed, or rewrite one's description. After a description change, render its reference image again (a
- `assets_generate`: Render reference images, which keep each character, environment and object looking the same in every segment. Needs both style template images. Without asset_id
- `assets_read`: The project's characters, environments and objects, each with its description (what every render follows), reference_image (null: not rendered; view_image it), 
- `delete`: Delete; confirm with the user first. A project or music track is deleted for good; an asset or segment_extra is removed to the bin. project: it and everything i
- `editor_edit`: Polish the video in the editor; changes show in the next export. scene_note: edit one scene with a note (move, restyle, add or remove layers and overlays, chang
- `editor_read`: scenes: the editor timeline, one scene per segment, as {total, offset, returned, scenes}. music: {tracks}, timed in seconds. audio_library: tracks to add with e
- `export_video`: Render the finished video from the editor timeline; free. When the export job completes, get_status carries export_url.
- `get_generation_options`: What a generate call can be told to use. models: the allowed models with credit estimates and settings_schema (the valid settings keys); is_default marks the de
- `get_status`: Where things stand and what to do next; start and resume here. Always reports the account: plan, credits, credits held by running jobs, and credits_available to
- `projects_edit`: Create a channel or a project, or change a project's title, brief or video format. A new project takes its channel's style; a channel with no style needs one (s
- `projects_read`: Your channels, or the projects in one channel.
- `render`: Render segment images and clips, the biggest spend in the video: always run it with dry_run=true first and get the user's yes on the estimate. generate: without
- `script_edit`: Change the script or its settings; only revise spends credits. save: replace the active version's text (the old text is lost: show the user the current script f
- `script_generate`: generate: write the script from the brief and the narrative style; each run is a new version (review it with script_read). analyze (Analyze Script): find the sc
- `script_read`: The active script, its versions, and the script settings (script_target_minutes, voice_mix, visual concept). Show the script to the user before Analyze Script.
- `segment_edit`: Change one segment without losing renders. Returns the changed segments. set_prompts: write prompts verbatim, no AI rewrite. The renders stay as they are: rende
- `segment_restructure`: Change what a segment is. No render is ever lost: what a change replaces goes to the bin. combine: merge with a neighboring segment. The kept segment's prompts 
- `storyboard_edit`: Storyboard settings, used by the next storyboard run.
- `storyboard_generate`: Plan the storyboard: every segment, its timing, image and motion prompts, overlays and continuations, following the channel style and any `[SCENE: ...]` directi
- `storyboard_read`: segments: {total, offset, returned, segments}. Each segment has its segment_number (the handle segment tools take), kind (image, clip, talking head, real photo,
- `style_edit`: Create or change the channel style (one per channel, used by all its projects). create: offer the user two real options, never invented ones. (a) References (be
- `style_generate`: analyze: read the references again and rewrite art_style, narrative_style, director_style and text_style, replacing hand edits. template: render one of the styl
- `style_read`: get: the channel style: its references, its fields (art_style, narrative_style, director_style, text_style, any added; script_prompt on request), the summary an
- `view_image`: Show a Framesail image inline: a segment image, reference image, style template or preset preview.
- `voiceover_edit`: Voices and voice blocks; free. set_voice: the narrator's or a character's voice; every speaker needs one before the voiceover. rescan_blocks: split the active s
- `voiceover_generate`: Generate voice block audio. Every speaker needs a voice first, and every asset a reference image. Without voice_block_ids it fills every block with no audio, sk
- `voiceover_read`: voices: one engine's voice ids, labels and preview audio, as {groups, voices}. blocks: the voice blocks (narration and dialogue) with their speaker, voice_id (t

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
