// SCAN REPORT

Framesail

68 tools. 43 can modify or destroy data without limits.

6 destructive tools with no built-in limits. Policy required.

Last updated: 18 Aug 2026

43 can modify or destroy data

25 read-only

68 tools total

Community server · catalogue entry checked 18/08/2026 · full schemas captured for 63 of 68 tools

How to control Framesail ↓

TOOL MAP

What Framesail exposes to your agents

Read (25) Write / Execute (37) Destructive / Financial (6)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Framesail costs in tokens

12,085 tokens of tool definitions, loaded on every request

6.0% of a 200k context window

457 heaviest tool: director_note

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Framesail tools

Destructive · High delete_project This tool irreversibly deletes all data associated with a project with no undo mechanism. Destructive · High delete_asset This tool performs irreversible data deletion. Destructive · High delete_style This tool irreversibly deletes style data from the system. Destructive · Medium remove_music_track Removing a music track is an irreversible deletion of a project asset.

43 of Framesail's 68 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Framesail

PolicyLayer is an MCP gateway — it sits between your AI agents and Framesail, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_asset": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "activate_script_version": {
    "limits": [
      {
        "counter": "activate_script_version_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "await_jobs": {
    "limits": [
      {
        "counter": "await_jobs_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Framesail — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON FRAMESAIL →

Instant setup, no code required.

FULL CATALOGUE

All 68 Framesail tools

DESTRUCTIVE 6 tools

Destructive delete_asset Delete a project asset (e.g. one the scan over-extracted). Destructive delete_project Permanently delete a project and everything in it (script versions, assets, voiceover, segments, renders). Destructive delete_style Delete a style (e.g. a failed analysis experiment). Don't delete a style that projects still use as their Destructive director_note Edit ONE scene with a natural-language note (the same director chat the editor UI uses): move/restyle/add/ Destructive remove_music_track Remove a music track from the project. Destructive scan_script Analyze the active script: extracts character/environment/object assets and splits narration into voice bl

EXECUTE 4 tools

Execute analyze_style Re-run style analysis (after changing a style's inputs). Async — await_jobs(style_id=...) until the style_ Execute build_scenes Compile segments + assets + voiceover into the editor/render timeline (scenes). Run after segment assets a Execute export_video Render the final MP4 (Remotion). Fetches the current timeline and queues the render. Async — poll get_work Execute regenerate_segment_asset Regenerate a segment's primary image or video with optional overrides — the API equivalent of the editor's

WRITE 33 tools

Write activate_script_version Switch the project's active script to another saved version (ids come from get_script's version list — eve Write add_music_track Add background music to the project from the audio library (find track ids with browse_audio_library, cate Write add_segment_sfx Attach a sound effect from the audio library to a segment (find track ids via browse_audio_library with ca Write change_segment_type Change a segment's visual type: "image" | "video" | "overlay_scene". carry_frame=true reuses the already-r Write combine_segments Merge a segment with an adjacent one (segment numbers must be neighbors). keep: "this" | "other" — whose c Write create_asset Manually add a character/environment/object the scan missed. asset_type: "character" | "environment" | "ob Write create_channel Create a new channel — the container for projects and their reusable styles. Use when the user wants a fre Write create_project Create a project. The description (the video concept/topic) seeds script generation, so write a meaningful Write create_style Create a style. Two mutually exclusive paths: References (best): inputs=[{"input_type": "youtube" | "text Write generate_asset_reference Render an asset's reference image in the channel's art style — the visual anchor that keeps a character/en Write generate_script Generate the project's script from its description/concept and the channel's narrative style. Async — retu Write generate_segments Render every actionable segment asset (images, video clips, overlays) across the project, in dependency or Write generate_storyboard Plan the full visual storyboard: segments, shot pacing, image/video prompts, overlays, continuation chains Write generate_style_template Render one of a style's two template images — a REAL step of style setup, not an optional extra: a style i Write generate_voiceover Generate TTS audio for the project's voice blocks. Without voice_block_ids it fills gaps: only blocks with Write project_director_note Apply a project-WIDE director note ("make the intro punchier", "all captions bigger", "tighten pacing in t Write remove_segment_sfx Remove a sound effect from a segment. With one SFX attached, no name needed; with several, pass sfx_name ( Write rescan_voice_blocks Re-extract voice blocks from the active script WITHOUT touching assets or their reference images — the non Write revise_script AI-rewrite a passage of the active script in the project's narrative voice (the same in-editor revise the Write save_script Save script text (your own draft, or an edited version of the generated one — saving creates a new version Write set_character_voice Bind a TTS voice to a character asset — required before generate_voiceover for every character with dialog Write set_narrator_voice Set the project's narrator TTS voice — required before generate_voiceover whenever the script has narratio Write set_project_style Set the project's default style — the style whose art/narrative/director fields drive its generations. Use Write set_provider_key Register a BYOK provider API key (encrypted at rest, BYOK plan only). Jobs whose model belongs to this pro Write set_segment_continuation Make a segment's image render as a continuation of an EARLIER segment's frame (same composition evolving — Write split_segment Split a segment at the given time offsets (ms, 1-3 cuts → 2-4 parts). inherit_index picks which resulting Write update_asset Rename an asset and/or rewrite its description. If the look changed, regenerate its reference image afterw Write update_caption_config Merge a patch into the project's burned-in caption config (keys like enabled, plus styling). Read the curr Write update_music_track Tweak a music track. fields keys: name, volume (0-1), loop, start_frame, duration_frames, position, trim_s Write update_project Patch project fields. Updatable: title, description, asset_mix, sfx_level, video_concept, voice_mix, voice Write update_segment_content Rewrite one segment's creative direction from feedback ("make this shot a close-up", "show the machine fro Write update_style_fields Hand-edit a style's analyzed fields after reviewing them — e.g. tighten the art_style wording or adjust th Write update_voice_block Override one voice block's voice or playback volume (block ids from list_voice_blocks). Re-run generate_vo

READ 25 tools

Read await_jobs Block (server-side) until the scope has no pending/running jobs, or the timeout passes — use this instead Read browse_audio_library Browse the audio library for background music and sound effects. category: "music" | "sfx". Returns track Read get_credit_balance Current credit balance + plan info. Check before expensive steps (a full segment render can cost hundreds Read get_pipeline_progress THE resume/orientation tool: one call returns every pipeline step's state (script -> scan -> reference_ima Read get_project Fetch a project row — settings, voice config, default style, export URL. Read get_script Read the active script's full text + the version list. Use this to show the script to your user for review Read get_section_template Inspect the prompt sections a generation job exposes for per-call override via editable_sections (jobs: sc Read get_segment_assets List one segment's assets (images/video/overlays) including their status, config (prompts, model), and pub Read get_segments List the storyboard's segments (narration span, type, duration, creative direction). The 1-based segment_n Read get_style Fetch one style row — its inputs (reference material), analyzed fields (art_style, narrative_style, direct Read get_video_url Download URL for the most recent completed export. Read get_workflow_status Poll this between steps: returns active + recently-finished AI jobs (scope by project_id, or style_id for Read list_assets List the project's assets extracted by scan_script — characters, environments, objects. Each has a descrip Read list_channels List your channels. Every project lives in a channel, which owns the reusable styles (art/narrative/direct Read list_models List the models allowed for a generation job, with display names, credit estimates, and each model's setti Read list_music_tracks List the project's background music tracks (volume, loop, timing). Read list_projects List projects in a channel. Read list_provider_keys List registered BYOK providers (masked — only the last 4 characters). Read list_scenes List the project's scenes (composition layers, durations, layout). Read list_style_presets The curated preset catalog for the no-AI style creation path, grouped by axis (art_style / narrative_style Read list_styles List the channel's style rows (variable groups). Styles hold the art_style / narrative_style / director_st Read list_voice_blocks List the project's voice blocks (per-speaker narration chunks) with their audio status and assigned voices Read list_voices List available TTS voices (id, label, preview audio URL) for a provider: "minimax" (default engine) or "el Read view_image Fetch a rendered Framesail image so you (and your user) can SEE it — pass a URL from get_segment_assets, g Read whoami Verify the connection: the account email and plan behind the current credential. Call once after connectin

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Framesail

Can an AI agent delete data through the Framesail MCP server? +

Yes. The Framesail server exposes 6 destructive tools including delete_asset, delete_project, delete_style. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Framesail? +

The Framesail server has 33 write tools including activate_script_version, add_music_track, add_segment_sfx. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Framesail.

How many tools does the Framesail MCP server expose? +

68 tools across 4 categories: Destructive, Execute, Read, Write. 25 are read-only. 43 can modify, create, or delete data.

How do I enforce a policy on Framesail? +

Register the Framesail MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Framesail tool call.

Deterministic rules across all 68 Framesail tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON FRAMESAIL →

Instant setup, no code required.

68 Framesail tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Framesail's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →