Tella MCP server
Yes. Tella publishes an official MCP server at https://api.tella.com/mcp. It's hosted and lets you sign in with your Tella account. It offers 116 tools. We last checked it on 22 Nov 2026.
Official: answers MCP requests at api.tella.com, on Tella's own domain tella.com. Checked 22 Nov 2026. Maintained by Stuart Brameld.
Key facts
As of 22 Nov 2026, Tella's official MCP server scores 85/100 on MartechDB's Agent Readiness Index (v1.1), joint 17th of 48 in Video. It answered 55 of our 55 checks in the last 90 days and has 116 tools named in its documentation.
How the Agent Readiness Index works · Wrong? Suggest a correction
Tella MCP server review
85/100
Tella's MCP server scores 85/100 on MartechDB's Agent Readiness Index: one of the easiest marketing tools to connect an AI agent to. That ranks it joint 17th of 48 in Video.
The good
Hosted by Tella: connect by URL, with nothing to install
Sign in with your Tella account: your AI client sets up the sign-in itself, with no API key
Documented, with 116 tools known
Published to the official MCP Registry
Answered 100% of our checks in the last 90 days
The bad
Nothing we've found.
Official MCP server
Tella MCP server
- Address
- https://api.tella.com/mcp
- Runs
- Hosted
- Sign-in
- Cost to use
- 100 requests a minute per user per workspace, shared with API; video analytics 30 a minute per workspace.From Tella's own page
- Official MCP Registry
-
Listed as
com.tella/product· published 21 Nov 2026 - How we know it's official
-
- Answers MCP requests at api.tella.com, on Tella's own domain tella.com.
- Documentation
- www.tella.com/docs/mcp-server
- Tools
- 116 tools · from Tella's documentation
- First seen
- 1 Oct 2026
- Last checked
-
Reachable ·
16 Nov 2026: reachable17 Nov 2026: reachable18 Nov 2026: reachable19 Nov 2026: reachable20 Nov 2026: reachable21 Nov 2026: reachable22 Nov 2026: reachable
- Uptime
- 100% · 55 of 55 checks reachable since 1 Oct 2026
Tella MCP server tools (116)
The server needs sign-in before it lists its tools, so these are as Tella's documentation names them (read 2 Oct 2026). They may be out of date.
-
list_videosList all videos in your workspace with pagination support.
-
search_videosSearch your direct video library by title or indexed transcript sentences. Use `searchIn` to restrict the search to `title` or `transcript`; otherwise title results come before transcript results.
-
get_videoGet video information. Returns summary fields by default. Use include flags for additional data.
-
get_timelineGet an ordered outline of a video's complete timeline in one call. Start here when reading or editing a video: the default response identifies every clip, its position and playback duration, and counts its cuts, layouts, effects, overlays, sound effects, and transcript words. Use `include` only for the details needed next, instead of calling every per-clip list tool.
-
create_videoCreate a new video from an uploaded source. Call `create_source` first (`kind: "video"`), `PUT` the bytes to the returned `uploadUrl`, then pass the `sourceId` here — it becomes the new video's first clip.
-
update_videoUpdate video metadata and settings.
-
list_subtitle_presetsList Tella's built-in subtitle styles and your saved styles. Each result includes a `presetId`, name, scope (`default` or `personal`), and a `captionStyle` preview.
-
apply_subtitle_presetApply a built-in or saved subtitle preset to a video. This changes the subtitle appearance without changing the transcript or enabling subtitles.
-
save_subtitle_presetSave a subtitle look as a personal preset, like the editor's "Save as preset". Pass `videoId` to snapshot that video's current subtitles (style, font, weight, size, position, grouping and lines per block), `captionStyle` to build one from scratch on the style's defaults, or both — explicit caption fields, including the font, size and lines per block, override the video's. The preset then shows up in `list_subtitle_presets` (scope `personal`) and in the editor's Subtitles panel, and can be applied to other videos with `apply_subtitle_preset`.
-
get_captions_fileGet ready captions as SRT or WebVTT text. Returns `format`, `fileName`, and `content`.
-
delete_videoDelete a video (moves to trash).
-
duplicate_videoCreate a copy of a video. Supports trimming to extract a time range or specific chapter.
-
export_videoStart a video export. Use `get_export_status` to poll until the export completes or fails.
-
get_export_statusGet an export's current status and progress. Poll this after `export_video` until `export.status` is `completed` or `failed`; `export.downloadUrl` appears when the export is ready.
-
add_collaborator_to_videoAdd a collaborator to a video. The user must be a member of your workspace.
-
update_collaborator_on_videoChange a collaborator's role on a video.
-
remove_collaborator_from_videoRemove a collaborator from a video.
-
list_playlistsList all playlists in your workspace.
-
create_playlistCreate a new playlist.
-
get_playlistGet detailed information about a playlist. Outside your workspace, you can only access a playlist with an ungated public link.
-
update_playlistUpdate playlist metadata and settings.
-
delete_playlistDelete a playlist.
-
add_video_to_playlistAdd a video to a playlist.
-
remove_video_from_playlistRemove a video from a playlist.
-
list_playlist_groupsList sidebar playlist groups.
-
create_playlist_groupCreate a sidebar group to organize playlists into.
-
update_playlist_groupRename a playlist group, change its icon, or move it within its sidebar section.
-
delete_playlist_groupDelete a playlist group.
-
move_playlist_to_groupMove a playlist into a group, or remove it from its group.
-
list_tagsList all tags visible to you: the workspace's shared tags plus your private tags.
-
create_tagCreate a tag for categorizing videos. When no color is given, one is derived from the name.
-
update_tagUpdate a tag's name, color, and/or description. Private tags can only be updated by their creator.
-
delete_tagPermanently delete a tag and remove it from all videos.
-
list_video_tagsList the tags on a video that are visible to you.
-
add_video_tagTag a video. Requires edit access to the video. Adding a private tag only affects your own library.
-
remove_video_tagUntag a video. Requires edit access to the video.
-
list_webhooksList your webhook subscriptions, with cursor pagination.
-
update_webhookUpdate a webhook subscription's URL, event filters, or delivery status. Provide at least one of `url`, `filterTypes`, or `disabled`.
-
publish_to_socialStart a publish to one destination. Returns immediately with a `queued` publication. One publish per destination runs at a time; starting another while one is `queued` or `running` returns a `conflict` error. Publishing again after one completes creates a second post.
-
list_social_publicationsThe latest publish of a video to each destination, including publishes made in the Tella app (TikTok among them). Poll this after `publish_to_social`.
-
get_video_analyticsViewing analytics for one video: summary, plays per day, retention per one-percent slice, geography, referrers, UTM traffic sources, and call-to-action clicks. Available for videos you created, collaborate on, or that are shared with your workspace.
-
get_workspace_analyticsViewing analytics aggregated across videos: by default every video shared with the workspace, or with `scope: "mine"` only the videos you created. Returns the summary, plays per day, retention, geography and referrer breakdowns, plus `topVideos` ranked by plays. Only `topVideos` is paginated — pass `pagination.nextCursor` as `cursor` for the next page.
-
apply_video_editsUse `apply_video_edits` whenever you need two or more timeline edits. It takes up to 200 mixed operations across any clips in one video, validates the whole request, and applies it as a single editor revision — substantially faster than repeated single-edit calls. For one edit, the standalone tool is still the convenient choice.
-
create_sourceCreate a new source upload. Returns a `sourceId` and a pre-signed `uploadUrl` — `PUT` the file bytes to `uploadUrl` (the URL expires after 1 hour).
-
get_sourceGet a source's processing status by its `sourceId`, however it was placed. After placing a newly uploaded video or audio source, poll this every few seconds until it is `ready`: while it is still processing, frames and previews of videos that use it answer not-ready instead of rendering.
-
list_libraryList placeable media for one scope. Media still being generated is omitted.
-
capture_screenshotCapture a public web page or a single post on X, Instagram, LinkedIn or TikTok. Web pages are captured above the fold at 1920×1080; social posts are cropped to their embed card. Private pages and social profiles or feeds are not supported.
-
add_library_itemSave an uploaded source to the library. Call `create_source` first, `PUT` the bytes to the returned `uploadUrl`, then pass the `sourceId` here.
-
remove_library_itemRemove an item from the library. This removes the library entry only — clips already using the underlying source keep working.
-
generate_imageGenerate a landscape image (2048×1152) from a text prompt. Usually takes 30-90 seconds. Once complete, place the item's `sourceId` with `add_overlay` for an image overlay, or with `add_layout` (`media: {type: "image", sourceId}`) for a b-roll still.
-
generate_sound_effectGenerate a short sound effect from a text prompt, for when Tella's curated catalog (`list_library` with `scope: "default"`) has nothing suitable. Usually takes 10-30 seconds. Once complete, place the item's `sourceId` with `add_sound_effect` (as `sourceId`, not `presetId`).
-
get_generation_statusPoll this after a generate tool until `generation.status` is `completed` or `failed`. While it is `pending` or `running`, wait a few seconds and call again. On `completed`, `generation.item` is the finished library item — pass its `sourceId` to `add_overlay`, `add_sound_effect`, `add_layout` or `apply_video_edits`. On `failed`, `generation.error` provides a sanitized, human-readable reason that may identify a content-safety rejection or timeout, or report a generic failure. Do not parse this text for machine handling; start a new generation.
-
list_backgroundsList available backgrounds in named categories. Each item includes a descriptive `name`, a `thumbnailUrl` for previewing, and a `background` object for applying to a clip. Built-in names, such as `Red Horizon` or `Plum Horizon`, match the names shown when you hover over backgrounds in the editor.
-
get_chaptersGet every chapter on a video, ordered by timestamp.
-
set_chaptersReplace every chapter on a video. Timestamps must be non-negative, ascending, and within the video duration. Pass an empty `chapters` array to clear all chapters.
-
upload_clipAdd a new clip to a video from an uploaded source. Call `create_source` first, `PUT` the bytes to the returned `uploadUrl`, then pass the `sourceId` here.
-
list_clipsList clips in a video, ordered by their position.
-
get_clipGet a single clip's details.
-
update_clipUpdate a clip's name, ordering, cuts, background, transition, Studio Sound opt-out, audio volumes, animated cursor, or frame styling (corner rounding and border style).
-
delete_clipRemove a clip from its video.
-
duplicate_clipDuplicate a clip. The copy is inserted right after the original by default.
-
reorder_clipMove a clip to a new position; other clips shift to stay contiguous.
-
cut_clipCut one or more time ranges from a clip in a single call. Overlapping or adjacent ranges are merged into the clip's existing cuts. To clear all cuts, call `update_clip` with `cuts: []`.
-
cut_clip_by_transcriptCut one or more ranges from a clip by referencing word indices in the transcript. The server resolves each word's exact start/end ms — no padding is applied. Use `get_transcript` to look up word indices.
-
get_silencesDetect silent ranges in the clip's audio, in ms on the clip's playback timeline (cuts applied) — pass them directly to `cut_clip`. Silences already removed by cuts are not reported.
-
remove_fillersAuto-detect and cut filler words ("um", "uh", etc.) from the clip's transcript.
-
remove_silencesAuto-detect and cut silent pauses from the clip's audio, like the editor's Remove silences tool.
-
list_sourcesList the underlying recordings (camera, screen, mic) the clip was cut from, each with the volume it plays at in this clip: `volume` is the clip's own override (`null` when it inherits) and `effectiveVolume` is what actually plays. Read these to inspect a mix; change it with `update_clip`'s `microphoneVolume`/`systemAudioVolume`.
-
get_clip_frameGet a rendered frame from a clip's playback timeline (cuts applied), including the clip's layouts, b-roll media, zooms, and masks. For `jpg`, `png`, or `webp`, returns inline image content the model can see, plus a signed URL. For `gif`, returns the signed URL only (vision models don't read animation, so the bytes aren't inlined).
-
get_clip_previewGet an MP4 preview from a clip's rendered playback timeline. The tool waits up to a minute for the render and returns a signed `url` rather than inline video content.
-
get_video_frameGet a rendered frame from an entire video's playback timeline. It returns the same processing results and accepts the same frame format and sizing options as `get_clip_frame`.
-
get_video_previewGet an MP4 preview from an entire video's rendered playback timeline. The tool waits up to a minute for the render and returns a signed `url` rather than inline video content.
-
get_storyboardGet a fixed 4×4 WebP storyboard whose 16 tiles are sampled evenly across the requested window (`durationMs`/16 apart; every 5 seconds for the default 80s window).
-
set_video_thumbnailSet a video's thumbnail. Two modes, mutually exclusive:
-
remove_video_thumbnailRemove a video's custom thumbnail (uploaded image or picked frame) and revert to the default auto-generated thumbnail.
-
get_source_thumbnailGet a thumbnail of a specific source recording. For `jpg`, `png`, or `webp`, returns inline image content plus a signed URL; for `gif` or `mp4`, returns the signed URL only.
-
get_source_waveformGet the waveform data for a source recording's audio track. Pass `videoId` with `clipId` for a source on a clip, or `sourceId` alone for a source in your workspace that isn't on any clip yet.
-
get_transcriptTranscript for the clip (cuts applied — what the viewer hears). Word indices are stable identifiers for `cut_clip_by_transcript`; they don't shift when cuts change. To see words that were cut out, clear the cuts first (`update_clip` with `cuts: []`) — cuts are always undoable.
-
update_transcript_wordsFix what the transcript says. Each edit addresses one word by its `index` from `get_transcript` and sets `text` (the corrected wording, which also unhides the word) or `hidden` (whether the word shows in captions and subtitles). You can send `text` with `hidden: false`, but not with `hidden: true`. Returns the edited words in their new state.
-
list_saved_layoutsList your saved Favorite layouts. Each result includes an ID, name, scene type, and whether it is a preset or custom layout. Custom layouts also report the canvas ratio they require and their geometry as a `kind: custom` `layout`.
-
apply_saved_layoutApply one of your saved Favorite layouts to a clip. Omit the time range to set the clip-spanning base layout, or provide both `startTimeMs` and `durationMs` to apply it to part of the clip.
-
save_layoutSave a clip's layout as a Favorite, like the editor's star on a layout tile. Omit `layoutId` to save the clip-spanning base layout, or pass a layout ID from `list_layouts`.
-
list_layoutsList the layouts on a clip, including the synthetic base layout (the layout that spans the whole clip). Custom layouts report their geometry as `kind: custom`. Each layout reports the `crop` of the clip's screen recording it shows. Every layout other than `base` reports `followsBase`: `true` when it follows the base layout, so updating `base` changes it too; `false` when it has its own layout.
-
add_layoutAdd a layout to a clip. Pass `startTimeMs` + `durationMs` for a time range, or omit both for a clip-spanning layout.
-
update_layoutUpdate a layout on a clip. Only provided fields change.
-
remove_layoutRemove a non-base layout from a clip. Use `update_layout` to change the base layout.
-
generate_auto_layoutsLet AI watch the clip and lay it out — the same as the editor's "Auto layouts". The AI picks an editing style (or follows `style`), sets the clip's base layout, and adds time-ranged layout changes. Generation watches the actual video, so this can take on the order of a minute for longer clips.
-
auto_cropAutomatically crop a clip's screen recording based on the content visible at a selected frame. The result includes the applied crop, confidence, detected aspect ratio, and the resolved source frame.
-
set_background_musicSet or replace the video's background music track, from Tella's curated music or from your own audio.
-
remove_background_musicRemove the video's background music track.
-
list_zoomsList zooms on a clip.
-
add_zoomAdd a zoom to a clip.
-
update_zoomUpdate an existing zoom. Only provided fields change.
-
remove_zoomRemove a zoom from a clip.
-
generate_auto_zoomsAutomatically generate tracking zooms from the mouse clicks in the clip's screen recording — the same as the editor's "Generate zooms". Every click opens a zoom window; nearby windows are merged. Requires the clip to contain a screen recording; returns an empty list when it has no usable mouse clicks.
-
get_mouse_eventsGet the mouse events from the clip's screen recording. Move events are sampled (clicks are always kept); events during cut-out footage are dropped. Returns an empty list when the recording has no mouse data (camera-only clips, uploads, older recorder versions).
-
list_blursList blur masks on a clip.
-
add_blurAdd a blur mask to a clip.
-
update_blurUpdate an existing blur.
-
remove_blurRemove a blur from a clip.
-
list_highlightsList highlight masks on a clip.
-
add_highlightAdd a highlight mask to a clip.
-
update_highlightUpdate an existing highlight.
-
remove_highlightRemove a highlight from a clip.
-
list_overlaysList the image and video overlays on a clip. Each result includes its `zIndex` in the shared image, video, text, and Lottie overlay stack, from 0 (back) upward. Lottie overlays share the stack but aren't listed, so the reported positions can skip a number.
-
add_overlayAdd an image or video overlay on top of a clip. Call `create_source` first (`kind: "image"` or `kind: "video"`), `PUT` the bytes, then pass the returned `sourceId` — the overlay type follows the source's kind. When `point`/`dimensions` are omitted, a centered box is computed from the source.
-
update_overlayUpdate an existing overlay. Only provided fields change.
-
remove_overlayRemove an overlay from a clip.
-
list_text_overlaysList the text overlays on a clip. Image and video overlays are listed separately by `list_overlays`. Each result includes its `zIndex` in the shared image, video, text, and Lottie overlay stack, from 0 (back) upward. Lottie overlays share the stack but aren't listed, so the reported positions can skip a number.
-
add_text_overlayAdd a text overlay on top of a clip.
-
update_text_overlayUpdate an existing text overlay — its copy, font, text color, background, timing, position, size, transition, or depth. Only provided fields change.
-
remove_text_overlayRemove a text overlay from a clip.
-
list_sound_effectsList the sound effects on a clip.
-
add_sound_effectAdd a sound effect to a clip, from Tella's curated library or from your own audio.
-
update_sound_effectUpdate an existing sound effect. Only provided fields change.
-
remove_sound_effectRemove a sound effect from a clip.
Connect your AI to Tella
Add the official Tella MCP server to Claude, ChatGPT or your editor.
Connect Tella MCP to Claude
Claude.ai and Claude Desktop
Open Customize, then Connectors.
Click +, then Add custom connector.
Name it Tella, paste the address below and click Add.
Connect Tella MCP to ChatGPT
Open Settings, then Apps, then Advanced settings.
Turn on Developer mode, then click Create.
Name it Tella and paste the address below.
Connect Tella MCP to Cursor
Opens Cursor if it's installed. If nothing happens, use the JSON below.
Connect Tella MCP to VS Code
Opens VS Code if it's installed. Otherwise add the JSON settings from the Cursor tab to your .vscode/mcp.json.
Tella MCP server questions
Does Tella have an official MCP server?
Yes. Tella publishes its MCP server itself. Its address is on Tella's own domain (api.tella.com). MartechDB only lists servers a vendor publishes, never community copies.
What is the Tella MCP server URL?
The address is https://api.tella.com/mcp.
Does the Tella MCP server need an API key?
No. You sign in with your Tella account (OAuth), and your AI client handles the rest.
How do I connect Tella MCP to Claude, ChatGPT or Cursor?
In Claude, add https://api.tella.com/mcp as a custom connector (Customize, Connectors, Add custom connector). In ChatGPT, turn on developer mode (Settings, Apps, Advanced settings) and create an app with the same address. In Cursor, use the Add to Cursor link on MartechDB's page, or paste the JSON settings into your mcp.json. In Claude Code, run: claude mcp add --transport http tella https://api.tella.com/mcp
What can the Tella MCP server do?
It offers 116 tools, including list_videos, search_videos, get_video, get_timeline and create_video (as its documentation names them, read on 2 Oct 2026).
Is the Tella MCP server in the official MCP Registry?
Yes, as com.tella/product.
Is the Tella MCP server working?
Yes. It answered our most recent check. We last checked it on 22 Nov 2026.
What are the alternatives to Tella's MCP server?
In Video, the most agent-friendly alternatives with an official MCP server are Summify (97/100), vidIQ (95/100), Video Highlight (95/100), Zebracat (94/100) and Video To Blog (92/100). Tella scores 85/100 on the same index.
Alternatives to Tella's MCP server
Vendors in Video with an official MCP server, the most agent-friendly first. Tella scores 85/100.
Summify
summify.io
vidIQ
vidiq.com
Video Highlight
videohighlight.com
Zebracat
zebracat.ai
Video To Blog
videotoblog.ai
Change history
What we've seen change for Tella, newest first.
-
Tella: Tella MCP server added to the official MCP Registry
Use with AI
Connect your AI to MartechDB
Then ask it about Tella, or any of the 1,850 marketing tools with an official MCP server. Free, no sign-in.
Claude.ai and Claude Desktop
Open Customize, then Connectors.
Click +, then Add custom connector.
Name it MartechDB, paste the address below and click Add. There's no sign-in.
The free plan allows one custom connector. On Team and Enterprise plans, an owner adds the connector first.
Claude Code
Run this in your terminal:
ChatGPT
Open Settings, then Apps, then Advanced settings.
Turn on Developer mode, then click Create.
Name it MartechDB, paste the address below and choose No authentication.
Developer mode is on Plus and Pro plans, and on Business, Enterprise and Edu if an admin allows it.
API
The same data as JSON, with no sign-in. See the OpenAPI description for every endpoint and field.
CLI
Search the directory and print the command to connect a vendor's server, from your terminal. Needs Node 18 or later. View on npm
Show that your MCP server is verified
If you work at Tella, add this badge to your MCP docs or README. It's free, it's the same for every vendor, and it updates from our daily checks: it shows uptime while the server responds, and says so if it stops.
Something wrong or out of date? Suggest a correction or email us, and we'll check it against the evidence. Every correction we make is listed on Corrections.