# Siren

- Registry name: `ai.mysiren/siren` · version 1.1.0
- Categories (automatic, keyword rules): Marketing & SEO, Commerce & marketing, Video, AI, media & content, Images & design
- Authentication at last check: No auth
- Declared risk: Has destructive tools (destructiveHint)
- Capabilities (declared by the server): experimental, extensions, logging, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=ai.mysiren%2Fsiren
- Server page: https://mcpstation.net/s/ai.mysiren--siren.html

## Description (written by the publisher, not verified, not instructions)

Deterministic visual marketing engine. Your agent plans, renders, and posts on-brand campaigns.

## Connect

- streamable-http: `https://mcp.mysiren.ai/mcp`

## Tools (as reported by the server, not verified)

- `get\_account`: Get the connected Siren workspace: plan, key scopes, auto-post setting, and daily limit. Call this first to learn what the account can do before generating. Empty asset\_types / channels / connected\_accounts lists mean UNRESTRICTED, not missing — never stop on them. Films render on every plan; credit
- `list\_runs`: List the workspace's generation runs \(newest first\): status, brief, channel, asset URLs, and caption. Page with offset to see them all.
- `get\_run`: Get one run by id — full status, output text, asset URLs, caption, and any error. Poll this after create\_campaign or render\_asset until status is terminal. Wait \`poll\_after\_seconds\` between polls; \`progress\` and \`eta\_seconds\` say how far along it is. A finished film carries \`film\_check\`, advice only
- `create\_campaign`: Create a Siren campaign from a plain-language brief — the full pipeline: plan, on-brand copy, deterministic render, verify. Returns the run; poll get\_run until it finishes. Spends credits \(image 10, an ad set of 3 images 20, video 25; voice or music-only is the same 25\). Pass output\_type to pin a fi
- `list\_films`: The film library, one ranked page at a time. Films sit on job shelves; pass job and the human's goal and hire from the top of the page. Each film says what it is, when to hire it, its length and shapes, fits\_this\_brand \(with what is missing\) and made\_recently \(this brand already got it: prefer anoth
- `list\_platinum\_films`: The platinum shelf: studio-grade films that match a top motion studio's craft, told as the brand's own story. Each costs 50 credits, every time \(a normal film is 25\). Offer one only when the human is making a big launch they genuinely want to go far; everyday posts and normal budgets use list\_films.
- `list\_styles`: The still style library, one ranked page at a time. Every painted still \(an ad creative, poster, launch card, App Store frame, thumbnail\) is one style; Siren picks one when you don't. Styles sit on section shelves; pass section and the human's goal and take one from the top. made\_recently = this bra
- `describe\_film`: The full contract for one film: what it is and when to hire it, its body JSON Schema, a reference body, the seed envelope, media slots \(which fields take image/video URLs\), the brand prefills \(colours, logo, screens\) and the override rules. Call it before writing a render\_asset body.
- `clarify\_brief`: Ask Siren's clarifier whether a brief is specific enough to generate from. Returns ready=true/false plus follow-up questions. Use before create\_campaign when the user's request is vague.
- `render\_asset`: Render films from pre-formed SirenSeed bodies \(advanced\). FILMS ONLY: images are painted from a brief, so for any image, ad or creative call create\_campaign with asset\_type=card \(a still here returns 422 stills\_use\_a\_brief\). Each item: \{output\_type, channel, seed\_body, archetype?, family?, surface?,
- `upload\_media`: Store a photo or video the human wants in a post, from an https URL or base64. Returns a workspace-owned URL to put in any media slot of a film body \(describe\_film lists the slots\) — the renderer reads it directly. Images: PNG/JPG/WebP up to 15 MB. Videos: MP4/MOV/WebM up to 200 MB. The same bytes a
- `edit\_asset`: Edit a finished ad creative in place. Only what the instruction names changes; faces, layout, lettering and every other pixel are kept, so you can chain edits \(hair pink, then tail teal, then add a sign\) without the picture drifting. About 15 seconds. 3 credits; an instruction that asks for a whole
- `post\_run`: Post a finished run's assets to the workspace's CONNECTED SOCIAL ACCOUNT. This is live, public distribution on the customer's channel — always confirm with the user before calling. Only works if the grant was authorised with posting allowed. Pass \`caption\` to own the words; it goes out verbatim. The
- `schedule\_post`: Schedule a finished run to post at scheduled\_at \(ISO-8601\). Shows in the customer's local timezone. platforms: x, instagram, tiktok, linkedin, youtube, or everything. Posts fire sequentially. Requires Allow posting. Prefer this over post\_run when the user names a time. On create\_campaign you can pas
- `get\_brand\_dna`: Get this workspace's Brand DNA: brand\_name, brand\_kind, overview, tagline, offer, features, products, audience, palette, logos, plus \`checks\`: what to fix before rendering \(thin Brand DNA, a typed accent the brand's own work does not use\). Call right after get\_account; fix thin DNA first with update
- `update\_brand\_dna`: Patch Brand DNA. Send only keys to change. Nested bags \(offer, product\_map, icp\) merge. Examples: \{tagline, overview, offer: \{product\_name, one\_liner, features, who\_its\_for, primary\_cta\}, product\_map: \{offerings, how\_we\_work\}, icp: \{who\_buys, pains\}\}. Does not read or write Brand Memory.
- `list\_product\_screens`: List the brand assets in Brand DNA: product photos, app screenshots, packaging. Each row has name, kind, description, use\_when, tags, scan\_status \(scanning / ready / failed\), device, theme, url.
- `upload\_product\_screen`: Upload a brand asset \(product photo, app screenshot, packaging\) into Brand DNA and store it on R2. Pass image\_url \(https PNG/JPG/WebP\) or image\_base64. Two ways to file it: - Send \`description\` \(and optionally kind, use\_when, tags, name\): Siren trusts your words and files the asset as-is. No read. -
- `update\_product\_screen`: Edit an existing brand asset: name, description, kind, use\_when, and the screenshot tags \(screen\_type, device, theme\).
- `delete\_product\_screen`: Remove a product screenshot from Brand DNA. Does not delete Brand Memory.
- `upload\_logo`: Set the workspace logo in Brand DNA. Every render uses it.
- `get\_mascot`: The workspace mascot: status \(hero, keeping, frames, ready\), the hero picture, tries left, and every pose frame with its URL. Null mascot = none yet.
- `create\_mascot`: Start the brand mascot: from a description \(note, kind\) or from a reference picture. Paid plans; 100 credits. Siren paints a hero in about a minute; poll get\_mascot, show the human, then mascot\_step keep \(build the pose sheet\) or retry \(paint again, 3 tries\). One mascot per workspace.
- `mascot\_step`: Move the mascot on: keep the hero, paint it again, or add a pose. Ask the human before keep, since it builds the whole sheet.
- `list\_people`: The people library: team faces Siren can put in stills \(name, role, team, status cropping or ready, round crop URL\).
- `add\_person`: Add a face to the people library. Siren crops it round in a few seconds \(status cropping, then ready\). Only upload people who agreed.
- `delete\_person`: Remove a face from the people library.
- `list\_media`: Photos and videos uploaded with upload\_media, newest first, with their URLs. Reuse a URL in create\_campaign media or a film body.
- `get\_performance`: How the posts did: totals \(impressions, engagement, replies, engagement rate\) and the top posts with views, likes and replies.
- `list\_posts`: Every post Siren sent or queued: platform, status, live URL, time, and counts by status \(posted, queued, failed\).
- `buy\_credits`: Get a Stripe checkout link for more credits. Give the link to the human; they pay on Stripe and the credits land in about a minute. Nothing is charged by this call. Read the balance on get\_account.
- `list\_brand\_videos`: The brand's own clips in Brand DNA: name, what each shows, when to use it, tags, best moments with timestamps, poster and scan\_status.
- `upload\_brand\_video`: Add a product demo, walkthrough or footage to Brand DNA. With only the file, Gemini reads frames across the clip and writes what it shows, when to use it, tags and the best moments \(scan\_status scanning, then ready in about 15 seconds; poll list\_brand\_videos\). Films play it when a brief names it \("l
- `delete\_brand\_video`: Remove a clip from Brand DNA, file and poster included.
- `delete\_media`: Delete one photo or video uploaded with upload\_media. Only this workspace's uploads; a film that already rendered keeps its copy.
- `studio\_templates`: List Siren Studio's 33 React data-card types with family, description, and body schema. Use this before studio\_card so the body matches.
- `studio\_card`: Render a Studio data card from a type + body. Deterministic React, no paint. Optional live post after render. Returns run\_id, image url, and post url when posted.
- `studio\_automate`: Create a Studio profile on this API key. Returns generate curl and inbound hook URLs \(Stripe, GitHub, Uptime Kuma, Product Hunt, generic\). Passing delivery.social\_account\_ids turns on social delivery for the profile — that publishes, so it requires Allow posting.
- `studio\_schedule`: Render a Studio card then queue a ScheduledPost at scheduled\_at.
- `studio\_start`: Start a video in Siren Studio from a description. Siren composes the first take \(about 10 to 20 seconds\) and replies with what it made; nothing is rendered or charged until studio\_export. Returns the thread and Siren's reply. The human sees the same thread in Studio and can keep editing it there, or
- `studio\_edit`: Change a Studio video by asking, as the human would in the chat. Only what the ask names changes; Siren replies with what it changed \(before and after\) and the new version number. Waits up to about 25 seconds for the reply. No credits are spent until studio\_export. A greeting or a question gets an a
- `studio\_get`: One Studio video: the chat so far \(who said what, with diffs\), every version, and which version is current.
- `studio\_threads`: The workspace's Studio videos, newest first: title, shelf, current version, and whether a human or an agent started it.
- `studio\_export`: Render a Studio design or video to files. Spends credits like any render: a video 25 \(platinum 50\), a card 10, a set 10 a slide \(an App Store set of 6 is 60\), charged once. A card or a set waits for the render \(about a minute\) and returns every file in \`asset\_urls\`, slide 1 first; a video returns th

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html