
Screenbird MCP server
Which MCP servers are Screenbird's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-27
- Registry nameapp.screenbird/screenbirdverified in the MCP registry
The registry name sits under screenbird.app. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-27
- Tools12
- Server calls itselfscreenbird
- Server version1.1.0
- Protocol version2025-06-18
On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 102 ms.
- Whether its tools do the product's job has not been judged yet.
Once connected
- create_design change data without a sign-in: anyone with the address can call them.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score80 of 100answers 100 · definitions 100 · context 100 · connects 100 · lowered by the warning signs below
- Answered100% of days8 of 8 daily checks
- Median first answer90 ms
- Space in an agent's context≈ 1,981 tokensthe definitions of all its tools (12), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 12 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · update menu boards and specials from a phone
- not sure · schedule promotions to appear on screens at set times
- not sure · show class timetables on reception screens
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
- Tools that change data, on a server that answers without a sign-in: create_design
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
list_screensList the connected team's screens: online status and what each screen and sub-screen shows right now (its normal content, pushed content, a scene or screen mirroring), with the end time if there is one. Also returns the account's time…
search_contentSearch the team's content that can be shown on a screen: files, designs, apps, split screens and playlists. Newest first. Returns the id, name and type of each item.
push_contentShow content on one screen, or on one sub-screen of a split screen, in place of what it shows now, until a time or until it is put back to normal. A split screen needs a subscreen_id. Returns what the screen shows afterwards. Content only…
release_screenEnd pushed content or a scene on one screen or sub-screen; it goes back to its own content.
list_scenesList the team's scenes in their order, with their state (live, partly live, changed since it went live, off) and which screens and sub-screens each scene sets (at most 20 targets per scene; targets_total is the real number). Results come…
activate_scenePut a scene live: every screen and sub-screen in the scene switches at once, in place of what it shows. Running it again puts changes to the scene live. A screen only shows the scene once it is online and has a player paired; each result…
release_sceneEnd one scene: its screens go back to their own content.
release_allEnd all scenes and all pushed content on the team's screens. Screen mirroring keeps running.
create_designCreate a design (a full-screen slide for a screen, such as a menu, an announcement or an event poster) from a description. It picks a fitting template, fills in the text and adds stock photos where the template has them; no images are…
search_helpSearch the Screenbird help center (how features work, setup, troubleshooting). Returns up to 3 articles with title, summary and link; set full to true for the complete text of each article.
get_install_stepsSteps to install the Screenbird player on a device type, ending with the pairing code that the user enters in the dashboard.
check_deviceCheck whether a device (as the user names it, for example "Samsung TV", "Chromecast", "iPad") works with Screenbird. Returns works, coming_soon, does_not_work, works_in_browser or unknown, with an explanation.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"screenbird": {
"type": "http",
"url": "https://mcp.screenbird.app/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http screenbird https://mcp.screenbird.app/mcpclaude.ai, ChatGPT and other clients: add https://mcp.screenbird.app/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.