
Unmerge MCP server
Which MCP servers are Unmerge'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 2026-10-29
- Registry nameapp.unmerge/unmergeverified in the MCP registry
The registry name sits under unmerge.app. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-29
- Tools4
- Server calls itselfunmerge
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 112 ms.
- Whether its tools do the product's job has not been judged yet.
Once connected
- For "split a flat poster into named transparent layers", the likely first call is split_into_layers.
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 score100 of 100answers 100 · definitions 100 · context 100 · connects 100
- Answered100% of days7 of 7 daily checks
- Median first answer178 ms
- Space in an agent's context≈ 507 tokensthe definitions of all its tools (4), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- can do · split a flat poster into named transparent layers
- not sure · export separated layers as a layered PSD or PNG zip
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
None of the five warning signs in these definitions.
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 →
split_into_layersSplit a flat image (PNG, JPG or WebP) into named transparent layers, with the hidden parts behind objects filled in. Costs 1 credit per layer returned (at most 17); the account needs at least 5 credits to start. Pass the image as a public…
get_layersStatus of a split. When ready, returns every layer with its name, position and a PNG download URL valid for one hour. Free.
unlock_layersFor a split with status needs_credits: pay the extra credits owed (shown as credits.owed) so the layer files become available. Charges once even if called again.
get_creditsCredits available on this Unmerge account. One credit is one layer returned.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"unmerge": {
"type": "http",
"url": "https://unmerge.app/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http unmerge https://unmerge.app/mcpclaude.ai, ChatGPT and other clients: add https://unmerge.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.