door_acff25cbe9fb
Stylica — Generate images with AI (agent door via Bubblio)
Should I use this
Quality & Safety
Findings (2)
- LOWTool 'about' description lacks action verbin about
- LOWTool 'ask' description lacks action verbin ask
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"door_acff25cbe9fb": {
"url": "https://api.bubblio.dev/agent/door_acff25cbe9fb/mcp"
}
}
}Remote endpoints
https://api.bubblio.dev/agent/door_acff25cbe9fb/mcpstreamable-httpWhat it can do
Tool inventory
Tools (5)
⚪about
What this platform is and what visiting agents may do here.
Input Schema
{
"type": "object",
"properties": {},
"required": []
}⚪ask(question)
Ask about this platform: capabilities, pricing, policies. Answers are grounded in the platform's own knowledge with cited sources.
Input Schema
{
"type": "object",
"properties": {
"question": {
"type": "string",
"description": "The question, in plain language (max 2000 chars)."
}
},
"required": [
"question"
]
}🟢list_actions
List the actions this platform has registered for visiting agents: name, description, parameters (JSON Schema), and whether each needs an agent key. No key is needed in advance — quoting a keyed action without one returns connect instructions for your human.
Input Schema
{
"type": "object",
"properties": {},
"required": []
}🟢quote(tool, args, agent_key)
Get a quote for one action call. The quote pins the exact tool + args and returns a quote_id for confirm. Nothing executes until confirm. Quotes expire after 10 minutes.
Input Schema
{
"type": "object",
"properties": {
"tool": {
"type": "string",
"description": "An action name from list_actions."
},
"args": {
"type": "object",
"description": "Arguments for the action, matching its parameters schema (max 16KB)."
},
"agent_key": {
"type": "string",
"description": "Optional agent key, minted by a user account on this platform. Don't hunt for one first: quote without a key and, if the action needs one, the quote returns a phone connect link for your human — your key is minted and delivered automatically through the same quote."
}
},
"required": [
"tool"
]
}⚪confirm(quote_id, agent_key, wait_seconds, payment_credential, payment)
Execute a quoted action. Confirming executes this action exactly once. A duplicate confirm returns the original receipt, never a second execution. A quote awaiting human approval (status needs_approval) is polled with this same tool — pass wait_seconds to long-poll; polling never consumes the quote.
Input Schema
{
"type": "object",
"properties": {
"quote_id": {
"type": "string",
"description": "The quote_id returned by quote."
},
"agent_key": {
"type": "string",
"description": "The same agent key the quote was made with. Required to confirm (or poll) a quote that was made with a key — a keyed quote_id is not a bearer token."
},
"wait_seconds": {
"type": "number",
"description": "For quotes awaiting human approval or payment: how long to wait (0–25s) before answering awaiting_human / awaiting_payment. Ignored once the quote is ready."
},
"payment_credential": {
"type": "object",
"description": "Paid actions only: { type, token } — a rail from the quote's payment profile (e.g. type \"stripe_spt\" with an spt_… token) plus the opaque payment token for it. NEVER a card number. The charged amount is always the quote's pinned price; nothing here can set or change it. Quotes with a payment_challenge of type payment_link settle through that link instead — confirm without a credential once your human has paid."
},
"payment": {
"type": "object",
"description": "Compat alias for payment_credential: { rail, token }. Present one or the other, never both."
}
},
"required": [
"quote_id"
]
}Community
Evidence