saypix
Registry code: 0f664a3691101189
Edit photos with a plain-words instruction using the user's Saypix credits. List models, check balance and estimate cost first. Get the user's approval for the instruction and credit spend before edit_image. Use a unique requestId for each intended edit. Identical retries reuse that id for 24 hours. Never retry an uncertain submission with a new id; inspect https://saypix.io/dashboard/history first. To keep editing a result, pass its taskId as parentTaskId instead of uploading again. Poll get_edit_status at most once every 5 seconds. Never invent completion or an image URL. Private tools need…
- endpoint
- https://saypix.io/api/mcp
- protocol
- streamable-http ·2025-06-18
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is saypix live?
- Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
- Is saypix free to use?
- Not measured yet.
- What tools does saypix have?
- 6 tools: upload_image, list_edit_models, estimate_edit_cost, get_credit_balance, edit_image, get_edit_status.
- Is saypix safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 100%· all time 100%
last good check
of 6 tools
- unknown → live
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
upload_image unknown never probed
Upload and moderate a PNG/JPEG/WebP photo to edit. Provide raw base64 (no data URL), maximum 3 MiB decoded. Use the returned url as imageUrl in edit_image. Requires a key. Clients with file/shell access can instead POST multipart file to https://saypix.io/api/upload with the same Bearer key; do not ask the language model to transcribe image bytes.
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "required": [ "base64", "mimeType" ], "properties": { "base64": { "type": "string", "pattern": "^[A-Za-z0-9+/]*={0,2}$", "maxLength": 4194304, "minLength": 4 }, "mimeType": { "enum": [ "image/png", "image/jpeg", "image/webp" ], "type": "string" } } }arguments 24 lineslist_edit_models unknown never probed
List Saypix image-edit models, what each is good at, credits per edit and supported aspect ratios. Public; no key needed.
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }arguments 5 linesestimate_edit_cost unknown never probed
Return the exact credit cost of one edit with a model. Free; does not edit or reserve credits.
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "required": [ "model" ], "properties": { "model": { "type": "string", "maxLength": 80, "minLength": 1, "description": "Exact model id from list_edit_models." } } }arguments 15 linesget_credit_balance unknown never probed
Read your spendable Saypix credit balance. Requires a key.
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }arguments 5 linesedit_image unknown never probed
Start a paid edit with user approval and an exact expectedCredits quote. Give imageUrl from upload_image, or parentTaskId to keep editing an earlier result. Required requestId deduplicates identical retries for 24h; never use a new id to retry an uncertain submission. Returns taskId.
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "required": [ "model", "requestId", "prompt", "expectedCredits" ], "properties": { "model": { "type": "string", "maxLength": 80, "minLength": 1, "description": "Exact model id from list_edit_models." }, "prompt": { "type": "string", "maxLength": 1000, "minLength": 1, "description": "The edit instruction in plain words, e.g. \"Change the background to a sunny beach\"." }, "imageUrl": { "type": "string", "format": "uri", "maxLength": 2048, "description": "url returned by upload_image. Give this OR parentTaskId." }, "requestId": { "type": "string", "pattern": "^[a-zA-Z0-9_-]{16,80}$", "description": "Unique submission id, e.g. a UUID. Reuse for identical retries within 24 hours; never change after an uncertain outcome." }, "aspectRatio": { "enum": [ "auto", "1:1", "4:3", "3:4", "3:2", "2:3", "16:9", "9:16" ], "type": "string", "default": "auto", "description": "\"auto\" keeps the photo's shape." }, "parentTaskId": { "type": "string", "maxLength": 200, "minLength": 1, "description": "Keep editing an earlier successful edit of yours: its result becomes the source image." }, "expectedCredits": { "type": "integer", "maximum": 9007199254740991, "description": "Exact cost from estimate_edit_cost.", "exclusiveMinimum": 0 } } }arguments 62 linesget_edit_status unknown never probed
Check your own edit. Poll no faster than every 5 seconds. On success returns imageUrl of the edited PNG and its step page; failed edits are refunded automatically. Requires a key.
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "required": [ "taskId" ], "properties": { "taskId": { "type": "string", "maxLength": 200, "minLength": 1 } } }arguments 14 lines
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's id0f664a3691101189.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/0f664a3691101189/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/0f664a3691101189?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.