_ registry / mcp http-sse · checked 50m ago

inbox-preview

https://api.powerline.ai

Registry code: d6ebdeea13a7883d

api record

Render HTML/.eml emails in real Gmail, Outlook & Yahoo web clients and screenshot them

from a public catalogue that lists it, not from the operator

endpoint
https://api.powerline.ai/v1/mcp
protocol
http-sse ·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 it live, free and safe measured by this hub
Is inbox-preview live?
Yes — it answered the hub's last check (checked 50m ago). It answered 100% of checks over the last 30 days.
Is inbox-preview free to use?
Yes — the hub reached it with no key and no payment.
What tools does inbox-preview have?
4 tools: get_screenshot, get_job, submit_preview, list_clients.
Is inbox-preview 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.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
814ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

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.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 4 tools
1 open 3 never probed 1 of 4 classified

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.

  • list_clients open 50m ago

    List the email clients this deployment can render right now, with their rendering tier, engine, and capabilities

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "properties": {}
    }
    arguments 5 lines
  • get_screenshot unknown 50m ago

    Fetch a rendered screenshot. Returns the image URL for the given job, client, width, and environment (color scheme / images).

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "job_id",
        "client",
        "viewport_width"
      ],
      "properties": {
        "client": {
          "enum": [
            "gmail",
            "outlook",
            "yahoo"
          ],
          "type": "string",
          "description": "Client ID"
        },
        "job_id": {
          "type": "string",
          "description": "The job ID"
        },
        "color_scheme": {
          "enum": [
            "light",
            "dark"
          ],
          "type": "string",
          "default": "light",
          "description": "The render's color scheme"
        },
        "viewport_width": {
          "type": "number",
          "description": "Viewport width of the render, matching the job (1280 when the job used client defaults)"
        },
        "images_disabled": {
          "type": "boolean",
          "default": false,
          "description": "Whether the render had images blocked"
        }
      }
    }
    arguments 42 lines
  • get_job unknown 50m ago

    Get the status and screenshots for a preview job. Poll until status is "completed".

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "job_id"
      ],
      "properties": {
        "job_id": {
          "type": "string",
          "description": "The job ID returned by submit_preview"
        }
      }
    }
    arguments 13 lines
  • submit_preview unknown never probed

    Submit an email for rendering across email clients — full HTML, or a complete raw .eml (base64). Provide exactly one of html/eml. Returns a job ID to poll for results.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "properties": {
        "eml": {
          "type": "string",
          "description": "A complete raw RFC 822 message (.eml), base64-encoded — inserted verbatim (real headers, multipart, attachments). Max 10MB decoded. Provide exactly one of html or eml."
        },
        "html": {
          "type": "string",
          "description": "The full email HTML to preview. Provide exactly one of html or eml."
        },
        "renders": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "client"
            ],
            "properties": {
              "client": {
                "enum": [
                  "gmail",
                  "outlook",
                  "yahoo"
                ],
                "type": "string",
                "description": "Client ID"
              },
              "color_scheme": {
                "enum": [
                  "light",
                  "dark"
                ],
                "type": "string",
                "description": "Render in the client's light or dark mode (default light). Dark must be supported by the client — check color_schemes in list_clients."
              },
              "viewport_width": {
                "type": "number",
                "description": "Viewport width in pixels (200-2560). Defaults to the client default (1280)."
              },
              "images_disabled": {
                "type": "boolean",
                "description": "Render with remote images blocked (default false)"
              }
            }
          },
          "description": "Exactly the renders you want, one entry each (e.g. outlook light + outlook dark are two entries). Omit for the server default: every live client at its default width, light."
        },
        "subject": {
          "type": "string",
          "description": "Email subject line"
        },
        "include_previews": {
          "type": "boolean",
          "description": "Also capture the inbox-list row (how the message looks unread in the list) and the subject heading, returned as inbox_preview / subject_preview on each render. Default false: they cost more than the body render itself, so ask only when you need them."
        },
        "include_full_page": {
          "type": "boolean",
          "description": "Also screenshot the whole client window around the opened email (the mailbox UI as well as the message), returned as full_page on each render next to the usual email-only screenshot. Default false. Best-effort: the render mailbox identity and any other mail are masked, and the capture is omitted when that cannot be verified."
        }
      }
    }
    arguments 63 lines
_ try it through the hub, ceiling 0

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.

_ is this your agent? claim it: badge, payouts, history

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.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. 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.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id d6ebdeea13a7883d.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/d6ebdeea13a7883d/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/d6ebdeea13a7883d/badge.svg)](https://brick.blue/agent/d6ebdeea13a7883d?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.

_ how we know
card completeness
80%

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.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
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.

_ also on powerline.ai 1 entry

Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.