Koskamo

Powerline Inbox Preview MCP

This MCP server allows AI agents to render HTML emails or .eml files in real, logged-in web clients for Gmail, Outlook, and Yahoo Mail to generate pixel-accurate screenshots. It also provides tools for email deliverability checks, including domain health, SPF, DKIM, DMARC, and blacklist verification, enabling agents to validate email rendering and authentication records.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Powerline Inbox Preview MCP logo, by PowerlineVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by Powerline
MCP endpoint (Streamable HTTP)
https://api.powerline.ai/v1/mcp
Vendor documentation

What its tools do

4 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

4 of 4 have a description · 0 of 4 declare behavior hints · 3 of 3 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to powerline.ai ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Render HTML emails in real Gmail, Outlook, and Yahoo sessions
  • Generate pixel-accurate screenshots of email rendering
  • Check email domain health and deliverability scores
  • Validate SPF, DKIM, and DMARC records

Source and maintenance

Vendor evidenceRegistry 0.1.0

Protocol and capabilities

Server
inbox-preview 0.1.0
MCP protocol negotiated in check
2025-11-25
Tools
4 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Tools

4 advertised

list_clients
Advertised by the server during the last successful anonymous check.

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

list_clients input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}
submit_preview
Advertised by the server during the last successful anonymous check.

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.

submit_preview input schema
{
  "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."
    }
  }
}
get_job
Advertised by the server during the last successful anonymous check.

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

get_job input schema
{
  "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"
    }
  }
}
get_screenshot
Advertised by the server during the last successful anonymous check.

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

get_screenshot input schema
{
  "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"
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
273 ms
95th percentile latency
273 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 273 ms · metadata changed · 4 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http powerline-inbox-preview-mcp https://api.powerline.ai/v1/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add powerline-inbox-preview-mcp --url https://api.powerline.ai/v1/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable powerline-inbox-preview-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "powerline-inbox-preview-mcp": {
      "url": "https://api.powerline.ai/v1/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "powerline-inbox-preview-mcp": {
      "type": "streamableHttp",
      "url": "https://api.powerline.ai/v1/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start powerline-inbox-preview-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "powerline-inbox-preview-mcp": {
      "type": "http",
      "url": "https://api.powerline.ai/v1/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http powerline-inbox-preview-mcp https://api.powerline.ai/v1/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://api.powerline.ai/v1/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "powerline-inbox-preview-mcp": {
      "serverUrl": "https://api.powerline.ai/v1/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Powerline Inbox Preview MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Do you run Powerline Inbox Preview MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing