mcpField
O
OgForge

OgForge

Remote
ogforge.mike-tusa.workers.devMedia & Design

About OgForge

Render 1200x630 Open Graph social preview images from templates; returns a cacheable PNG URL.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://ogforge.mike-tusa.workers.dev/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://ogforge.mike-tusa.workers.dev/mcpAuth required

Tools

1
ParameterTypeRequiredDescription
bgstringNoBackground hex color, e.g. 0f172a.
fgstringNoText hex color.
logostringNoPublic https:// URL of a PNG, JPEG or SVG logo (max 512 characters, 300 KB). Fetched by OgForge's server.
sitestringNoSite or brand name, e.g. "example.dev". Max 60 characters (longer text is truncated with "…").
emojistringNoOne emoji, e.g. 🚀
labelstringNoSmall pill or tag, e.g. "Engineering". Max 40 characters (longer text is truncated with "…").
themeenumNoColor scheme (default depends on the template).light | dark
titlestringYesHeadline, e.g. "How we cut API latency by 60%". Max 120 characters (longer text is truncated with "…").
accentstringNoAccent hex color.
authorstringNoAuthor or byline. Max 60 characters (longer text is truncated with "…").
subtitlestringNoSecondary line / description. Max 200 characters (longer text is truncated with "…").
templateenumNoLayout (default blog).blog | launch | docs | minimal | gradient
include_imagebooleanNoAlso return the PNG inline as MCP image content (default false; usually 30-150 KB).

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.