About AlertForge
AlertForge’s Agent Plugin connects compatible agents to its hosted service for creating stream branding, animated overlays, AI alerts, and transparent video assets. It includes an approval-aware workflow and portable plugin metadata.
Key features
- 01Create coordinated stream branding
- 02Generate animated overlay packs
- 03Create AI stream alerts
- 04Produce transparent video assets
- 05Approval and credit checkpoints
Use cases
- 01Prepare a coordinated visual identity for a stream
- 02Generate overlays and alerts for a broadcast
- 03Create transparent video assets from visual direction
MCP support
Connects to AlertForge’s hosted MCP server at `https://alertforge.ai/api/mcp` over Streamable HTTP. The public `get_product_info` tool needs no authentication; other tools require OAuth 2.1 or an access key and an active paid subscription.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://alertforge.ai/api/mcpclaude mcp add --transport http lasan713-alertforge https://alertforge.ai/api/mcp{"mcpServers":{"lasan713-alertforge":{"type":"http","url":"https://alertforge.ai/api/mcp"}}}Open in Cursor{"servers":{"lasan713-alertforge":{"type":"http","url":"https://alertforge.ai/api/mcp"}}}Open in VS Code{"mcpServers":{"lasan713-alertforge":{"type":"http","url":"https://alertforge.ai/api/mcp"}}}{"mcpServers":{"lasan713-alertforge":{"serverUrl":"https://alertforge.ai/api/mcp"}}}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.
Tools
Details
From the project READMEAlertForge Agent Plugin
The official public integration package for AlertForge. It connects compatible AI agents to AlertForge's hosted MCP server for creating coordinated stream branding, animated overlay packs, AI stream alerts, and transparent video assets.
This repository contains only portable plugin metadata and workflow instructions. It does not contain AlertForge application source, customer data, credentials, executable hooks, or install scripts.
Included components
- A portable Agent Plugin manifest
- A Streamable HTTP MCP connection to
https://alertforge.ai/api/mcp - A workflow skill that preserves user approval and credit-confirmation checkpoints
- Compatibility metadata for clients that read Claude-style plugin manifests
Authentication and billing
The get_product_info tool is public. All other tools use AlertForge's OAuth 2.1 authorization-code flow with PKCE (or a revocable access key for older clients) and require an active paid AlertForge subscription. Creation uses the account's AlertForge credit balance; the tools quote costs before the corresponding create action.
No credentials are stored in this repository. OAuth-capable clients discover authentication from AlertForge's published metadata.
Data and network access
The plugin connects only to https://alertforge.ai. Depending on the user's request, the hosted service may process:
- prompts and visual direction supplied by the user;
- user-selected reference-image URLs;
- the user's AlertForge projects, asset status, and credit balance; and
- generated images, videos, overlay packages, and signed download links.
The plugin does not read local files, environment variables, SSH keys, browser data, or unrelated repositories. It does not execute local commands or install dependencies.
See the agent setup guide, privacy policy, terms, and support page.
Validation
Validate the JSON files with any JSON Schema-aware editor. Claude Code users can also run:
claude plugin validate .
The hosted MCP server can be checked without authentication by initializing it and listing its tools. Paid creation should only be tested with an authorized AlertForge-owned QA account.
License
The metadata and instructions in this repository are licensed under the MIT License. The AlertForge service, product source, branding, and generated assets are governed separately by AlertForge's terms.
Comments
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.