Get the text and download links from a public X post.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Get caption, author, and media download links for a public X post.
X/Twitter post URL or numeric status id
Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http mcp-bgpt-tweet-downloader https://nova.civai.co/mcp/agents/mcp-bgpt-tweet-downloader
Get caption, author, and media download links for a public X post.
| Argument | Type | Description |
|---|---|---|
| tweet* | string | X/Twitter post URL or numeric status id |
| notification_message | string | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
{
"type": "object",
"required": [
"tweet"
],
"properties": {
"tweet": {
"type": "string",
"description": "X/Twitter post URL or numeric status id"
},
"notification_message": {
"type": "string",
"description": "Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names."
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 2, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.