Ellora is answering right now. Last checked 3 min ago.
Check drafts against your voice profile and writing brief, and cut the AI slop before you publish.
Today is the operative word: we check Ellora every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 3 min ago.
claude mcp add ellora --transport http https://api.getellora.com/v1/external/mcp
https://api.getellora.com/v1/external/mcp
[mcp_servers.ellora]
url = "https://api.getellora.com/v1/external/mcp"
{
"mcpServers": {
"ellora": {
"url": "https://api.getellora.com/v1/external/mcp"
}
}
}
{
"servers": {
"ellora": {
"type": "http",
"url": "https://api.getellora.com/v1/external/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.getellora.com/v1/external/mcp | streamable-http | sign-in | 233 ms | 3 min ago |
Check AI-written drafts against your source documents, with the passage behind every verdict.
Save drafts, publish posts in your Follore space, and file issues of the columns you run.
Draft posts in your own voice from saved business context and check every draft before you post.
Check packages for CVEs, slopsquatting, and CISA KEV before your AI agent installs them.
Learns your writing voice locally and rewrites AI drafts so they sound like you.
Your writing voice measured across 45 attributes; drafts in that voice, scored against it.
Local-first social MCP: an agent drafts and schedules posts; you approve before anything publishes.
Check that a source really says what your claim says, before you publish. Verbatim, multi-path.
Answers built from our own checks of this server.