A side-by-side look at the 370.ai — AI Gateway: Video (Seedance 2.0, Wan, HappyHorse), Image, Speech + 100+ Chat Models and Omnicord MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose for cloud platforms work; choose for communication as a local process. You can also run both side by side in one block.
mcpServersDISCORD_TOKEN.get_rate_limit_status, get_bot_info, run_setup_check.Rows where the two servers differ are marked.
| Spec | 3 370.ai — AI Gateway: Video (Seedance 2.0, Wan, HappyHorse), Image, Speech + 100+ Chat Models | |
|---|---|---|
| Category | Cloud Platforms | Communication |
| Quality signal | 37/100 · Fair | 65/100 · Great |
| Install command | Not confirmed yet | Confirmed |
| Transport | — | Local subprocess (stdio) |
| Auth | Not declared | API key required |
| Pricing | Not declared | Free |
| Required env vars | None listed | DISCORD_TOKEN |
| Verified owner | Community listing | Community listing |
| GitHub stars | — | 8 |
| Directory activity | 2 views 0 installs 0 upvotes | 9 views 0 installs 0 upvotes |
| Tools | Not listed | 155 |
| Full listing | View 370.ai — AI Gateway: Video (Seedance 2.0, Wan, HappyHorse), Image, Speech + 100+ Chat Models | View Omnicord |
No tool names declared yet. Check the project README from the listing page.
get_rate_limit_statusHow rate limiting has been going: how many times Discord asked Omnicord to slow down (the request layer waits automatically), and the invalid-request counter that matters because Discord temporarily bans an IP after 10,000 invalid responses in ten minutes. Useful when calls feel slow.get_bot_infoIdentity and status of a connected Discord bot: bot user, application, guild count, enabled gateway intents, and the Omnicord version. With more than one bot configured, pass bot to pick which (list_servers shows the configured bots). Use run_setup_check for a full health check with fix instructions.run_setup_checkEnd-to-end health check of the Omnicord setup: token presence and validity, privileged gateway intent toggles, guild count against Discord's verification thresholds, and default guild membership. Every failed check comes with instructions for fixing it. With more than one bot configured, pass bot to check a specific one. Run this first when anything misbehaves.get_server_overviewStructured snapshot of a server: identity, member counts, boost status, channel outline grouped by category, and role count. The natural first call when starting work on a server.list_channelsAll channels in a server grouped by category, with type and topic. Filter by type: text, voice, forum, stage, announcement, category.list_rolesAll roles in a server, highest first, with color, position, and a plain-language digest of their key permissions.read_messagesRecent messages from a channel as a digest: author, time, content, attachments, reactions, and resolved reply references. Returns oldest first. Use next_before to page further back.search_messagesSearch the server's message history through Discord's native search index. Covers every channel the bot can read, or one channel if you name it, and looks inside embeds and polls, not just plain text. Matching is whole-word full text, not substring, so search for words rather than fragments. Filter by author, by what a message carries (image, link, file, and so on), or by pinned state, and order by newest first or by relevance.search_membersFind specific members by a name fragment, or list those holding a given role. For the whole roster use list_members; for one member's full profile use get_member; to turn a fuzzy name into an id use find. Name search uses Discord's member search; role filtering walks the member list and reports if it hit the paging cap.get_memberOne member in detail: identity, nickname, roles by name, join date, and timeout state. Accepts a user ID or a name.findUniversal name resolver. Give it a name fragment and get ranked candidates across channels, roles, and members with their IDs. Use this when unsure what an entity is called or to grab an ID once and reuse it.send_messageSend a message to a channel, optionally as a reply, with embeds, or as a Components V2 layout of text, sections, image galleries, separators and link buttons inside colored containers. Components replace content and embeds rather than joining them, and the choice is permanent for that message. For a private message to one person use send_dm; to post under a custom name and avatar use send_webhook_message; to send later use schedule_message. Mentions are suppressed by default; raise the mentions mode only deliberately. Supports dry_run.Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
No confirmed install command for 370.ai — AI Gateway: Video (Seedance 2.0, Wan, HappyHorse), Image, Speech + 100+ Chat Models yet — follow the setup steps linked from its listing page rather than a guessed package name.
{
"mcpServers": {
"orygnscode-omnicord": {
"command": "npx",
"args": [
"-y",
"@orygn/omnicord"
],
"env": {
"DISCORD_TOKEN": "YOUR_DISCORD_TOKEN_HERE"
}
}
}
}