Intelliverse Router MCP Server
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Intelliverse Router MCP Server create a new app called MyApp"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Intelliverse Router MCP server + Agent Skills
Run the whole Intelliverse platform from any MCP-capable agent: create App IDs, mint tier API keys, ingest and search per-app knowledge bases, send email, generate media, check credits, and chat — without ever naming an LLM.
npx -y github:intelli-verse-x/router-mcpVerified 2026-07-12: initialize + tools/list over stdio, 15 tools.
Full setup guide with copy-paste configs: https://router.intelli-verse-x.ai/skills
Tools (15)
Tool | Auth | What it does |
| API key | Chat completion; |
| API key | Tier aliases your key can call |
| API key | LLM daily budget + per-App-ID media credit wallets |
| management | App IDs — entry point for KB, wallets, per-app costs |
| management | Tier-gated key administration |
| API key | App-scoped pgvector knowledge base |
| API key | Per-App-ID email via the platform engine (Pro+, |
| API key | Credit-metered image/video/voice/audio/3D jobs |
Env vars: ROUTER_API_KEY (Workspace → API Keys), ROUTER_MANAGEMENT_KEY
(Account → Management Keys; needed for app/key admin tools),
ROUTER_WORKSPACE_ID (default workspace for admin tools). Optional overrides:
EDGE_BASE_URL, KB_BASE_URL. Keys are free —
sign up, no card.
Related MCP server: AnythingLLM MCP Server
Install per platform
The JSON body is identical everywhere; only the file location / wrapper differs.
Cursor
One-click: Add to Cursor
— or .cursor/mcp.json (project) / ~/.cursor/mcp.json (global):
{
"mcpServers": {
"intelliverse-router": {
"command": "npx",
"args": ["-y", "github:intelli-verse-x/router-mcp"],
"env": {
"ROUTER_API_KEY": "iv-r-v1-...",
"ROUTER_MANAGEMENT_KEY": "ivm-...",
"ROUTER_WORKSPACE_ID": "your-workspace-uuid"
}
}
}
}Claude Desktop
Same JSON as Cursor, in claude_desktop_config.json
(macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\).
Claude Code
claude mcp add intelliverse-router \
--env ROUTER_API_KEY=iv-r-v1-... \
--env ROUTER_MANAGEMENT_KEY=ivm-... \
--env ROUTER_WORKSPACE_ID=your-workspace-uuid \
-- npx -y github:intelli-verse-x/router-mcpVS Code (GitHub Copilot)
.vscode/mcp.json:
{
"servers": {
"intelliverse-router": {
"type": "stdio",
"command": "npx",
"args": ["-y", "github:intelli-verse-x/router-mcp"],
"env": {
"ROUTER_API_KEY": "iv-r-v1-...",
"ROUTER_MANAGEMENT_KEY": "ivm-...",
"ROUTER_WORKSPACE_ID": "your-workspace-uuid"
}
}
}
}Windsurf
Same JSON as Cursor, in ~/.codeium/windsurf/mcp_config.json.
Cline
Same JSON as Cursor, via the MCP Servers panel → Configure MCP Servers
(cline_mcp_settings.json).
Continue
~/.continue/config.yaml:
mcpServers:
- name: intelliverse-router
command: npx
args: ["-y", "github:intelli-verse-x/router-mcp"]
env:
ROUTER_API_KEY: iv-r-v1-...
ROUTER_MANAGEMENT_KEY: ivm-...
ROUTER_WORKSPACE_ID: your-workspace-uuidOpenAI Codex CLI
codex mcp add intelliverse-router \
--env ROUTER_API_KEY=iv-r-v1-... \
--env ROUTER_MANAGEMENT_KEY=ivm-... \
--env ROUTER_WORKSPACE_ID=your-workspace-uuid \
-- npx -y github:intelli-verse-x/router-mcpChatGPT
ChatGPT developer-mode apps connect only to remote MCP servers over HTTPS; this server is stdio-only today, so there is no ChatGPT path yet (hosted streamable-HTTP endpoint is on the roadmap). In the OpenAI ecosystem use the Codex CLI above.
Agent Skills
skills/ ships SKILL.md playbooks that drive these tools end-to-end — copy them
into your agent's skills folder (~/.cursor/skills/ for Cursor,
~/.claude/skills/ for Claude Code):
Skill | What it does |
| Platform wiring — the 60-second create_app → key → KB loop |
| Scaffold web/mobile apps wired to an App ID |
| Honest-scope Nakama game-backend stubs |
| Electron/Tauri desktop apps delegating to IVX Agency |
| Real-time voice + lip-sync avatars over LiveKit |
git clone https://github.com/intelli-verse-x/router-mcp
cp -r router-mcp/skills/* ~/.cursor/skills/ # or ~/.claude/skills/The 60-second loop
create_app— describe your app; get an App ID and recommended tier.create_api_key— mint a key bound to that app.kb_ingest— feed it docs or URLs.chat/kb_chat— start building. No model names, ever.send_email— tell your users it's live.
Development
npm install && npm run build && node dist/index.jsserver.json at the repo root is the payload published to the official
MCP Registry as
io.github.intelli-verse-x/router-mcp (MCPB bundle from the GitHub release).
Available Tools
15 toolschatChat via Intelliverse RouterA
Send a chat completion. Never name an LLM — omit model (the Intelliverse default routes at your plan tier) or pass intelliverse/air, intelliverse/pro, intelliverse/pro-max, intelliverse/fusion.
Inputs: prompt (required), model, system.
create_api_keyCreate an API keyA
Mint a tier API key (air | pro | pro_max), optionally bound to an App ID and daily spend limit. The raw key is returned exactly once — store it.
Inputs: name (required), tier (required), app_id, workspace_id, +1 more.
create_appCreate an App IDB
Create an app (the entry point for knowledge bases, credit wallets, and per-app cost tracking). Returns the app id and a recommended tier based on the declared workload.
Inputs: name (required), use_cases (required), url, latency, +4 more.
generate_mediaGenerate mediaA
Generate image | video | voiceover | audio (music/sfx) | gen3d assets. Credits are held from the App ID's wallet and settled on completion. Returns a job — poll with media_job_status.
Inputs: kind (required), app_id (required), text, prompt, +2 more.
get_creditsGet budget and credit balancesB
LLM daily budget for the API key plus per-App-ID media credit wallets (image, video, voice, audio, audiobook, 3D).
Inputs: app_id.
kb_chatChat grounded in an app's knowledge baseA
RAG chat: retrieves relevant chunks for the App ID and answers with [doc:id] citations.
Inputs: app_id (required), prompt (required).
kb_documentsList knowledge base documentsB
List documents ingested for an App ID.
Inputs: app_id (required).
kb_ingestIngest into an app's knowledge baseA
Add documents (raw text or URLs — URLs are scraped) to the app's pgvector knowledge base. Chunks are embedded and become searchable memory for that App ID.
Inputs: app_id (required), documents (required).
kb_searchSearch an app's knowledge baseB
Semantic search over the app's chunks. Returns matches with similarity scores.
Inputs: query (required), app_id (required), top_k.
list_api_keysList API keysA
List API keys (prefixes only) with tier, app binding, and spend limits.
Inputs: workspace_id.
list_appsList App IDsC
List apps in the workspace with their recommended tiers and routing profiles.
Inputs: workspace_id.
list_modelsList available tiersA
List the tier aliases your API key can call. These are the only model strings that exist.
Inputs: no named parameters.
media_job_statusCheck a media jobC
Get status/output of a media generation job.
Inputs: id (required).
revoke_api_keyRevoke an API keyC
Permanently delete an API key by id.
Inputs: id (required).
send_emailSend email from an App IDA
Send transactional/newsletter email through the platform email engine (Pro plan+). Billed at the email.send10 SKU from the App ID's iv_credits wallet (hold → dispatch → settle); failed sends are never charged and partial batches settle on accepted recipients only.
Inputs: to (required), app_id (required), subject (required), reply_to, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 15 tools
Each tool targets a distinct domain: knowledge base (kb_*), app management, chat, models/credits, API keys, email, and media generation. Overlaps are minimal and well-defined.
Most tools follow a verb_noun pattern with underscores. Slight inconsistency: 'kb_documents' is a noun phrase while others are verb phrases. Otherwise consistent.
15 tools is appropriate for the broad scope covering knowledge base, chat, media, email, and API management. Each tool serves a clear purpose without redundancy.
Core operations are present (create, ingest, search, generate), but missing update/delete for apps and documents, and no cancel for media jobs. Notable gaps for full lifecycle.
Maintenance
Related MCP Connectors
Manage ElevenLabs voice agents and generate speech, music, sound effects, images, and video.
Email inboxes, webhooks, mock APIs, 2FA codes, approvals and 170 tools for AI agents.
Ask other AI models and generate images, speech, music and video from your coding agent.
Create and manage AI agents that collaborate and solve problems through natural language interacti…
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables interaction with Retell AI's voice and chat agent platform. Build, deploy, and manage AI phone agents, configure conversation flows, handle calls/chats, and manage phone numbers through natural language.52MIT
- AlicenseBqualityDmaintenanceEnables seamless integration with AnythingLLM instances, providing complete workspace management, chat operations, document handling, user administration, and AI agent configuration through natural language.3859 npm16MIT
- AlicenseCqualityDmaintenanceEnables AI agents to manage Vapi Voice AI platform resources such as assistants, calls, phone numbers, analytics, and workflows through natural language.343MIT
- AlicenseCqualityNot gradedmaintenanceEnables AI agents to interact with GoHighLevel's internal v2 API, managing Agent Studio, Voice AI, and Knowledge Base features through natural language commands.471MIT