What is the Vamos MCP?
MCP (Model Context Protocol) is the universal way AI tools talk to external services. The Vamos MCP server lets any MCP-compatible AI client — Claude Code, Claude Desktop, Cursor, ChatGPT, Manus, Codex — call Vamos directly from inside that tool.
Translation: ask Claude Code (or whichever AI you live in) to run Vamos research, write a script with your Brand Voice, or pull comments from a TikTok — without ever switching tabs.
All work runs against your existing Vamos workspace: your Brand Profile, Brand Voice, Memory, and credits.
Setup
The server endpoint is the same for every client:
First connection opens a browser window for Vamos sign-in (OAuth 2.1 + PKCE — same login as app.getvamos.ai). After that the client stores the token and reconnects silently.
Claude Code
One command:
claude mcp add --transport http vamos-mcp https://mcp.getvamos.ai/mcp
Claude Desktop / Cursor / Codex / Manus / others
Add a remote MCP server in the client's settings with:
Transport: StreamableHTTP (sometimes labelled "HTTP" or "remote")
Auth: OAuth (the client handles it — just sign in when prompted)
Each tool's UI is slightly different but the values are the same. If the client only supports stdio, it isn't compatible with the Vamos MCP yet.
What you can do
The MCP exposes 5 tools. Your AI client picks the right one automatically based on what you ask.
Tool | What it does |
| Runs a full Vamos AI chat turn — research, analysis, scripts, captions. Has access to all Vamos tools (video search across TikTok / Instagram / YouTube / LinkedIn / X / Facebook / Threads, web search, profile and post analysis, comment pulls) and writes using your Brand Voice and Memory. |
| Starts a new Vamos conversation and returns its |
| Lists your existing Vamos chats so the AI can continue an earlier conversation. |
| Reads message history from a chat — useful for follow-ups or summarising past research. |
| Returns your remaining workspace credits and plan tier. |
You don't call these directly. You just chat with your AI tool — "use Vamos to find the top 10 finance Reels this week" — and it picks the right tool.
What you can't do (yet)
No image generation, file upload, or Canvas edits. Those stay in the Vamos web app.
No streaming text. Vamos returns the full answer once the agent finishes (30 sec – 5 min depending on the task). Some clients show progress, some go silent until done — see the host table below.
No raw tool results. The MCP returns the agent's prose. Things like full search-result JSON, transcripts, or comment dumps live only inside the chat in app.getvamos.ai.
No workspace switching mid-session. The token is bound to your active workspace at sign-in. Switched workspaces in the Vamos app? Sign out and back in inside your AI client to refresh.
Not idempotent. Retrying a call re-runs the agent and re-bills credits. Don't loop on errors.
Common workflows
1. Research while you're already coding / writing
You're in Claude Code building something and need creator data:
"Use Vamos to find the top 5 TikToks about morning routines this month and summarise the hooks."
Vamos runs the search, returns the analysis, and Claude keeps coding with that context.
2. Generate a script in your Brand Voice
"Use Vamos to write a 60-second YouTube Short script about productivity, in my voice."
Brand Voice and Memory load automatically — no toggles, no pasted samples.
3. Continue an existing Vamos chat
"List my recent Vamos chats and continue the one about the launch campaign."
The AI calls list_chats, picks the right one, and resumes from there.
4. Competitor deep-dive
"Pull @[creator]'s last 30 Reels via Vamos, analyze hook patterns, and tell me what they're testing."
5. Check credits before a heavy task
"What's my Vamos credit balance?" → AI calls get_credit_usage.
Host compatibility
Not every AI client treats long-running tools the same. Use this to set expectations.
Client | Live progress? | UX on long tasks |
Claude Desktop | Yes | Shows live progress mid-call |
Claude Code | Yes | Shows live progress mid-call |
Codex | Partial | Depends on the version |
Cursor | Minimal | Shows little until done |
ChatGPT | No | Silent until result returns |
Manus / autonomous agents | Varies | May retry aggressively — re-bills credits per retry |
Tip: on ChatGPT and Cursor, expect up to 5 minutes of silence on heavy research prompts. Break large requests into smaller asks.
Billing & credits
MCP calls run on your workspace credits — same pool as the web app.
Pricing matches the web app — the MCP doesn't cost extra. AUTO model selection still applies.
Read-only tools (
list_chats,get_messages,get_credit_usage) don't deduct credits. Onlychat_completionspends.Run out of credits? The tool returns
ERR_INSUFFICIENT_CREDITS— top up at Settings → Billing.
FAQ
Do I need to install anything else? No. The Vamos MCP is hosted — no local server, no API key, no scraping setup. Just the URL.
Which Vamos plan do I need? Any paid plan with credits. The MCP is included on Pro and Business.
Can I use it on free / trial? Yes, while you have trial credits. After credits run out you'll get ERR_INSUFFICIENT_CREDITS until you upgrade or top up.
I switched workspaces in the Vamos app — why is the AI still writing for the old one? The MCP token is bound to your active workspace at sign-in. Sign out of the MCP in your AI client and reconnect.
Why did my call time out? The MCP has a 5-minute hard cap. The chat is preserved — open it in app.getvamos.ai, see what the agent finished, and continue there.
Can I revoke access? Yes — sign out of the MCP server inside your AI client, or contact us to revoke server-side.
Does it support team / multi-user setups? Each user authenticates with their own Vamos account, so each teammate connects independently. There's no shared MCP key.
Questions? Chat widget or [email protected].