The visual install guide for Claude, Cursor, ChatGPT and Manus is at getvamos.ai/mcp. This article is the reference: tools, limits, host behaviour, billing and troubleshooting.

The tools

Your AI client picks the right one from what you ask. You do not call them directly.

chat_completion_start Starts a turn in the background and returns a run id at once. Add include_data when you want the answer's videos, ads and creators as rows.
Spends credits: Yes, on completion
chat_completion_poll Checks a run. Long-polls, so it returns as soon as the status changes.
Spends credits: No
chat_completion_cancel Aborts a run so credits stop accruing.
Spends credits: No
set_up_workspace Sets up a new, empty workspace from your accounts, website and offer, in its own chat.
Spends credits: Yes, on completion
create_chat Starts a new Vamos conversation and returns its id. It can open the chat in another of your workspaces.
Spends credits: No
list_chats Lists your chats, so the AI can continue one rather than starting fresh. It can list another of your workspaces too.
Spends credits: No
get_messages Reads a chat's history. Also how to check whether a timed-out turn already finished.
Spends credits: No
get_credit_usage Your remaining credits and plan.
Spends credits: No
auth_status Whether the session is authenticated, and the sign-in URL if not.
Spends credits: No

A completion has the same reach as the web app: video search, web search, profile and post analysis, comment pulls. It writes using your voice and your memories from Brain.

What search covers: Instagram, TikTok and YouTube. Ask and it will also go after YouTube long-form and Facebook Ads. LinkedIn, X and Facebook can be read from a link but cannot be searched.

The using-vamos skill

For Claude Code, install the using-vamos skill alongside the MCP. It teaches Claude how to call Vamos well rather than merely that it can.

Download it from getvamos.ai/skill, put it at ~/.claude/skills/using-vamos/SKILL.md, and restart Claude Code. It activates when you ask about social media.

What it adds over a bare MCP connection:

Continues an existing chat rather than starting a new one each time.
Sends your whole request as one message instead of fanning out.
Passes Vamos's answer through with its links intact.
Asks for rows only when you want them in a sheet or a pipeline.
On a timeout, checks whether the turn already finished before retrying.

The skill is Claude Code only for now.

What you cannot do

No file upload and no doc editing. Those stay in the web app.

No streaming. You get the full answer when Vamos finishes, which is anywhere from a few seconds to 15 minutes.

Rows on request. By default you get Vamos's written answer. Ask for the data and chat_completion_start or get_messages returns the videos, ads and creators the answer cites as JSON and CSV, with up to 10 transcripts, at no extra credits. Full comment dumps stay in the chat in the web app.

Retries are not free. Re-running a completion runs the whole job again and bills again. On a timeout, call get_messages first.

Using more than one workspace

You choose a workspace when you sign in, and that is the connection's default. To work in another of your workspaces, name it in your request. The AI opens or lists chats there, and credits come from that workspace.

Host behaviour on long tasks

Every client works the same way: the request starts a run, and the client polls until the answer is ready. Research usually takes 2 to 8 minutes, and a run stops at 15.

Nothing streams while it works. Most clients show the polling, and ChatGPT and Cursor can sit silent until the result returns. On those, break big requests into smaller ones.

Manus and other agents may retry hard, and each new start bills. Cap retries at one.

Billing

MCP runs on the same credits as the web app and costs no extra.

Only chat_completion_start and set_up_workspace spend. Everything else is free. A background run bills when it completes even if you stop polling, so cancel rather than abandoning it.

Out of credits returns ERR_INSUFFICIENT_CREDITS. On an active paid plan, buy extra credits in Settings, under Billing. A locked workspace or an ended plan returns ERR_WORKSPACE_LOCKED, even with credits left.

Troubleshooting

The AI is writing for the wrong workspace. Name the workspace in your request, or sign out of the Vamos MCP in your client and reconnect to change the default.

Nothing seems to be happening in Cursor. Cursor does not show much while it polls. Give it 15 minutes, then check your credit balance.

My agent is burning credits. Some agents retry failed calls, and each retry re-runs the completion. Set a retry cap of one.

The skill will not activate. Check the path is exactly ~/.claude/skills/using-vamos/SKILL.md, restart, and ask something explicitly about social media.

The AI told me to open a dashboard page that does not exist. It hit an auth error and invented navigation. Ask it to call auth_status, which returns the real sign-in URL, or reconnect in your client's connector settings.

Can I revoke access? Sign out of the MCP server in your client, or click Disconnect beside it in Vamos, under Settings, then Connectors.

Does it work for a team? Each person authenticates with their own account. There is no shared key.

Which plan do I need? Any plan with credits, Free included. A locked workspace or an ended plan is refused.

MCP reference