ai.vaaya/mcp

Description and use

Pay-per-call agent superpowers: media/video gen, product demos, research, GTM, scraping, compute.

Compatible agents

• Claude Desktop
• Claude Code
• Hermes
• Codex CLI

Capabilities

close: Close an E2B sandbox session and stop its billing. Pass the session_id. Captures the final metered uptime cost and releases the hold. ALWAYS call this when finished with a session — an open session keeps billing per second of uptime. Safe to call repeatedly (idempotent).

consult: Vaaya's consultant. Describe ANY external capability you or the user might want — generate an image/video, search or scrape the web, run code in a sandbox, send/receive email, enrich a contact — and it helps figure out the best way, teaching the user what Vaaya can do. It is CONVERSATIONAL and remembers prior turns. It returns: mode='converse' (a reply to RELAY to the user verbatim — questions, options, ideas; get the user's response and call consult again with it, so the conversation continues), mode='call' (an ordered list of calls to run via use, with a message explaining the preferred choice + alternatives + why; multi-step results may contain placeholders like '<from step 1: sandbox_id>' — run earlier steps first and substitute), or mode='unsupported'. Every reply includes suggestions (2-3 things to do next) — surface these to the user. AFTER you run a call result's calls via use, call consult ONE more time with a short note on the outcome (what was produced / any failures

docs: Vaaya's deep reference, FREE and instant. Pass topic to get the full playbook for a capability area — exact services, actions, params, prices, model lists, and gotchas — the same reference files the vaaya skill ships. Topics: 'media' (image/video/audio models + product-demo videos), 'gtm' (leads, enrichment, outreach, signals, email), 'research' (OneSearch lanes, deep research, company/market research playbooks), 'data' (scraping, people, social platforms, public records, onchain, compliance), 'compute' (sandboxes, browser automation, files, memory, workers, phone calls, llm). Read the matching topic BEFORE non-trivial work in that area — it is cheaper than a wrong call. Never bills; safe to call any time.

llm: Ask a DIFFERENT LLM a question and get its answer, billed per token from the Vaaya wallet (model cost + 3%, usually a fraction of a cent). Use it to get a second opinion from a rival model, cross-check an answer, summarize a huge blob cheaply, or query a specific model the user names (Kimi, GPT, Gemini, Claude, DeepSeek, and 300+ more). model accepts 'auto' (default: short prompts go cheap, long go mid), 'cheap' | 'mid' | 'best' tiers, or any exact OpenRouter slug like 'moonshotai/kimi-k3'. Typical costs: cheap tier well under 0.1 cents, best tier 1-3 cents per call. Not for the conversation you are already having — it is a one-shot ask to another model.

result: Fetch the status + output of an async job started by use (e.g. a video render). Pass the job_id that use returned with { async: true }. Returns { status, result?, progress?, charged_cents }: running (still working — when the job reports it, progress carries { phase, percent, rendered_frames, total_frames, eta_sec } and hint is a one-line summary like "rendering 42% (380/900 frames, ~120s left)", so you can tell real progress from a hang; wait a bit and call again), succeeded (result holds the output, e.g. the video URL; the call is charged now), or failed/cancelled (no charge; on failed, read error AND hint — hint carries the service's usage notes, which usually explain how to fix the call). Safe to call repeatedly — it never starts new work or double-charges. ALWAYS use this to retrieve an async result instead of re-running use (re-running starts a new paid job).

session: Run a command or code in an open E2B sandbox session (started by use with action create_session, which returns a session_id). Pass session_id plus either command (a shell command) or code (+ optional language: python/javascript/bash). Returns stdout/stderr/exit_code (or the code result). The sandbox stays alive — and billed per second of uptime — until you close it; re-running reuses the SAME box, so filesystem + process state persist between calls. ALWAYS close when done.

use: Execute a single external call, and bill on success. Used for any external capability (image/video/audio generation, web search, scraping, email, document parsing, code sandbox, browser automation, embeddings, etc.). The server validates params against a registered schema and proxies to the upstream — you never pass URLs or API keys. Call it directly when you know the exact (service, action, params, max_cost_cents) — from the vaaya skill's catalog or a call you've made before; when unsure, get the call from consult rather than guessing.

vaaya_account: Show which Vaaya account this connection is linked to and its money state. Returns { email, name, user_id, connected_client, scopes, balance_cents, credit_line, available_cents, credits_url, switch_account }. Call it whenever the user asks "which account is connected", "what's my balance", "how much credit is left", or "how do I switch accounts" — and relay the answer. credit_line is the card-backed credit the account can spend past its prepaid balance (a $2 welcome line plus any GitHub-score line); available_cents = balance + active line, the number calls are gated on.

vaaya_logout: Disconnect this client from the current Vaaya account: revokes this connection's authorization server-side, so every later call fails with 401 until the user reconnects. Call it when the user asks to log out, sign out, disconnect, or switch Vaaya accounts — then relay the returned switch steps VERBATIM (the browser sign-out step is what actually enables switching accounts).

vaaya_onboard: Public onboarding hint for an agent whose user isn't linked to Vaaya yet. Returns where the human should go to connect (and sign up if new). Call this when vaaya_test_connection reports needs_auth, or any tool returns unauthorized, then relay the instructions to the user. If the user IS already linked it returns first_call instead — show first_call.show_to_user as written so they know what to try.

vaaya_test_connection: Round-trip ping that confirms the agent → Vaaya connection and whether the user is linked. Returns { ok:true, userId, scope, version, server_time, first_call } when linked — SHOW first_call.show_to_user to the user as written, it is the same set of starter examples the website and installer give them. Returns { ok:false, needs_auth:true, verification_uri, signup_uri, instructions } when not linked yet — relay that to the user so they can connect (and sign up if new).

streamable-http: Transport declared by the upstream MCP registry.

Installation

1. npx -y @vaaya/[email protected]

Limitations and review notes

Discovered metadata only; install commands are stored for review but never executed by AtlasRepo.