# Vaaya (remote · vaaya.ai)

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

- Trust score: 70/100 (medium)
- Change this week: +9
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `vaaya.ai`: 70/100 (this document), [markdown](https://verifymcp.io/servers/ai-vaaya-mcp/vaaya.md), [page](https://verifymcp.io/servers/ai-vaaya-mcp/vaaya)
- npm · `@vaaya/mcp`: 35/100, [markdown](https://verifymcp.io/servers/ai-vaaya-mcp/vaaya-mcp.md), [page](https://verifymcp.io/servers/ai-vaaya-mcp/vaaya-mcp)

## Channel facts

- Endpoint: `https://vaaya.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.3.3`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 94/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 26/100
  - AI-judged instruction clarity (poor).
  - Context-footprint check failed: tool/resource definitions use about 1987 tokens (~220/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http ai-vaaya-mcp https://vaaya.ai/mcp
```

### Codex

```toml
[mcp_servers.ai-vaaya-mcp]
url = "https://vaaya.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-vaaya-mcp": {
      "type": "remote",
      "url": "https://vaaya.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-vaaya-mcp --url https://vaaya.ai/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-vaaya-mcp:
    url: "https://vaaya.ai/mcp"
```

### Other

```json
{
  "mcpServers": {
    "ai-vaaya-mcp": {
      "type": "http",
      "url": "https://vaaya.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 68, +5)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 61, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 61)

First indexed and scored.

## MCP tools (9)

### `vaaya_test_connection` (~84 tokens)

Test Vaaya Connection

Round-trip ping that confirms the agent → Vaaya connection and whether the user is linked. Returns { ok:true, userId, scope, version, server_time } when linked, or { 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).

Output parameters:

- `instructions` (string): What to tell the user to get connected.
- `needs_auth` (boolean): True when this agent is not linked to a Vaaya user yet.
- `ok` (boolean): True when the agent is linked to a Vaaya user.
- `scope` (string): Space-separated authorized scopes.
- `server_time` (string): Server time, ISO 8601.
- `signup_uri` (string): Where a new user signs up.
- `userId` (string): Linked Vaaya user id.
- `verification_uri` (string): Where the user approves the connection.
- `version` (string): Server version.

### `vaaya_onboard` (~65 tokens)

Get Onboarding Instructions

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.

Output parameters:

- `already_linked` (boolean): True when the agent is already connected.
- `instructions` (string): What to tell the user to get connected.
- `message` (string): Status message to relay to the user.
- `needs_auth` (boolean): True when this agent is not linked to a Vaaya user yet.
- `signup_uri` (string): Where a new user signs up.
- `verification_uri` (string): Where the user approves the connection.

### `vaaya_account` (~134 tokens)

Show Connected Account & Balance

Show which Vaaya account this connection is linked to and its money state. Returns { email, name, user_id, connected_client, scopes, balance_cents, premium_allowance, credits_url, switch_account }. Call it whenever the user asks "which account is connected", "what's my balance", "how much premium/media credit is left", or "how do I switch accounts" — and relay the answer. `premium_allowance` is the gated free-tier ledger for premium services (media generation, enrichment, compute, scraping): it is SEPARATE from wallet balance, and only credit-pack purchases raise it.

Output parameters:

- `balance_cents` (number): Wallet balance remaining, in cents.
- `connected_client` (string): OAuth client name this connection was made through.
- `credits_url` (string): Where the user buys credit packs.
- `email` (string): Email of the connected Vaaya account.
- `instructions` (string): What to tell the user to get connected.
- `name` (string): Display name of the connected user.
- `needs_auth` (boolean): True when this agent is not linked to a Vaaya user yet.
- `ok` (boolean): True when the call succeeded.
- `premium_allowance` (object): Gated free-tier state for premium services: cap, purchased, spent, remaining (cents). Separate from wallet balance.
- `scopes` (array): Authorized scopes for this connection.
- `signup_uri` (string): Where a new user signs up.
- `switch_account` (string): How to connect a different account — relay to the user.
- `user_id` (string): Vaaya user id.
- `verification_uri` (string): Where the user approves the connection.

### `vaaya_logout` (~85 tokens)

Disconnect / Switch Vaaya Account

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).

Output parameters:

- `error` (string): Error code/message when ok=false.
- `logged_out` (boolean): True when the authorization was revoked.
- `message` (string): What happened — relay to the user.
- `ok` (boolean): True when the call succeeded.
- `to_switch_account` (string): Exact steps to reconnect with a different account — relay verbatim.

### `consult` (~356 tokens)

Consult Vaaya — Plan Any Capability

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) — it returns result-aware, Vaaya-grounded next steps to offer the user (the `call` result's `after_running` field reminds you). Call consult whenever you hit a capability gap or the user wants to know what's possible. It does NOT execute or bill — you run returned calls via `use`. ALWAYS show the user consult's `message` and `suggestions` and let them steer.

Input parameters:

- `intent` (string, required): Plain-English description of what you want, or your answer to a previous clarify question. Be concrete — include the prompt text, URL, budget, or target the task implies.

Output parameters:

- `after_running` (string): Reminder to call consult again with the outcome.
- `calls` (array): Ordered list of { service, action, params, max_cost_cents, why } to run via `use`.
- `if_tools_missing` (string): What to do when a named first-party tool (gtm_*, worker_*, …) is missing from your tool list: it was just unlocked — refresh the tool list; never improvise a fallback.
- `if_use_unavailable` (string): What to do when the `use` tool is missing from your tool list — relay to the user.
- `message` (string): Consultant's reply — relay to the user verbatim.
- `mode` (string): How to proceed: relay 'converse', run 'call', or report 'unsupported'.
- `reason` (string): Why the request is unsupported (mode='unsupported').
- `run_with` (string): Which tool to execute the calls with.
- `suggestions` (array): 2-3 suggested next steps to surface to the user.

### `use` (~275 tokens)

Execute a Paid Service Call

Execute a single call that `consult` handed you, 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. Always get the exact (service, action, params, max_cost_cents) from `consult` first — don't guess them.

Input parameters:

- `action` (string, required): Action within the service (e.g. "search", "generate", "create_session"), taken from the call `consult` returned.
- `intent` (string): Optional: the one-line `why` from the consult call you're running (or the user's goal for it). Used only for internal transaction visibility — it never affects validation, billing, or execution. Pass…
- `max_cost_cents` (number, required): Hard ceiling in cents on what you will be charged. `use` refuses if the registry price exceeds this. Pick at least 2× the listed price so retries work.
- `params` (object, required): Parameters from the call `consult` returned, validated against the service's registered schema.
- `service` (string, required): Service identifier, taken verbatim from the call `consult` returned.

Output parameters:

- `async` (boolean): True when the job runs asynchronously — poll with `result`.
- `balance_remaining_cents` (number): Wallet balance remaining, in cents.
- `charged_cents` (number): Amount billed for this call, in cents.
- `data`: Upstream result payload (URLs, text, ids, …).
- `error` (string): Error code/message when ok=false.
- `job_id` (string): Async job id for `result` polling.
- `ok` (boolean): True when the call succeeded.
- `protocol` (string): Settlement rail used (x402 / mpp / ledger).
- `status` (number): Upstream HTTP status when the call failed.
- `transaction_id` (string): Vaaya transaction id for this call.

### `result` (~263 tokens)

Poll an Async Job

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).

Input parameters:

- `job_id` (string, required): The job_id returned by an async `use` call.

Output parameters:

- `balance_remaining_cents` (number): Wallet balance remaining, in cents.
- `charged_cents` (number): Amount billed for this call, in cents.
- `error` (string): Error code/message when ok=false.
- `hint` (string): Human-readable progress summary.
- `job_id` (string): The polled job id.
- `ok` (boolean): True when the call succeeded.
- `progress` (object): Progress detail (e.g. percent) while running.
- `result`: Final output when succeeded.
- `status` (string): Job state.

### `session` (~188 tokens)

Run Code in a Sandbox 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.

Input parameters:

- `code` (string): Code to execute (alternative to `command`).
- `command` (string): Shell command to run in the sandbox.
- `language` (string): Language for `code`: python (default), javascript, or bash.
- `session_id` (string, required): The session_id returned by create_session.

Output parameters:

- `error` (string): Error code/message when ok=false.
- `exit_code` (number): Process exit code.
- `ok` (boolean): True when the call succeeded.
- `result`: Structured result, when the runtime returns one.
- `stderr` (string): Captured standard error.
- `stdout` (string): Captured standard output.

### `close` (~79 tokens)

Close a Sandbox Session

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).

Input parameters:

- `session_id` (string, required): The session_id to close.

Output parameters:

- `balance_remaining_cents` (number): Wallet balance remaining, in cents.
- `charged_cents` (number): Total metered uptime cost, in cents.
- `error` (string): Error code/message when ok=false.
- `ok` (boolean): True when the call succeeded.
- `session_id` (string): The closed session id.
- `status` (string): Final session state.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-vaaya-mcp/vaaya#diagnostics

## Score history

- 2026-08-03: 70
- 2026-08-02: 69
- 2026-08-01: 69
- 2026-07-31: 68
- 2026-07-30: 63
- 2026-07-29: 63
- 2026-07-28: 62
- 2026-07-27: 61
- 2026-07-26: 61

## Links

- Remote endpoint: https://vaaya.ai/mcp
- Repository: https://github.com/vaaya-ai/vaaya-mcp
- Website: https://vaaya.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-vaaya-mcp/vaaya/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-vaaya-mcp/vaaya/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-vaaya-mcp/vaaya