# xyz.getava/ava (remote · api.getava.xyz)

Coding agents run multi-leg cross-chain DeFi. Legs re-derived from your sentence before signing.

- Trust score: 81/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `api.getava.xyz`: 81/100 (this document), [markdown](https://verifymcp.io/servers/xyz-getava-ava/api.md), [page](https://verifymcp.io/servers/xyz-getava-ava/api)

## Channel facts

- Endpoint: `https://api.getava.xyz/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.5.1`

## 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 2026-09-20.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2794 tokens (~186/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 97/100
  - Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 83/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 50% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "ava_approve_execute" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the xyz.getava/ava MCP server?

xyz.getava/ava is a hosted endpoint at https://api.getava.xyz/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http xyz-getava-ava 'https://api.getava.xyz/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "xyz-getava-ava": {
      "url": "https://api.getava.xyz/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "xyz-getava-ava": {
      "type": "http",
      "url": "https://api.getava.xyz/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.xyz-getava-ava]
url = "https://api.getava.xyz/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add xyz-getava-ava --url 'https://api.getava.xyz/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  xyz-getava-ava:
    url: "https://api.getava.xyz/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "xyz-getava-ava": {
      "Transport": "http",
      "Url": "https://api.getava.xyz/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add xyz-getava-ava -t streamable-http -u 'https://api.getava.xyz/mcp'
```

### Other

```json
{
  "mcpServers": {
    "xyz-getava-ava": {
      "type": "http",
      "url": "https://api.getava.xyz/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.

### 2026-09-20 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-09 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-07 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-05 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (15)

### `ava_copilot_turn` (~159 tokens)

Natural-language copilot turn: message → intent → plan → testnet quote. Example: Swap 10 USDC to SUI on sui with 50 bps slip. Returns actions with approve_execute + executionId. Optional agentId/agentCredential for KYA gate (fail closed on reject). Does NOT fill until ava_approve_execute.

Input parameters:

- `agentCredential` (object): Optional ava.kya.agent-credential.v1 object for KYA evaluation.
- `agentId` (string): Optional agent id; uses a default testnet-scoped KYA credential when full agentCredential is omitted.
- `message` (string, required)
- `mode` (string)
- `portal` (string)
- `userId` (string)

### `ava_approve_execute` (~311 tokens)

Human-in-the-loop approve: the one call that actually settles a plan from ava_copilot_turn. It is gated by the bound mandate's status and constraints and by server-side policy limits, and it CAN REFUSE (e.g. mandate paused/cancelled, a policy violation, a stale preview hash); a refusal means no funds moved and no success receipt was written, only a refusal record. Testnet mode settles against simulated balances and returns a receipt + before/after balances, never a real chain. Mainnet mode signs with the caller's own Turnkey wallet and submits for real where a venue is live, and fails closed everywhere else, so it never claims a fill it cannot show. Call ava_list_venues for which routes are live rather than assuming; that tool reads the same registry this one enforces, so it cannot drift from what will actually execute. NEVER call without explicit user confirmation of the previewed quote.

Input parameters:

- `executionId` (string, required): executionId from actions[].type === approve_execute on the prior copilot turn
- `mode` (string): Default testnet. Live is fail-closed without a submit path.
- `portal` (string, required): Portal slug matching the pending plan (e.g. sui)
- `previewHash` (string): previewHash from ava_preview_tx. Binds the signature to the artifact the human reviewed; a stale hash fails before signing.
- `userId` (string, required): Same userId used on ava_copilot_turn / portfolio

### `ava_lend_execute` (~501 tokens)

Execute a REAL lend against one of your mandates. Routes Ava has already settled a mainnet transaction on: Morpho Blue on Base, and Aave v3 on Monad, BNB Chain and Avalanche. Aave v3 on Arbitrum One is wired through the identical pipeline and address-verified, but nothing has ever settled there, so do not describe it as proven. Aave v3 on Optimism and Base, and Compound v3 on Base and Arbitrum, are wired and address-verified but operator-disabled until each settles a real transaction, so calls on those routes refuse at the capability gate. This is the only MCP tool that moves live capital. Two-phase by design: call it once WITHOUT previewHash to receive the exact artifact a human must approve plus its hash, show that to the human, then call again WITH that previewHash. Your call is never treated as the human's confirmation, because you are not the person whose money moves. Only a settlement verified against the venue's own on-chain event returns a txHash; anything else has no txHash field at all, so a draft can never be narrated as a fill.

Input parameters:

- `amount` (string): Human decimal amount of the mandate's asset. Defaults to the mandate's full capital when omitted.
- `idempotencyKey` (string): Your own key for this economic action. Supply the SAME key when retrying: a fresh key per attempt makes every retry look new, which is exactly what defeats single-flight protection. Required for the…
- `mandateId` (string, required): The mandate authorising this capital. Required: Ava will not choose which of the user's authorisations to spend. From ava_create_mandate or ava_list_mandates.
- `op` (string): Supply into the venue or withdraw from it. Defaults to supply.
- `portal` (string)
- `previewHash` (string): The hash returned by the first call, after a human approved that exact artifact. Omit on the first call.
- `userId` (string, required)
- `venue` (string): Venue selector for chains carrying more than one wired lend venue. Absent keeps the chain's default: Base -> Morpho, every Aave v3 chain -> Aave v3. On Base, name aave_v3 or compound to reach those r…

### `ava_portfolio` (~85 tokens)

Simulated testnet portfolio for a userId (same data as GET /v1/portfolio): seeded balances, fills, optional portal. Requires userId. Does not invent live chain balances.

Input parameters:

- `portal` (string): Portal slug (default base)
- `userId` (string, required): Required user id (from POST /v1/users/session or x-ava-user-id)

### `ava_session` (~92 tokens)

Create or resume a human/org identity (userId), the first call in the loop. One human can own many agent instances (Claude + Cursor + OpenClaw + Ava-hosted). Moves no money and provisions no wallet by itself; call once and reuse the returned userId on every other tool.

Input parameters:

- `displayName` (string)
- `userId` (string): Reuse existing userId if known

### `ava_create_agent` (~186 tokens)

Register an agent instance under userId, before it has a wallet or a mandate. Mode A (multi-agent): agentId=byo-external + label (e.g. claude-workspace, cursor-arb) for a coding agent that already exists elsewhere. Mode B (hosted): agentId=defi-lend|defi-swap|defi-perp|portfolio hires an Ava-run agent. One userId may own many agent instances; this call alone never touches funds.

Input parameters:

- `agentId` (string, required): Catalog id e.g. byo-external, defi-lend, defi-swap, defi-perp, portfolio
- `label` (string): Optional label to distinguish agents under one human (e.g. claude-workspace, cursor-home, openclaw-night).
- `portal` (string, required)
- `userId` (string, required)

### `ava_provision_wallet` (~116 tokens)

Provision a Turnkey-custodied wallet address for this userId, scoped to one chain family (evm | solana | sui). Requires ava_session first. Returns the address for funding and later signing; it does not fund the wallet and does not move any money. If Turnkey is not configured server-side, the wallet comes back with status pending_provision rather than a fabricated active address, and cannot sign or hold funds until it is active.

Input parameters:

- `family` (string, required)
- `userId` (string, required)

### `ava_preview_tx` (~130 tokens)

Pre-sign preview: build the exact venue artifact (CoW EIP-712 order or unsigned Solana transaction) for a pending plan against the provisioned Turnkey wallet, simulate it where supported, and return it UNSIGNED. Nothing is signed or submitted. Show the artifact to the human, then pass the returned previewHash to ava_approve_execute so the signature covers exactly what was reviewed.

Input parameters:

- `executionId` (string, required): executionId from the prior ava_copilot_turn approve_execute action
- `portal` (string, required): Portal slug matching the pending plan
- `userId` (string, required)

### `ava_plan_workflow` (~227 tokens)

Turn ONE natural-language DeFi request into the dependent actions it actually contains, across one chain or several. Example: "Supply 300 USDC to Morpho on Base, bridge no more than 200 to Avalanche, then supply what arrives to Aave" returns three legs with the third depending on the second and taking its amount from what the bridge actually delivered, not a plan-time guess. Same-chain works identically: "swap 100 USDC to WETH on Base then supply the WETH to Aave" records the swap OUTPUT token so the second leg is denominated in WETH. Plans nothing it cannot execute: a clause naming an unsupported operation, an unnamed venue, a zero or negative amount, or one amount split across venues comes back in `unsupported` with a reason rather than being guessed at. Signs nothing and moves nothing. Every leg reports `executable` so you can see what Ava could actually run today.

Input parameters:

- `message` (string, required): The user's request, verbatim. Do not pre-parse it.
- `userId` (string, required)

### `ava_plan_standing` (~278 tokens)

Turn a request for REPEATED autonomous action into an envelope of bounds the user signs once. Use this instead of ava_plan_workflow when the request describes a cadence: "every hour, rotate my USDC into the best yield on Base using Aave and Morpho, never move more than 200 per rotation, never exceed 1000 total, stop after 30 days". Asking a human to approve each rotation would defeat the point, so the user authorizes LIMITS rather than a plan: allowed operations, venues, chains, per-move and cumulative caps, a minimum gain that stops the agent churning capital for fees, an expiry, and revocation. Every bound must come from the user: anything missing is returned in `missing` and the envelope is NOT signable until supplied. minGainBps is required from you because users say "the best yield" rather than a basis-point floor, and Ava must not choose how much of their money goes to gas. Returns the envelope unsigned; nothing is authorized until the user signs it.

Input parameters:

- `message` (string, required): The user's request, verbatim.
- `minGainBps` (number): Minimum improvement, in basis points, a rotation must beat to be worth its fees. Ask the user; do not invent it.
- `userId` (string, required)

### `ava_create_mandate` (~221 tokens)

Create a capital mandate: the objective, capital and constraints an agent is allowed to act under, optionally scoped to an agentInstanceId. Example: "Earn on 500 USDC on Base, max 5% drawdown". Or pass structured capital {asset,amount,chain}. Creating a mandate moves no money by itself and is not yet signed by an external wallet: it is Ava's own record of what was asked for, not a user-authorised instruction a stranger can rely on. Every later ava_approve_execute run under this mandate is gated on its status (active/paused/cancelled) and constraints, and can refuse.

Input parameters:

- `agentInstanceId` (string): Optional: bind mandate to one agent under the user (BYO or hosted)
- `capital` (object)
- `conditions` (array)
- `constraints` (object)
- `message` (string)
- `name` (string)
- `objective` (string)
- `portal` (string, required)
- `userId` (string)

### `ava_list_mandates` (~57 tokens)

List capital mandates for a userId (optional filter by agentInstanceId).

Input parameters:

- `agentInstanceId` (string)
- `portal` (string)
- `status` (string)
- `userId` (string, required)

### `ava_eval_mandate` (~78 tokens)

Read-only: check a mandate's exit conditions against a market snapshot and record the result. Omit snapshot to pull a live CoinGecko price for the condition asset. Never executes and never moves money; ava_approve_execute is the only tool that does.

Input parameters:

- `mandateId` (string, required)
- `snapshot` (object)

### `ava_agent_record` (~160 tokens)

Read an agent's track record before delegating capital to it. Returns mandates held, executions attempted, refusals by typed code, and receipts with their proof standing. Distinguishes CLAIMED from PROVEN: receiptsProven counts only chain-confirmed receipts; unconfirmed receipts prove nothing. AP2-aligned (each receipt's ap2.reference is the hash of the closed mandate) so an AP2-aware verifier can check it. Owner-readable always; a stranger reads only if the owner opted the record public. Zero is zero, never a placeholder.

Input parameters:

- `agentInstanceId` (string, required): The agent to look up.
- `userId` (string): Caller identity (ava_session first). Owner sees the full record; others only a public one.

### `ava_get_receipt` (~193 tokens)

Retrieve the receipt for a prior ava_approve_execute by executionId, the loop's final step. Returns the stored receipt plus its honest proof.standing: none (nothing submitted), unconfirmed (an identifier exists but nothing independent confirmed it), chain-confirmed (the declared chain returned the transaction and it matches what the receipt claims), or chain-contradicted (the chain disagrees with the receipt). A verified receiptHash does not by itself mean chain-confirmed; read proof.standing, not just verified. Owner-scoped: only the userId the receipt was produced for can read it by executionId; also returns a receiptHash-addressed verify URL a stranger can check with no credential.

Input parameters:

- `executionId` (string, required): executionId returned by ava_copilot_turn / ava_approve_execute.
- `userId` (string): Same userId that produced the execution. Required for headerless callers.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/xyz-getava-ava/api#diagnostics

## Score history

- 2026-09-20: 81
- 2026-09-19: 80
- 2026-09-18: 80
- 2026-09-17: 80
- 2026-09-16: 79
- 2026-09-15: 79
- 2026-09-14: 78
- 2026-09-13: 78
- 2026-09-12: 77
- 2026-09-11: 77
- 2026-09-10: 76
- 2026-09-09: 76
- 2026-09-08: 75
- 2026-09-07: 75
- 2026-09-06: 74
- 2026-09-05: 74
- 2026-09-04: 73
- 2026-09-03: 73
- 2026-09-02: 73
- 2026-09-01: 72
- 2026-08-31: 72
- 2026-08-30: 71
- 2026-08-29: 71
- 2026-08-28: 70
- 2026-08-27: 70
- 2026-08-26: 69
- 2026-08-25: 68
- 2026-08-24: 67
- 2026-08-23: 67
- 2026-08-22: 66

## Common questions

### What is the xyz.getava/ava MCP server?

xyz.getava/ava is an MCP server listed in the public MCP registry as xyz.getava/ava. Coding agents run multi-leg cross-chain DeFi. Legs re-derived from your sentence before signing. This page covers its hosted endpoint (https://api.getava.xyz/mcp).

### Is the xyz.getava/ava MCP server safe to use?

xyz.getava/ava scores 81 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the xyz.getava/ava MCP server expose?

xyz.getava/ava exposes 15 tools: ava_copilot_turn, ava_approve_execute, ava_lend_execute, ava_portfolio, ava_session, and 10 more. Their descriptions and schemas cost roughly 2,794 tokens of context every time the server is loaded.

### Does the xyz.getava/ava MCP server require authentication?

Yes. xyz.getava/ava asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the xyz.getava/ava MCP server still maintained?

xyz.getava/ava is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.getava.xyz/mcp
- Repository: https://github.com/kamalbuilds/ava-4.0
- Website: https://www.getava.xyz/
- Changelog RSS feed: https://verifymcp.io/servers/xyz-getava-ava/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/xyz-getava-ava/api.json
- HTML version of this page: https://verifymcp.io/servers/xyz-getava-ava/api