API Tools

getava.xyz

This MCP server enables AI assistants to interact with the ava financial platform, handling sessions, copilot turns, approvals, and lend/portfolio operations.

1 endpoint15 known toolsFirst detected August 22, 2026Last detected September 6, 2026

ENDPOINT 1

https://api.getava.xyz/mcp

No auth detected

MCP server metadata

Name: ava
Version: 0.5.0

Capabilities

tools

Known tools 15

ava_copilot_turn

Natural-language copilot turn: message → intent → plan → testnet quote.

Potential side effects

ava_approve_execute

Human-in-the-loop approve: the one call that actually settles a plan from ava_copilot_turn.

Inferred read-only

ava_lend_execute

Execute a REAL lend against one of your mandates.

Potential side effects

ava_portfolio

Simulated testnet portfolio for a userId (same data as GET /v1/portfolio): seeded balances, fills, optional portal.

Inferred read-only

ava_session

Create or resume a human/org identity (userId), the first call in the loop.

Potential side effects

ava_create_agent

Inferred read-only

ava_provision_wallet

Provision a Turnkey-custodied wallet address for this userId, scoped to one chain family (evm | solana | sui).

Inferred read-only

ava_preview_tx

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.

Inferred read-only

ava_plan_workflow

Turn ONE natural-language DeFi request into the dependent actions it actually contains, across one chain or several.

Inferred read-only

ava_plan_standing

Turn a request for REPEATED autonomous action into an envelope of bounds the user signs once.

Inferred read-only

ava_create_mandate

Create a capital mandate: the objective, capital and constraints an agent is allowed to act under, optionally scoped to an agentInstanceId.

Potential side effects

ava_list_mandates

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

Inferred read-only

ava_eval_mandate

Read-only: check a mandate's exit conditions against a market snapshot and record the result.

Inferred read-only

ava_agent_record

Read an agent's track record before delegating capital to it.

Inferred read-only

ava_get_receipt

Retrieve the receipt for a prior ava_approve_execute by executionId, the loop's final step.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.ava]
url = "https://api.getava.xyz/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "ava": {
      "type": "http",
      "url": "https://api.getava.xyz/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: ava
Remote MCP URL: https://api.getava.xyz/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

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

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

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

Generic MCP

Client-specific MCP configuration

{
  "name": "ava",
  "transport": "streamable-http",
  "url": "https://api.getava.xyz/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.