AgentWallet MCP Server

create_wallet

Create a new EVM or Solana wallet and return its ID and address. Private keys remain encrypted server-side and are never exposed.

Instructions

Create a new EVM or Solana wallet. Returns the wallet ID and address. Private key is encrypted server-side and never exposed.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_wallet"
  }
}

Input Schema

Name	Required	Description	Default
`label`	No	Friendly name for the wallet
`chain_id`	No	Default chain ID (1=Ethereum, 8453=Base, 42161=Arbitrum, 10=Optimism, 137=Polygon, 43114=Avalanche, 56=BSC, 7777777=Zora, 369=PulseChain, 900=Solana, 901=Solana Devnet)

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv1.14.8Oct 27, 2026
- addedInput schema / properties / chain_id / maximum
```
Added value: +9007199254740991
```
- addedInput schema / properties / chain_id / minimum
```
Added value: +-9007199254740991
```
First observedv1.7.3Mar 11, 2026

TDQS

A3.6/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral burden, and it does disclose two important traits: the return shape (wallet ID + address) and that the private key is encrypted server-side and never exposed. It omits whether creation is idempotent, whether multiple wallets may be created, rate limits, auth/permission requirements, and the fact that the key can later be retrieved only via export_wallet_key.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences with zero waste: what it does, what it returns, and the key security guarantee, in that order. Nothing is repeated from the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description usefully names the return values, and with no annotations it correctly front-loads the private-key safety property. The remaining gap is the absence of any usage context for a state-creating, security-sensitive operation among many wallet siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters (label, chain_id) are documented in the schema with a full chain-ID enumeration, and the baseline is 3. The description adds no meaning beyond the schema — it does not explain label defaults or the 8453/Base default chain implicit in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Create a new EVM or Solana wallet') and names the artifact produced (wallet ID and address). The chain scope ties directly to the chain_id parameter, so an agent knows this single tool covers both EVM and Solana creation rather than looking for a separate tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to create a wallet versus using an existing one (e.g. check list_wallets/get_wallet first), no prerequisites, and no mention of related siblings like wallet_mode, pause_wallet, or export_wallet_key. The agent is left to infer the call context entirely.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.