Wicked MCP server

memory_prepare

Read-onlyIdempotent

Returns the exact message to sign for any memory operation. Sign it with your wallet, then call the target memory tool with the same arguments plus timestamp, nonce, and signature.

Instructions

Wicked Memory step 1 of every call: returns the exact message_to_sign. Sign it with your own wallet (EIP-191 personal_sign), then call the matching memory_* tool with the SAME arguments plus the returned timestamp, nonce and your signature. Timestamp must be within 5 minutes; nonce is single-use, so prepare again for every call.

Use when you are about to call any other memory tool and need the exact message to sign for that request. Not for the call itself.

Behavior: pure local computation, no network call, nothing is stored.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "operation": "<operation>",
      "wallet": "<wallet>"
    },
    "name": "memory_prepare"
  }
}

Input Schema

Name	Required	Description
`params`	No	The arguments you will pass to the tool, by name, e.g. {"content":"...","tags":["a"]} or {"memory_id":"<uuid>"}.
`wallet`	Yes	Your agent's 0x wallet address (memories are scoped to it).
`operation`	Yes	"store", "search", "get", "update", "history", "delete" or "deletions".

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.1Oct 3, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds traits annotations cannot express: pure local computation, no network call, nothing is stored, timestamp must be within 5 minutes, and the nonce is single-use. Those are exactly the operational constraints an agent must know before composing a signed call.

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 tight sections (what it returns, when to use, behavior) with the returned value front-loaded. No filler sentences; each one carries a constraint or routing instruction.

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

Completeness5/5

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

For a 3-param prerequisite tool with no output schema, the description still names the returned field (`message_to_sign`) and the full two-step signing workflow. An agent has everything needed to call it correctly on the first attempt.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3; the description nevertheless adds the non-obvious coupling that `params` must be the SAME arguments later passed to the target memory_* tool, and that the returned timestamp/nonce/signature travel alongside them. It does not enumerate the operation strings beyond what the schema already lists.

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: it returns the exact `message_to_sign` for a Wicked Memory operation. It explicitly positions itself against siblings by saying it is for the signing step and 'Not for the call itself', so an agent can distinguish it from memory_store, memory_get, etc. without opening any schema.

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

Usage Guidelines5/5

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

Gives the precise when: before calling any other memory tool, then sign with EIP-191 personal_sign and call the matching memory_* tool with the SAME arguments plus timestamp, nonce and signature. It also names the exclusion ('Not for the call itself') and the re-use rule (nonce is single-use, so prepare again for every call).

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

Deploy Server