Skip to main content
Glama

Wicked MCP

by io.github.choaticpixels
OverviewDiscussionsAdmin

memory_prepare

Step 1 of every Wicked Memory call: get the exact message to sign. Wicked Memory is persistent, wallet-scoped memory for agents (store, semantic search, versioned history, hard delete). Each call needs a fresh wallet signature; this server never signs or holds a key.

Sign `message_to_sign` with your wallet (EIP-191 personal_sign), then
call the matching tool (memory_store, memory_search, ...) with the SAME
arguments plus the returned `timestamp`, `nonce` and your `signature`.
The timestamp must be within 5 minutes and the nonce is single-use, so
prepare again for every call.

Args:
    operation: One of "store", "search", "get", "update", "history",
        "delete", "deletions".
    wallet: Your agent's 0x wallet address (your memories are scoped to it).
    params: The same arguments you will pass to the tool, by name, e.g.
        {"content": "...", "tags": ["a"]} for store, {"q": "..."} for
        search, {"memory_id": "<uuid>"} for get/update/history/delete.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paramsNo
walletYes
operationYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden and does so well: it discloses that the server never signs or holds a key, that each call requires a fresh signature, and that nonces are single-use with a 5-minute expiry. These are exactly the behavioral traits an agent needs to avoid a failed or rejected call.

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

Conciseness4/5

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

Front-loaded with the core purpose, then the signing workflow, then a structured Args section — each part earns its place. It is somewhat long, but the length is justified by the multi-step protocol and the parameter documentation gap it must fill.

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?

An output schema exists, so return values need not be explained. Given the multi-step signing flow and the 0% schema coverage, the description supplies everything required: the exact signing algorithm, the required follow-up call, the carried-over arguments, and the freshness constraints.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must compensate, and it does: it enumerates all seven valid `operation` values, explains that `wallet` scopes memories, and gives concrete per-operation `params` examples (content/tags for store, q for search, memory_id for get/update/history/delete). This fully documents all three parameters beyond the bare 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?

The opening sentence states a specific verb and resource: 'get the exact message to sign,' and frames it as 'Step 1 of every Wicked Memory call.' This clearly distinguishes it from siblings like memory_store or memory_search, which are the actual operations that follow.

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?

Explicitly prescribes the workflow: sign `message_to_sign` with EIP-191 personal_sign, then call the matching tool with the SAME arguments plus timestamp, nonce, and signature. It also states the operative constraints (5-minute timestamp window, single-use nonce, must prepare again for every call), leaving nothing to inference.

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

All Wicked MCP toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources