Wicked MCP

memory_store

Store a memory in Wicked Memory (free; fair-use rate limited). Call memory_prepare with operation "store" and these same arguments first, sign its message, then pass timestamp/nonce/signature here. A real embedding is computed at write time. Returns the stored memory (data.id, validity window, ...).

Args:
    wallet: Your agent's 0x wallet address (scopes the memory).
    content: The text to remember (max 16 KB).
    timestamp: From memory_prepare.
    nonce: From memory_prepare (single use).
    signature: Your wallet's signature over memory_prepare's message_to_sign.
    tags: Up to 20 short tags for filtering.
    metadata: Free-form JSON object (max 8 KB).
    source: Which agent/session wrote this.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`tags`	No
`nonce`	Yes
`source`	No
`wallet`	Yes
`content`	Yes
`metadata`	No
`signature`	Yes
`timestamp`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 2, 2026

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the free/fair-use rate limit, the mandatory two-step prepare-and-sign flow, that a real embedding is computed at write time, and that the stored memory is returned. It omits behavior around overwrites/conflicts and whether content is deduplicated, which keeps it from a 5.

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 purpose and the critical two-step flow before the args list, and nearly every sentence earns its place. Minor waste in the trailing "validity window, ..." ellipsis, which is imprecise in a return-value description.

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?

Given an output schema exists, the description need not detail returns, and it correctly focuses on the workflow, the signing prerequisite, limits, and parameter meanings. An agent has everything needed to invoke this correctly.

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%, yet the description documents every one of the 8 parameters with meaningful semantics: wallet scopes the memory, content max 16 KB, nonce is single-use, timestamp/nonce/signature come from memory_prepare, tags up to 20, metadata max 8 KB free-form. This fully compensates for the schema gap.

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 ("Store a memory in Wicked Memory") and is clearly distinguishable from siblings like memory_prepare, memory_update, and memory_get. An agent knows exactly what this tool does.

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

Usage Guidelines4/5

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

Gives explicit prerequisite guidance: call memory_prepare with operation "store" and the same arguments, sign the message, then pass timestamp/nonce/signature here. This is strong when-to-use context. It stops short of routing between this and alternatives like memory_update, but the write-path workflow is unambiguous.

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

All Wicked MCP tools Inspect

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.