Skip to main content
Glama
Sign In

Wicked MCP

by io.github.WickedAPI
OverviewDiscussionsAdmin

memory_store

[Wicked Memory] Store a memory (free, fair-use rate limited). A real embedding is computed at write time. Run memory_prepare with operation 'store' and these same arguments first.

Use when you want to save something for later, scoped to your wallet. Not for changing an existing memory (use memory_update).

Behavior: writes state upstream (not read-only); needs the credentials or wallet signature noted above where applicable.

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": {
      "wallet": "<wallet>",
      "content": "<content>",
      "timestamp": "<timestamp>",
      "nonce": "<nonce>",
      "signature": "<signature>"
    },
    "name": "memory_store"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsNoUp to 20 short tags.
nonceYesFrom memory_prepare (single use).
sourceNoWhich agent/session wrote this.
walletYesYour agent's 0x wallet address.
contentYesText to remember (max 16 KB).
metadataNoFree-form JSON object (max 8 KB).
signatureYesYour wallet's signature over memory_prepare's message_to_sign.
timestampYesFrom memory_prepare.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and openWorldHint=true, so the "writes state upstream (not read-only)" sentence largely restates them. The description does add genuine non-annotation context: free/fair-use rate limiting, embedding computation at write time, wallet signature requirement, and the single-use nonce flow that makes retries unsafe.

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, then prerequisite, then exclusion, then behavior — good ordering with no wasted preamble. The closing line "needs the credentials or wallet signature noted above where applicable" is generic boilerplate that mostly echoes the annotations, keeping it off a 5.

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?

For an 8-parameter signed write with full schema coverage and annotations, the description covers the prerequisite flow, rate-limit posture, and mutation semantics. It stops short of saying what comes back (memory id, embedding reference) or whether stored tags/metadata are indexed for later memory_search, which is a minor gap given no output schema.

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 per-parameter meaning is already documented; baseline would be 3. The description earns above baseline by explaining that the wallet scopes the write and that the nonce/timestamp/signature trio must come from a prior memory_prepare call with identical arguments, which is a cross-field relationship the schema does not express.

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?

"Store a memory" is a specific verb+resource, and the description immediately scopes it ("scoped to your wallet") and names the sibling it is not ("Not for changing an existing memory (use memory_update)"). An agent can distinguish this from memory_update, memory_search, and memory_prepare without opening a 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?

Explicit when-to-use ("save something for later, scoped to your wallet"), explicit when-not plus the alternative ("Not for changing an existing memory (use memory_update)"), and a stated prerequisite flow ("Run memory_prepare with operation 'store' and these same arguments first"). All three routing signals an agent needs are present.

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