Wicked MCP

memory_search

Semantic search over YOUR memories (scoped to wallet; no other wallet's memories are ever returned). Ranked by real cosine similarity computed at query time (score). Call memory_prepare with operation "search" and these same arguments first.

Access: this is the one metered endpoint. With a free-tier key
(MEMORY_API_KEY, if this server has one) it is free and rate-limited;
otherwise it returns http_status 402 with x402 payment instructions under
`payment_required` (0.001 USDC on Base). To pay: build and sign the x402
payment from `payment_required`, then call this tool AGAIN with the SAME
arguments (same timestamp/nonce/signature, which a 402 does not consume)
plus `payment_signature`.

By default only currently-active versions are searched; use `as_of` to
search memory as it stood at a past instant, or include_superseded=true
for every version.

Args:
    wallet: Your agent's 0x wallet address.
    q: What to look for, in natural language.
    timestamp: From memory_prepare.
    nonce: From memory_prepare (single use).
    signature: Your wallet's signature over memory_prepare's message_to_sign.
    limit: 1-50 results (default 10).
    tags: Only memories having ALL of these tags.
    created_after: ISO-8601 lower bound on creation time.
    created_before: ISO-8601 upper bound on creation time.
    as_of: ISO-8601 instant; search the versions valid at that moment.
    include_superseded: Also search old, superseded versions.
    payment_signature: x402 payment payload (base64) for the keyless path.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`q`	Yes
`tags`	No
`as_of`	No
`limit`	No
`nonce`	Yes
`wallet`	Yes
`signature`	Yes
`timestamp`	Yes
`created_after`	No
`created_before`	No
`payment_signature`	No
`include_superseded`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 2, 2026

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses strict wallet scoping, metered-endpoint behavior, free-tier vs. the 402/x402 flow with price and chain, and the non-obvious fact that a 402 does not consume the nonce. Default version-filtering behavior (active-only) is also stated.

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?

Purpose and wallet scoping are front-loaded, with access/payment and version-selection details following in logical order. The payment paragraph is somewhat verbose, but every clause (price, chain, resend-same-args rule) is operationally necessary, so little is wasted.

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 12-parameter, no-annotation tool with a bare schema, it covers auth flow, payment/quota behavior, scoping guarantees, and version semantics, and an output schema already exists so return-shape detail is unnecessary. Nothing material an agent needs to invoke it correctly is missing.

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 coverage is 0%, so the description must compensate, and it documents every one of the 12 parameters with meaning beyond the bare schema: limit range and default (1-50, default 10), tags as AND-semantics, ISO-8601 bounds for created_after/before, as_of as a point-in-time version selector, single-use nonce, and the relationship of signature to memory_prepare's message_to_sign.

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 precise verb+resource ('Semantic search over YOUR memories') and immediately bounds scope: results are limited to the given `wallet`. It also specifies the ranking mechanism (real cosine similarity at query time, returned as `score`), which cleanly distinguishes it from memory_get and memory_history.

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 a hard prerequisite ('Call memory_prepare with operation "search" and these same arguments first') and an explicit retry path on payment failure with identical arguments. It also tells the agent how to widen retrieval (as_of vs. include_superseded). It does not explicitly contrast against sibling retrievers like memory_get, so it falls short of a full 5.

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.