Wicked MCP

sanity_check_batch

Verify several claims in one call — use this for a multi-sentence output instead of calling sanity_check once per sentence. Split the output into individual claims, pass the source as context, and every claim is checked against it. One payment / one rate-limit hit covers the whole batch, and grounded batches are scored far faster than N separate calls.

Returns `data` as a list with one result per claim, in the same order
as `claims`; each result is shaped exactly like sanity_check's (see
that tool for how to read `verdict`, `confidence_score` and `evidence`).
In "open" mode a separate live web search runs per claim, so large open
batches are slow.

Access: the public mcp.wickedapi.com server uses a shared, rate-limited
key, so this returns real verdicts directly -- but the shared budget is
small (about 20 requests/minute and 30 open-mode checks/day across ALL
users; grounded mode is not counted against the daily limit). An
http_status 429 means that shared budget is used up: retry after the
Retry-After seconds, run this server locally with your own
SANITY_API_KEY, or pay per call via x402 directly. A server with no key
configured returns an http_status 402 carrying x402 payment instructions
under `payment_required` instead.

Args:
    claims: 1-50 statements to verify, each up to 5,000 characters.
    context: Shared source text for every claim — a string or a list of
        strings. Required for mode "grounded".
    mode: "grounded" (check against `context`) or "open" (check against
        live web evidence).

Input Schema

TableJSON Schema

Name	Required	Default
`mode`	No	grounded
`claims`	Yes
`context`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 2, 2026

TDQS

A5/5.0

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 richly: one payment/rate-limit hit covers the batch, the shared key budget (~20 req/min, 30 open-mode checks/day across all users), that grounded mode is exempt from the daily cap, http_status 429 with Retry-After and remediation paths, and 402 with x402 payment instructions when no key is configured. This is far beyond a generic 'batch verification' statement.

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?

Front-loaded with purpose and the sibling contrast, then organized into a Returns paragraph, an Access/error-handling paragraph, and an Args block. The length is justified by the genuine operational complexity (batching, dual modes, rate limits, payment fallback); no sentence is filler.

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?

Covers everything an agent needs: ordering guarantee of the returned list, the fact that each result mirrors sanity_check's shape, mode-dependent behavior, batching constraints, and both 429 and 402 failure paths. An output schema exists, so the description appropriately points to sanity_check for field semantics rather than duplicating them.

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 does: claims are 1-50 statements each up to 5,000 characters, context is a shared source that accepts a string or list of strings and is required for grounded mode, and mode's two valid values are spelled out with their semantics.

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 ('Verify several claims in one call') and explicitly contrasts itself with its sibling: use this instead of calling sanity_check once per sentence. An agent can distinguish the batch variant from the single-claim variant without opening either 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 an explicit when-to-use trigger (multi-sentence output), the alternative it replaces (per-sentence sanity_check), and when each mode applies ('grounded' checks against context, 'open' checks live web evidence). It even warns that open mode is slow because a separate live search runs per claim.

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.