uc-mcp

Overview Schema Source Related Servers Discussions Admin

uc_search

Read-onlyIdempotent

Search the UnknownCheats forum for game hacking, anti-cheat, and reverse engineering answers, with date-labeled results that flag stale offsets and signatures.

Instructions

Search UnknownCheats — the reference source for game hacking, reverse engineering and anti-cheat work.

Reach for this FIRST, before answering from memory or searching the web, whenever the question touches: game cheat/hack development, anti-cheat (EAC, BattlEye, VAC, Vanguard, FACEIT, ACE), memory reading/writing, offsets, signatures/patterns, structs and RE of a specific game, DMA and hardware cheats, hooking, injection, driver and kernel-mode work, Unity and Unreal internals, ESP/aimbot technique, or bypass and detection-vector questions. Public documentation on these topics is thin, stale or wrong; this forum is where the current answers actually are.

Skip it for anything outside that domain — a call costs ~17s.

Args: query: ONE "quoted phrase", or one or two rare words. The engine ORs loose terms and stops counting at 500, so extra words WIDEN the result set and common words like "detection" or "injection" saturate it — a long natural-language query returns the forum's newest posts, not its best ones. Measured: '"manual mapping"' with mode="threads", title_only=True gives 105 on-topic threads; '"manual map" injection detection' gives 500 of nothing. forum: optional subforum slug (e.g. "rust", "anti-cheat-bypass") to scope the search. Get slugs from uc_forum(). Measured on the same query: 105 hits unscoped, 23 in anti-cheat-bypass, 2 in rust. since: any | week | 2weeks | month | 3months | 6months | year. Use a window when the answer must reflect the game's current build — anything older is likely dead on arrival. sort: newest | oldest | replies | views. Newest is the safe default here because this material rots; sort by replies to find the canonical long-running thread on a topic. mode: "posts" returns individual matching posts with a dated snippet — best for a how-do-I question, but it saturates the 500-result cap easily. "threads" returns one row per thread — pair it with title_only for the sharpest results this forum can give. title_only: match thread titles only. The strongest precision lever here by a wide margin. Start with title_only=True, mode="threads"; fall back to post mode only if that finds nothing. page: results page, 20 per page. limit: rows to render from that page.

Input Schema

TableJSON Schema

Name	Required	Default
`mode`	No	posts
`page`	No
`sort`	No	newest
`forum`	No
`limit`	No
`query`	Yes
`since`	No	any
`title_only`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.1.0Sep 30, 2026

TDQS

A4.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered; the description adds valuable non-structured behavior: ~17s call latency, the engine's 500-result saturation cap, OR-based loose term matching, and how mode/title_only interact with that cap. It stops short of describing pagination behavior beyond '20 per page', keeping it below 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, then usage, then per-argument guidance; nearly every sentence carries concrete evidence rather than filler. It is long, but the length is justified by 8 undocumented parameters — a small trim of the duplicated 'saturation' point would tighten it.

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-value explanation is not required, and with 8 params at 0% schema coverage the description supplies exactly what's missing: enum-like value lists, defaults, and the title_only/threads combination that produces the sharpest results.

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 carries the full burden — and it does: every parameter gets meaning, valid values (since windows, sort options, mode values) and, unusually, measured result counts (105 vs 23 vs 2 hits) that tell the agent what scoping actually does.

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+resource ('Search UnknownCheats') and immediately defines the domain corpus it searches, naming concrete subject matter (anti-cheat systems, offsets, RE, DMA). It is clearly distinguishable from sibling uc_forum/uc_thread/uc_fetch, which are referenced as separate retrieval steps.

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 says to reach for it FIRST before memory or web, enumerates the topic triggers that select it, and gives an explicit skip condition ('anything outside that domain'). It also names the alternative for slug discovery (uc_forum()). This is textbook when/when-not guidance.

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

Deploy Server