This server provides League of Legends game mode-specific data, focusing on Arena augments, ARAM balance values, and mode mechanics.
get_augment — Fuzzy search for Arena (競技場) hex augments by name or keyword in Chinese or English, returning the augment's rarity and full effect description.
list_augments — Browse all Arena hex augments filtered by rarity tier — Silver (白銀), Gold (黃金), Prismatic (稜彩), Special (特殊), or all at once — with a brief effect summary for each.
aram_balance — Look up a champion's current-patch ARAM (Howling Abyss) balance adjustments, including damage dealt/taken, healing, shielding, ability haste, attack speed, tenacity, and energy regeneration buffs or nerfs.
mayhem_balance — Query ARAM: Mayhem mode balance values for a champion (not yet supported).
lol-mode://mode-mechanics (resource) — Access hand-curated explanations of game mode mechanics, such as Abyss auras and Arena rules.
Both Chinese (zh_tw) and English (en_us) are supported for augment searches and champion name lookups.
Provides tools for querying League of Legends game mode data, including arena augments, champion balance adjustments for Arena and ARAM, and patch notes, sourced from Riot Games' official data and community resources.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@lol-mode-mcp what's the ARAM balance for Jinx?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
LoL「模式限定」資料的 MCP server + 查詢網站 —— 競技場(Arena)海克斯強化、競技場/ARAM 每英雄平衡、逐 patch 改動(競技場/一般對戰/ARAM Mayhem)。中英雙語,中文名稱一律採台服官方譯名(遊戲內字串,非機器翻譯)。
市面上的 LoL 工具幾乎都只做英雄/裝備,模式資料沒人整合,這個 server 補上這塊。
類型 | 名稱 | 說明 |
tool |
| 模糊搜尋海克斯強化(競技場/ARAM Mayhem 兩套分開查,同名互相提示) |
tool |
| 依稀有度列出強化清單(mode 選競技場或 ARAM Mayhem) |
tool |
| 英雄本 patch 的競技場專屬平衡:基礎數值加成 + 逐技能改動(技能用台服名) |
tool |
| 逐 patch 改動清單(舊值 ⇒ 新值);scope 可選競技場/一般對戰/ARAM Mayhem,query 可用中文名 |
tool |
| 英雄本 patch 的 ARAM 平衡數值,標明增益/削弱 |
tool |
| ARAM: Mayhem 數值(延伸功能,暫未支援) |
tool |
| 模式機制說明:強化選取規則、回合表、貴賓投票、Mayhem 進度(含「機率/英雄限定名單官方未公開」的誠實聲明) |
resource |
| 同上機制說明的 JSON 原文 |
改動說明的中文採規則式翻譯(固定句型 + 台服術語對照表),沒把握的句子保留英文並標 🔤 —— 寧可給原文也不亂翻。
Related MCP server: LolByte MCP Server
https://lol.zhongqqq.win/ —— 五個分頁:海克斯圖鑑(競技場/ARAM Mayhem 雙圖鑑、稀有度篩選)、競技場平衡、ARAM 平衡表(可排序)、Patch 改動(範圍/版本切換)、模式機制。支援中/EN 切換、深色/淺色主題、角色定位篩選(官方職業圖示)、原畫背景、中文名搜尋。
打開 Claude(桌面版/網頁版/手機版皆可)
設定(Settings)→ 連接器(Connectors)→ 新增自訂連接器(Add custom connector)
名稱隨意填(例如 LoL 模式資料),網址貼上:
https://lol.zhongqqq.win/mcp💡 伺服器閒置一段時間會休眠,第一個問題可能要等 30~60 秒喚醒,之後就是正常速度。 (原生網址
https://lol-mode-mcp.onrender.com/mcp亦可用。)
儲存後開新對話,直接問:「灼燒煉金那個強化在做什麼」、「悟空的 ARAM 有被削嗎」
用 uv + Python 3.10+ 可直接跑(uv sync && uv run lol-mode-mcp);雲端部署設定在 render.yaml,push 即自動部署。
競技場/Mayhem 強化與職業圖示:CommunityDragon —— 感謝社群維護的遊戲資料鏡像(patch 剛更新時可能有延遲)
平衡數值與逐 patch 改動:League of Legends Wiki(內容授權 CC BY-SA 4.0)
英雄/裝備/技能台服譯名:Riot Data Dragon
📮 作者:GitHub @NewJeans0722;問題與建議請開 Issue
🤖 本專案與 Claude(Anthropic)協同開發:架構、程式碼與測試由 Claude Code 輔助完成,需求、範圍決策與驗收由作者主導
lol-mode-mcp 並非 Riot Games 官方出品,亦未獲得 Riot Games 認可或贊助。League of Legends 及 Riot Games 為 Riot Games, Inc. 之商標或註冊商標。
lol-mode-mcp isn't endorsed by Riot Games and doesn't reflect the views or opinions of Riot Games or anyone officially involved in producing or managing Riot Games properties. Riot Games, and all associated properties are trademarks or registered trademarks of Riot Games, Inc.
MIT(程式碼);引用的資料內容依各來源授權(見上)。
查詢英雄本 patch 的 ARAM(嚎哭深淵)平衡數值,標明增益與削弱。
涵蓋:造成傷害/承受傷害/治療/護盾/技能急速/攻擊速度/韌性/能量回復。 「無調整」與「查詢失敗」會明確區分。
Args: champion: 英雄名稱,中英文皆可(例:「悟空」、"Wukong"、「犽宿」)。
| Name | Required | Description | Default |
|---|---|---|---|
| champion | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses covered stats (damage dealt/taken, healing, shields, etc.) and clarifies the distinction between no adjustment and query failure. No mention of auth or rate limits, but adequate for a simple query tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured: a clear purpose statement, then detailed scope, followed by explicit parameter guidance. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool is a simple query with one parameter and an existing output schema, the description covers all necessary context. It specifies the query inputs, the range of stats, and the expected behavior for edge cases (no adjustment vs failure).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'champion' has 0% schema description coverage, but the description adds significant meaning: it accepts both Chinese and English names, provides examples, and implies flexibility. 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.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries ARAM balance numbers for champion patches, specifying gain and nerf indicators. It distinguishes itself from sibling tools like 'get_augment' and 'mayhem_balance' by focusing specifically on ARAM balance.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use the tool (to query ARAM balance for a champion) and notes that it distinguishes between 'no adjustment' and 'query failure'. However, it does not explicitly state when not to use or provide alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
模糊搜尋競技場(Arena)海克斯強化,回傳名稱、稀有度與完整效果說明。
Args: query: 強化名稱或關鍵字,中英文皆可(例:「地獄三頭犬」、"Cerberus"、「灼燒」)。 locale: 回覆語言,"zh_tw"(預設)或 "en_us"。
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| locale | No | zh_tw |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It mentions fuzzy search and locale but omits whether the operation is read-only, pagination behavior, error handling, or any limitations. For a search tool this is insufficient transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is relatively concise and front-loaded with purpose. The args section is clear, though including examples adds length. It efficiently conveys key info without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the existence of sibling tools and an output schema, the description sufficiently covers what the tool does and how to use it. It could be more complete with notes on result limits or behavior, but overall adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description adds essential meaning: it explains 'query' can be Chinese/English keywords with examples, and 'locale' specifies response language. This goes beyond the bare schema types.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it performs fuzzy search for Arena hex augments and returns name, rarity, and effect. This specific verb-resource combination distinguishes it from siblings like list_augments (exact list) and aram_balance/mayhem_balance (different game modes).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains the tool's function and provides example queries, implying when to use it (fuzzy search for augments). However, it does not explicitly state when not to use it or contrast with siblings, leaving some inference to the agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
依稀有度列出競技場海克斯強化清單(名稱 + 一句效果摘要)。
Args: tier: "all"(預設)/ "silver" 白銀 / "gold" 黃金 / "prismatic" 稜彩 / "special" 特殊(稜彩道具、鐵砧類)。中文別名也可以。 locale: 回覆語言,"zh_tw"(預設)或 "en_us"。
| Name | Required | Description | Default |
|---|---|---|---|
| tier | No | all | |
| locale | No | zh_tw |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must fully disclose behavioral traits. The description only states the basic function and output format. It does not mention authentication requirements, rate limits, pagination, sorting order, or what happens with invalid parameters. This lack of behavioral context is a significant gap for a tool that likely performs a read operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is relatively concise, with the main purpose in the first sentence. The parameter details are presented in a bullet-like format that is easy to scan. However, it could be more structured (e.g., using a table or explicit argument list) and the first line could be slightly more formal. Overall, it is efficient and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that the tool has an output schema, the description does not need to detail return values. It explains the output (name + effect summary) and the filtering parameters. However, it does not mention whether the list is sorted, if there are any limits on results, or the default behavior when 'tier' is 'all'. This leaves some operational gaps for an agent to infer.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% coverage with no parameter descriptions. The description compensates by explaining 'tier' with a clear list of values and 'locale' with two options. It also notes that Chinese aliases are accepted. This adds substantial meaning beyond the schema's defaults, making it easy for an agent to construct valid arguments.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('list') and resource ('arena hex augmentation list'), and specifies the output (name + effect summary). The purpose is specific and aligns with the tool name. However, it does not distinguish this tool from siblings like 'get_augment' or 'mayhem_balance', which could cause ambiguity for an AI agent.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides parameter details including allowed values for 'tier' and 'locale', and mentions Chinese aliases. It implies usage for listing augments by rarity. However, it does not explicitly state when to use this tool versus alternatives (e.g., 'get_augment' for a single augment) or give any exclusion criteria, leaving some navigational ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
查詢英雄在 ARAM: Mayhem 模式的平衡數值(延伸功能,暫未支援)。
Args: champion: 英雄名稱,中英文皆可。
| Name | Required | Description | Default |
|---|---|---|---|
| champion | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the burden. It implies a read-only query but does not specify behavior when called (e.g., error on '暫未支援'). The lack of detail on response or side effects reduces transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short (two lines) but the first line mixes purpose with a note about not being supported, which could be separated. It is not overly verbose, but the structure could be cleaner.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having an output schema (not shown), the description lacks details about the output format or what happens when the tool is called while not supported. The tool is simple, but the '暫未支援' note suggests incompleteness in functionality, making it less complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds valuable context to the 'champion' parameter, specifying it accepts both Chinese and English names (英雄名稱,中英文皆可). This goes beyond the schema's simple type string, and with 0% schema coverage, the description compensates well.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries balance values for ARAM: Mayhem mode, distinguishing it from sibling aram_balance which likely targets normal ARAM. The note '暫未支援' indicates it is not yet functional, which could confuse but does not obscure the intended purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like aram_balance. Does not specify prerequisites or scenarios where this tool is appropriate despite the '暫未支援' warning.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0aram_balanceget_augmentlist_augmentsmayhem_balanceScored across 4 tools
Each tool has a distinct purpose: ARAM balance, Arena augment search, Arena augment list, and Mayhem balance (unimplemented). No overlap in functionality.
All tool names use snake_case with descriptive terms (aram_balance, get_augment, list_augments, mayhem_balance), forming a consistent naming pattern.
4 tools is a reasonable count for a server focused on League of Legends game mode data. It covers two modes plus a placeholder, not too few or too many.
The server provides core queries for ARAM balance and Arena augmentations, but lacks other common operations like listing all champions or more detailed statistics, leaving notable gaps.
Teamfight Tactics data & AI coaching for Claude and ChatGPT — 19 tools, built-in Riot key.
Live competitive-game predictions, meta data and decision tools for AI agents.
VALORANT reference data MCP (valorant-api.com).