Одна запись в конфигурации MCP. 150+ специализированных агентов по запросу. Никакой ручной настройки.
Ваш ИИ-ассистент — универсал. Иногда вам нужен специалист — дизайнер игровой экономики, аудитор безопасности, технический писатель. Этот MCP-сервер дает вашему ассистенту мгновенный доступ к более чем 150 шаблонам экспертных агентов. Опишите, что вам нужно, и он найдет подходящего агента и запустит его.
You: "Help me design a balanced game economy"
Claude: [searches -> finds Game Economy Designer -> spawns it -> expert response]Шаблоны автоматически загружаются при первом запуске из agency-agents и остаются актуальными. Вам не нужно ничего делать.
Вы можете. Скрипт установки agency-agents копирует все 160+ файлов агентов прямо в директорию конфигурации вашего инструмента (например, ~/.claude/agents/). Это работает, но имя и описание каждого агента загружаются в контекстное окно каждого диалога, используете вы их или нет.
Мы провели замеры:
Подход | Расход контекста | Когда |
Установленные агенты ( | ~8 300 токенов | В каждом диалоге, всегда |
MCP-сервер (в режиме ожидания) | ~55 токенов | В каждом диалоге |
MCP-сервер (поиск) | ~350 токенов | Только при поиске |
MCP-сервер (использование агента) | ~2 700 токенов | Только при запуске (медиана) |
Это 150-кратное снижение базового использования контекста. Вы получаете те же 160+ агентов, но платите только за того, которого используете в данный момент.
Установленные агенты (8 300 токенов): Мы запустили скрипт установки agency-agents (install.sh --tool claude-code), который скопировал 162 файла агентов в ~/.claude/agents/. Затем открыли новую сессию Claude Code и выполнили /context. Claude Code сообщил: "Custom agents: 8.3k tokens" — они загружаются в каждый диалог независимо от того, используется ли какой-либо агент.
MCP в режиме ожидания (55 токенов): Если вместо этого настроен MCP-сервер, /context показывает только имена двух отложенных инструментов (agency_search, agency_browse) и краткое описание сервера в системном промпте. Данные агентов не загружаются.
MCP поиск (350 токенов): Измерено путем токенизации полных JSON-схем инструментов, которые загружаются, когда ассистент вызывает ToolSearch для разрешения инструментов agency_search и agency_browse. Подсчитано с помощью @anthropic-ai/tokenizer.
MCP использование агента (2 700 токенов): Медианное количество токенов по всем 145 файлам агентов, измеренное с помощью @anthropic-ai/tokenizer. В контекст загружается только тот файл агента, который вы используете. Диапазон составляет 383–12 724 токена в зависимости от агента (p25: 1 549, p75: 3 584).
Related MCP server: pantheon-mcp
Как плагин:
/plugin marketplace add npupko/agency-mcp-server
/plugin install agency@agency-mcp-serverИли через CLI:
claude mcp add agency -- npx -y agency-mcp-serverДобавьте в свою конфигурацию MCP:
{
"mcpServers": {
"agency": {
"command": "npx",
"args": ["-y", "agency-mcp-server"]
}
}
}Это всё. При первом запуске шаблоны клонируются в ~/.cache/agency-mcp-server/ и обновления подтягиваются каждые 24 часа.
Спросите своего ассистента:
"Search for a game economy designer agent"
Вы должны увидеть результаты от инструмента agency_search. Если это первый запуск, шаблоны будут автоматически загружены (~30 секунд).
Ваш ассистент получает четыре инструмента:
agency_search(query, division?) — опишите задачу, получите подходящих агентов с инструкциями по запуску
agency_browse(division?) — изучите разделы и агентов, если хотите увидеть, что доступно
agency_status() — проверьте свежесть индекса: количество агентов, время последнего обновления, наличие доступных обновлений
agency_update() — подтяните последние шаблоны из git и пересоберите индекс поиска без перезагрузки
Когда вы просите помощи с чем-то конкретным, ваш ассистент вызывает agency_search, выбирает лучший вариант и запускает субагента с полным системным промптом этого специалиста. Вы получаете экспертный ответ, не касаясь конфигурационного файла.
Агенты организованы по разделам:
Раздел | Примеры |
Engineering | Software Architect, DevOps Engineer, Technical Writer |
Design | UI Designer, UX Researcher, Design Systems |
Game Development | Game Economy Designer, Game Mechanics Designer |
Marketing | Content Strategist, SEO Specialist, Email Marketing |
Security & Specialized | Security Auditor, Data Scientist, Legal Analyst |
...и другие | Academic, Sales, Strategy, Support, Testing, Spatial Computing |
Вся настройка осуществляется через переменные окружения в вашей конфигурации MCP:
Переменная | По умолчанию | Описание |
|
| Путь к шаблонам агентов. Установите его, чтобы использовать свои шаблоны вместо автоклонирования |
|
| Git-репозиторий для клонирования шаблонов. Укажите свой форк |
|
| Установите |
|
| Часы между проверками обновлений |
Укажите локальную директорию:
{
"mcpServers": {
"agency": {
"command": "npx",
"args": ["-y", "agency-mcp-server"],
"env": {
"AGENCY_AGENTS_PATH": "/path/to/your/agent-templates"
}
}
}
}Или клонируйте из своего репозитория:
{
"mcpServers": {
"agency": {
"command": "npx",
"args": ["-y", "agency-mcp-server"],
"env": {
"AGENCY_REPO_URL": "https://github.com/yourorg/custom-agents.git"
}
}
}
}Каждый агент — это Markdown-файл с YAML-заголовком, организованный по разделам:
engineering/
software-architect.md
devops-engineer.md
design/
ui-designer.md
game-development/
game-economy-designer.md---
name: Software Architect
description: Expert software architect specializing in system design...
---
Full agent system prompt goes here.Сервер индексирует поля name и description для поиска. Полное тело Markdown становится системным промптом агента при запуске.
agency_search(query, division?) — поиск агентов по описанию задачи, возвращает совпадения с путями к файлам и готовым шаблоном запуска
agency_browse(division?) — список всех разделов или список агентов в конкретном разделе
agency_status() — проверка свежести индекса: количество агентов, время последнего обновления, необходимость обновления
agency_update() — подтянуть последние шаблоны из git и пересобрать индекс поиска во время выполнения
agency://agents — полный индекс агентов в формате JSON
agency://divisions — список разделов с количеством и примерами
use-agent — опишите задачу, получите наиболее подходящего агента с инструкциями по запуску
npm install
npm run build
# Run with auto-fetched templates
node dist/index.js
# Run with local templates
AGENCY_AGENTS_PATH=./my-agents node dist/index.js
# Type checking
npm run typecheck
# MCP Inspector
npm run inspectШаблоны агентов от agency-agents авторства @msitarzewski.
MIT
Browse all agent divisions and their agents. Explore the agent registry when you want to see what's available. Use agency_search instead if you already know what kind of agent you need. Call with no arguments to see all divisions. Pass a division name to list its agents.
| Name | Required | Description | Default |
|---|---|---|---|
| division | No | Division to list agents for (omit to see all divisions) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only, non-destructive, idempotent behavior. The description adds clarity on how to invoke different behaviors (no args vs division), but does not add novel behavioral traits beyond annotations.
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, well-structured with usecase and instructions tags, and front-loaded with the primary action.
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 low complexity (1 optional param, no output schema), the description provides complete guidance on usage and alternatives, leaving no gaps.
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?
Schema coverage is 100% with a clear description for the division parameter. The description restates the schema's intent without adding new semantic detail, meeting the baseline.
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 'Browse all agent divisions and their agents.' It differentiates from sibling agency_search by recommending its use when knowing the agent type.
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?
Explicit instructions: 'Call with no arguments to see all divisions. Pass a division name to list its agents.' Also includes when to use agency_search instead.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find and launch a specialized agent for any task. Search agent templates by keyword. Returns matching agents with file paths and a spawn template. Call this before spawning any agency subagent.
Pass a task description as query (e.g. 'game mechanics', 'security audit')
Pick the best match from results
Spawn a subagent using the template at the bottom — replace with the file path and <describe the user's task> with the user's full, unabridged request
Return the subagent's response directly to the user without summarizing it
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Task or keyword to search for (e.g. 'game mechanics', 'frontend React', 'security audit') | |
| division | No | Optional: narrow to a division (e.g. 'engineering', 'game-development') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds behavioral details like output format (matching agents with file paths and spawn template) and the spawning workflow. It does not contradict annotations and provides useful context beyond them.
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 well-structured with <usecase> and <instructions> tags, front-loading the main purpose. Each sentence adds value, though the instructions are detailed. It is concise for the complexity involved.
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 lacking an output schema, the description comprehensively explains the output (matching agents with file paths and spawn template) and provides full workflow instructions. Given the tool's complexity and the annotations covering safety, the description is complete enough for an AI agent.
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?
Schema coverage is 100% with both parameters described. The description adds example values for query (e.g., 'game mechanics') and division (e.g., 'engineering'), and clarifies that query should be a task description, enhancing the schema's meaning.
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 'Find and launch a specialized agent for any task' and the usecase elaborates on searching agent templates by keyword, returning file paths and spawn templates. It distinguishes from siblings (agency_browse, agency_status, agency_update) by focusing on search and spawning, not browsing, status, or updates.
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 explicitly states 'Call this before spawning any agency subagent' and provides step-by-step instructions on how to use it: pass task description, pick best match, spawn using the template, and return response directly. This gives clear when-to-use and how-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check the current status of the agent index — last update time, whether an update is available, and agent count.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the tool as read-only, non-destructive, and idempotent. The description adds valuable behavioral details: what specific data the tool returns (last update time, update availability, agent count), which goes beyond the annotations.
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 a single, clear sentence with no fluff. It front-loads the purpose and efficiently conveys the key information.
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's simplicity (0 params, no output schema), the description fully informs the agent of what the tool does and what to expect. It covers all necessary aspects for correct invocation.
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?
There are no parameters, so the description does not need to add param meaning. The baseline for 0 params is 4, and the description effectively explains the output, compensating for the absence of an output schema.
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 'check' and the resource 'agent index status', and specifies the three pieces of information returned (last update time, update availability, agent count). This distinguishes it from sibling tools like agency_browse or agency_search.
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 implies when to use (for a quick status check) but does not explicitly state alternatives or when not to use. No guidance on context or exclusions is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Pull latest agent templates from git (if applicable) and rebuild the search index.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide idempotentHint=true, but description adds context: pulling from git (with 'if applicable') and rebuilding the search index. This clarifies the exact side effect beyond the annotation flags.
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?
Single sentence, no fluff. Every word adds value: specifies action, resource, and condition ('if applicable'). 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 no parameters, no output schema, and a simple action, the description is sufficient. It covers the essential behavior and conditionality, making it complete for an agent to understand and invoke.
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?
No parameters in schema; schema coverage is 100%. Description adds no parameter info, but baseline for 0 parameters is 4. No need for additional parameter details.
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?
Description clearly states the verb 'pull' and 'rebuild' on specific resources 'agent templates' and 'search index'. Distinguishes from sibling tools (browse, search, status) as an update operation.
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 explicit when-to-use or when-not-to-use guidance. However, the idempotentHint annotation implies it can be called repeatedly without side effects, and siblings handle other tasks. Lacks explicit alternatives or exclusion criteria.
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.
v0.3.1agency_browseagency_searchagency_statusagency_updateScored across 4 tools
Each tool has a clearly distinct purpose: browse lists divisions/agents, search finds agents by keyword with spawn templates, status checks index health, update refreshes the index. No overlap.
All tools follow a consistent 'agency_' + verb in snake_case pattern (browse, search, status, update), making it predictable and easy to understand.
With 4 tools, the server is slightly on the minimal side but still well-scoped for agent registry operations. Each tool serves a distinct purpose without redundancy.
The tool surface covers the core workflows: browsing, searching, status checking, and updating. Minor gap is the lack of a direct spawn tool, but search provides a template for spawning.
150+ vertical AI expert bots as agent tools. $1 bots run on YOUR machine - your data stays yours.
Contextual prompts and agent skills for 140+ AI platforms.
Discover, inspect and run 63,000+ agent tools from one balance. Pay per call, no subscriptions.
AI agent tools: web search, browser, 400+ LLMs, image gen, TTS, phone verify. Pay-per-use.
