AGL Agency Capacity
Agency capacity math, benchmarks, client context templates and an AI approval checklist.
我該用這個嗎
品質與安全性
發現項目（1）
- LOWTool 'rebrief_tax' description lacks action verb在 rebrief_tax 中
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"agency-capacity": {
"url": "https://connect.agilegrowthlabs.com/capacity"
}
}
}遠端端點
https://connect.agilegrowthlabs.com/capacitystreamable-http它能做什麼
工具清單
工具（7）
🟢capacity_check(active_clients, account_managers, avg_monthly_retainer, hours_lost_per_am_per_week, loaded_hourly_cost, ...)
Estimates an agency's accounts per account manager, yearly coordination cost, and how many more accounts the same team could carry at a target ratio. Use when the user shares client and team numbers and asks about capacity, hiring, or account manager load. Returns an estimate, not a guarantee.
輸入結構描述
{
"type": "object",
"properties": {
"active_clients": {
"type": "integer",
"minimum": 1,
"maximum": 2000,
"description": "Active client accounts."
},
"account_managers": {
"type": "integer",
"minimum": 1,
"maximum": 500,
"description": "People who own client accounts day to day."
},
"avg_monthly_retainer": {
"type": "number",
"minimum": 0,
"maximum": 1000000,
"description": "Average monthly retainer per client in USD. Optional."
},
"hours_lost_per_am_per_week": {
"type": "number",
"minimum": 0,
"maximum": 60,
"description": "Hours each account manager loses per week to re-briefing AI, chasing approvals, fixing work and reporting. Optional."
},
"loaded_hourly_cost": {
"type": "number",
"minimum": 0,
"maximum": 1000,
"description": "Loaded hourly cost of an account manager in USD. Optional."
},
"gross_margin_pct": {
"type": "number",
"minimum": 0,
"maximum": 100,
"description": "Gross margin percent. Optional."
},
"target_accounts_per_am": {
"type": "number",
"minimum": 1,
"maximum": 40,
"default": 18,
"description": "Target accounts per account manager. Default 18."
}
},
"required": [
"active_clients",
"account_managers"
],
"additionalProperties": false
}🟢rebrief_tax(minutes_per_rebrief, rebriefs_per_account_per_week, accounts_per_person, people, hourly_cost)
Estimates the monthly hours and cost a team spends explaining clients to AI tools before they do useful work. Use when the user asks what re-briefing AI or re-pasting client context costs.
輸入結構描述
{
"type": "object",
"properties": {
"minutes_per_rebrief": {
"type": "number",
"minimum": 0,
"maximum": 120,
"description": "Minutes spent loading client context into a new AI chat."
},
"rebriefs_per_account_per_week": {
"type": "number",
"minimum": 0,
"maximum": 100,
"description": "New AI chats per account per person each week."
},
"accounts_per_person": {
"type": "number",
"minimum": 0,
"maximum": 100,
"description": "Accounts each person works on."
},
"people": {
"type": "integer",
"minimum": 1,
"maximum": 1000,
"description": "People who use AI on client work."
},
"hourly_cost": {
"type": "number",
"minimum": 0,
"maximum": 1000,
"description": "Loaded hourly cost in USD. Optional."
}
},
"required": [
"minutes_per_rebrief",
"rebriefs_per_account_per_week",
"accounts_per_person",
"people"
],
"additionalProperties": false
}🟢capacity_benchmarks(topic)
Returns published benchmarks on accounts per account manager, time spent re-briefing AI, and rework of AI output, each with its source link. Use when the user asks what is normal for agencies.
輸入結構描述
{
"type": "object",
"properties": {
"topic": {
"type": "string",
"enum": [
"all",
"accounts_per_person",
"rebriefing",
"rework"
],
"default": "all",
"description": "Which benchmarks to return."
}
},
"additionalProperties": false
}🟢client_context_template(service_line, client_name)
Returns a fill-in template for a 1-file client context document (goals, voice, claims rules, priorities, approvals, decisions) for a service line. Use when the user wants AI tools or new teammates to stop needing a client re-brief.
輸入結構描述
{
"type": "object",
"properties": {
"service_line": {
"type": "string",
"enum": [
"general",
"seo",
"paid_media",
"content",
"lifecycle",
"automation"
],
"description": "general, seo, paid_media, content, lifecycle, or automation. Default general."
},
"client_name": {
"type": "string",
"maxLength": 80,
"description": "Optional client name to put in the title."
}
},
"additionalProperties": false
}🟢approval_checklist(service_line)
Returns an 8-check review list for AI-drafted client work, plus checks for the service line and how much review each risk level needs. Use when the user asks how to QA AI output before it reaches a client.
輸入結構描述
{
"type": "object",
"properties": {
"service_line": {
"type": "string",
"enum": [
"general",
"seo",
"paid_media",
"content",
"lifecycle",
"automation"
],
"description": "general, seo, paid_media, content, lifecycle, or automation. Default general."
}
},
"additionalProperties": false
}🟢define_term(term)
Defines an agency AI operations term, such as Portable Delivery Intelligence, accounts per person, re-brief tax, or AI operations sprawl. Leave term empty to list all terms.
輸入結構描述
{
"type": "object",
"properties": {
"term": {
"type": "string",
"maxLength": 80,
"description": "The term to define. Optional."
}
},
"additionalProperties": false
}🟡add_to_benchmark(consent, role, revenue_band, active_clients, account_managers, ...)
Adds 1 anonymous response to the Agency Capacity Benchmark run by Agile Growth Labs. Only call when the user explicitly agrees to share their numbers. Stores no name, email, or company. Max 3 per day per network.
輸入結構描述
{
"type": "object",
"properties": {
"consent": {
"type": "boolean",
"description": "Must be true. The user agreed to add anonymous numbers."
},
"role": {
"type": "string",
"enum": [
"owner-founder",
"coo-ops",
"delivery-account-lead",
"other"
]
},
"revenue_band": {
"type": "string",
"enum": [
"under-1m",
"1m-2m",
"2m-5m",
"5m-10m",
"10m-plus"
]
},
"active_clients": {
"type": "integer",
"minimum": 1,
"maximum": 2000
},
"account_managers": {
"type": "integer",
"minimum": 1,
"maximum": 500
},
"rebrief_hours_per_week": {
"type": "number",
"minimum": 0,
"maximum": 80,
"description": "Team hours per week spent re-briefing AI tools."
},
"ai_tools_count": {
"type": "integer",
"minimum": 0,
"maximum": 50,
"description": "AI tools used in client work."
},
"bottleneck": {
"type": "string",
"enum": [
"rebriefing",
"approvals",
"fixing",
"reporting",
"hiring",
"other"
],
"description": "The biggest delivery bottleneck."
}
},
"required": [
"consent",
"role",
"revenue_band",
"active_clients",
"account_managers",
"rebrief_hours_per_week",
"ai_tools_count",
"bottleneck"
],
"additionalProperties": false
}社群
證據