Agency Capacity

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Capacity benchmarks, capacity math and Portable Delivery Intelligence for marketing agencies.

Measured statistics

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Agency Capacity": {
      "url": "https://connect.agilegrowthlabs.com/capacity",
      "transport": "streamable-http"
    }
  }
}

Measured tools (5)

• capacity_check read-only

  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.

  Parameters:

  • active_clients (required) — integer — Active client accounts.
  • account_managers (required) — integer — People who own client accounts day to day.
  • gross_margin_pct — number — Gross margin percent. Optional.
  • loaded_hourly_cost — number — Loaded hourly cost of an account manager in USD. Optional.
  • avg_monthly_retainer — number — Average monthly retainer per client in USD. Optional.
  • target_accounts_per_am — number — Target accounts per account manager. Default 18.
  • hours_lost_per_am_per_week — number — Hours each account manager loses per week to re-briefing AI, chasing approvals, fixing work and reporting. Optional.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• rebrief_tax read-only

  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.

  Parameters:

  • minutes_per_rebrief (required) — number — Minutes spent loading client context into a new AI chat.
  • rebriefs_per_account_per_week (required) — number — New AI chats per account per person each week.
  • accounts_per_person (required) — number — Accounts each person works on.
  • people (required) — integer — People who use AI on client work.
  • hourly_cost — number — Loaded hourly cost in USD. Optional.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• capacity_benchmarks read-only

  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.

  Parameters:

  • topic — string — Which benchmarks to return.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• client_context_template read-only

  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.

  Parameters:

  • client_name — string — Optional client name to put in the title.
  • service_line — string — general, seo, paid_media, content, lifecycle, or automation. Default general.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• define_term read-only

  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.

  Parameters:

  • term — string — The term to define. Optional.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.