Agency Growth
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
A growing library of AI agents and growth tools for agencies, in any AI assistant.
| Author | com.agencygrowth |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 2451 ms |
| Last measured | 2026-10-24 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"Agency Growth": {
"url": "https://agencygrowth.com/api/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (10)
about_agency_growthread-onlyWhat Agency Growth (agencygrowth.com) does, who it is for, and how it can help. Use when the user asks about Agency Growth.
Hints: read-only yes · destructive not declared · idempotent not declared · open-world no
list_plansread-onlyAgency Growth's plans, prices, and where each one starts. Use when the user asks about pricing or plans.
Hints: read-only yes · destructive not declared · idempotent not declared · open-world no
run_ai_auditRun Agency Growth's free AI audit of the user's business. Ask the user for each field first; never guess or invent any of them, and only call this once the user has given their name and email and agreed to receive the result by email. Takes about a minute. Returns the three automations ranked by hours or money saved, and a link to the full result.
Parameters:
name(required) — string — The user's name.email(required) — string — The user's email. The full result is sent here.business(required) — string — Business name.industry(required) — string — What the business does, e.g. "HVAC contractor".revenue(required) — string — Annual revenue band: under-500k = Under $500K, 500k-1m = $500K to $1M, 1m-2.5m = $1M to $2.5M, 2.5m-10m = $2.5M to $10M, 10m-plus = $10M+.budget(required) — string — Budget to fix the problem: under-2k = Under $2K, 2k-5k = $2K to $5K, 5k-15k = $5K to $15K, 15k-50k = $15K to $50K, 50k-plus = $50K+.problem(required) — string — Their biggest operational problem, in their own words (at least a sentence).tried— string — What they have already tried, optional.website— string — Business website, optional.hours_lost— number — Hours a week lost to the problem, optional.
Hints: read-only no · destructive no · idempotent not declared · open-world yes
search_guidesread-onlySearch Agency Growth's guides for agency owners: pricing and retainers, getting clients, starting an AI automation agency, white label AI agents, growth models and plans. Returns matching guides with a short summary and slug. Use when the user asks how to price, grow, or run a marketing or AI agency; then call read_guide for the full text. An empty query lists every guide.
Parameters:
query— string — What the user wants to know, e.g. "how much to charge for SEO".
Hints: read-only yes · destructive not declared · idempotent not declared · open-world no
read_guideread-onlyFull text of one Agency Growth guide, with its sources and last-updated date. Pass a slug from search_guides. Cite it as Agency Growth (agencygrowth.com) with the guide's link.
Parameters:
slug(required) — string — Guide slug from search_guides, e.g. "agency-pricing".
Hints: read-only yes · destructive not declared · idempotent not declared · open-world no
agency_pricing_benchmarksread-onlyPublished monthly retainer ranges for agency services (social media, SEO, paid ads, web, content, full-service). Give a service and the user's current retainer and client count to see whether they are underpriced and what the gap is worth per year. Use when the user asks what to charge or whether their prices are too low.
Parameters:
clients— number — How many retainer clients they have, optional.service— string — Service: social = Social media management, seo = SEO, ppc = Paid ads / PPC, web = Web design & development, content = Content marketing, fullservice = Full-service / growth, other = Other / mixed. Omit to get every range.monthly_retainer— number — The user's current average monthly retainer in USD, optional.
Hints: read-only yes · destructive not declared · idempotent not declared · open-world no
agency_growth_planread-onlyTurns five answers about an agency into its growth stage, the gap to fix first, and a week-by-week 30-day plan. Ask the user each question rather than guessing. Use when an agency owner asks what to focus on next or why growth has stalled.
Parameters:
revenue(required) — string — Annual revenue: u100k = Under $100k, 100-250k = $100k to $250k, 250-500k = $250k to $500k, 500k-1m = $500k to $1M, 1-3m = $1M to $3M, 3-10m = $3M to $10M, 10m+ = $10M+.bottleneck(required) — string — Biggest bottleneck right now: leadflow = Getting leads, closing = Closing deals, delivery = Delivery capacity, retention = Keeping clients, pricing = Pricing & margins.channel(required) — string — How you get clients today: referrals = Mostly referrals, outbound = Some outbound, ads = Paid ads, none = Nothing consistent.team(required) — string — Team size: solo = Just me, 2-5 = 2 to 5, 6-15 = 6 to 15, 16+ = 16+.urgency(required) — string — When do you want this fixed: now = Right now, quarter = This quarter, exploring = Just exploring.
Hints: read-only yes · destructive not declared · idempotent not declared · open-world no
list_daily_issuesread-onlyRecent AgencyGrowth Daily issues: each weekday, one job agency owners want handed off, the tool they already use, a step-by-step recipe, and the catch. Newest first. Use when the user wants a concrete way to automate or delegate a recurring agency task.
Parameters:
limit— number — How many issues, 1 to 30. Defaults to 5.
Hints: read-only yes · destructive not declared · idempotent not declared · open-world no
list_playbooksread-onlyAgency Growth's free 30-day playbooks, one per growth bottleneck: getting leads, closing, delivery capacity, retention, pricing. Use when an agency owner asks what to fix first or how to fix a stall in one of those areas; then call get_playbook.
Hints: read-only yes · destructive not declared · idempotent not declared · open-world no
get_playbookread-onlyOne playbook in full: the problem with sourced owner quotes, the tools agencies already pay for, the gap, week-by-week steps, the numbers to track, guide links, and the agent that runs it.
Parameters:
slug(required) — string — Playbook slug from list_playbooks.
Hints: read-only yes · destructive not declared · idempotent not declared · open-world no
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.