Skip to main content
Glama
Sign In

Agency Autopilot

by com.jiyumarketing.mcp
OverviewDiscussionsAdmin

Forms: create a hosted lead form for a client

create_lead_form

Create a lead form that Agency Autopilot hosts for a client, and get the two-line embed snippet for the site. Each lead is stored here first, then delivered to the CRM the agency chooses: its HighLevel sub-account (through the existing connection), HubSpot (a private-app token) or any CRM through a signed webhook (Zapier, Make, Jobber…). HubSpot tokens and webhook addresses are entered on the dashboard page this returns, never in chat. On submit the form fires generate_lead and sends people to the thank-you page, so Ads and Analytics keep counting. Because Agency Autopilot hosts it, form_test can test it end to end.

Input Schema

NameRequiredDescriptionDefault
crmNonone
accentNoButton colour as a hex code, e.g. #1f6f4a
buttonNoButton text, e.g. "Get my free quote"
clientYesClient name from list_clients
fieldsNoFields in order. Default: first name, last name, phone, email, message.
confirmNoLeave false to preview: nothing changes and the preview shows exactly what would happen. Set true only after the user has agreed to this exact change.
servicesNoChoices for the service field, if used
copy_leads_toNoOptional: a hidden copy (BCC) of each of those lead emails, e.g. the agency owner. Needs email_leads_to.
thank_you_urlNoFull https:// address of the page to send people to after submitting (where the conversion tags fire). Strongly recommended.
email_leads_toNoOptional, off by default: an address (usually the client's) that gets an email for every real lead, with everything the person typed. Needs crm highlevel; it sends from that sub-account. Ask before setting it.
highlevel_location_idNoHighLevel sub-account for the leads; defaults to the client's linked one

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / confirm
      Added value: +{
+  "default": false,
+  "description": "Leave false to preview: nothing changes and the preview shows exactly what would happen. Set true only after the user has agreed to this exact change.",
+  "type": "boolean"
+}
  2. Changed2 schema fields changed
    • addedInput schema / properties / copy_leads_to
      Added value: +{
+  "description": "Optional: a hidden copy (BCC) of each of those lead emails, e.g. the agency owner. Needs email_leads_to.",
+  "type": "string"
+}
    • addedInput schema / properties / email_leads_to
      Added value: +{
+  "description": "Optional, off by default: an address (usually the client's) that gets an email for every real lead, with everything the person typed. Needs crm highlevel; it sends from that sub-account. Ask before setting it.",
+  "type": "string"
+}
  3. Added

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only cover the safety profile (not read-only, not destructive, open-world, non-idempotent). The description goes well beyond them: it explains where secrets are entered (dashboard, never in chat), that leads are stored locally before delivery, that submission fires generate_lead and redirects to the thank-you page, and that hosting enables form_test. That is exactly the behavioral context an agent needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the verb, resource and return artifact, then the delivery options. Dense but every sentence carries information; the final sentence on form_test is slightly tangential but still useful routing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter mutation with no output schema and external integrations, the description covers storage, delivery targets, credential handling, preview semantics, and downstream analytics. It even names what the call returns (embed snippet, dashboard page), closing the output gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 91%, so the baseline is 3; the description adds real meaning on top by explaining what each crm enum value entails (existing HighLevel connection vs. private-app token vs. signed webhook) and why thank_you_url matters (conversion tags fire there). It does not add much for accent/button/services, but those are self-documenting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb + resource ('Create a lead form that Agency Autopilot hosts for a client') plus the concrete artifact returned (the two-line embed snippet). It is distinguishable from sibling lead_forms (listing forms) and form_test (testing), both of which are named or implied.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Clear context: choose a delivery route (HighLevel sub-account, HubSpot token, signed webhook to Zapier/Make/Jobber), and it points at form_test for end-to-end testing. It also implies the preview-first workflow via the confirm parameter. It stops short of explicitly contrasting with lead_forms, so it is strong but not fully routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Agency Autopilot toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources