Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Houzz Pro API v1, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fhouzz.com%2Fhouzz" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fhouzz.com%2Fhouzz" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Houzz Pro API v1 API.
Capture a lead, move it through lead phases with updatePhase, and convert it into a project
Add tasks and milestones to a project or lead, mark tasks done, and read a project's punchlist
Record daily logs against a project with content, logDate, and logEndDate
Upload, copy, move, archive, and organise files in folders for a project or lead context
GET STARTED
Keep contacts, contact groups, vendors, and subcontractors current, including vendor archive and unarchive
Assign projects, leads, or tasks to team members and list who is assigned
Subscribe a webhook url to Houzz Pro triggers and set custom field values on records
Patterns agents use Houzz Pro API v1 API for, with concrete tasks.
★ Agent-run job admin for contractors
A remodeling contractor's AI agent turns a site visit summary into Houzz Pro records. Through Jentic it finds the project task and daily log operations by intent, writes a daily log for the day's work, and adds follow-up tasks to the same project, while a rule keeps it to those operations so it cannot delete projects or team members.
Call POST /v1/daily-logs with projectId and content describing today's framing work, then POST /v1/projects/{projectId}/tasks with title set to 'Order drywall' and a dueDate
Lead intake to project conversion
Inquiries from a website or ad form need to land in Houzz Pro without retyping. The lead operations create a lead with a contactId, budget, and source, move it through the lead phases listed by the lead-phases endpoint, and convert it to a project when the client signs, keeping the history together.
Call POST /v1/contacts with name set to the client's name, POST /v1/leads with that contactId and a budget, then POST /v1/leads/{id}/convertToProject once the client signs
Project schedule and punchlist tracking
A project manager wants a weekly view of what is due. Milestones carry startDate and dueDate per project, tasks carry dueDate and done, and the punchlist endpoint returns the closing items for a project, so an agent can compile a status report or flag overdue work.
Call GET /v1/projects/{projectId}/milestones and GET /v1/projects/{projectId}/tasks, then list items whose dueDate falls in the next 7 days
Syncing vendors and files with back-office tools
Purchasing and document work often lives in other systems. The vendor operations hold companyName, defaultPaymentTerms, and chargesTax for suppliers, and the file operations upload, move, and archive documents within a project context, so a sync job can keep supplier lists and plans in step.
Call GET /v1/vendors with companyName set to the supplier's name, and if none is found POST /v1/vendors with companyName and defaultPaymentTerms
101 endpoints — the houzz pro api gives verified partners access to the records remodelers, builders, and designers run their business on in houzz pro: projects, leads, contacts, tasks, milestones, daily logs, punchlists, files, vendors, subcontractors, and team members.
METHOD
PATH
DESCRIPTION
/v1/leads
Create a lead
/v1/leads/{id}/convertToProject
Convert a lead to a project
/v1/projects
List projects
/v1/projects/{projectId}/tasks
Create a project task
/v1/projects/{projectId}/milestones
Create a project milestone
/v1/daily-logs
Create a daily log
/v1/files/upload
Upload a file
/v1/webhookSubscriptions
Create a webhook subscription
/v1/leads
Create a lead
/v1/leads/{id}/convertToProject
Convert a lead to a project
/v1/projects
List projects
/v1/projects/{projectId}/tasks
Create a project task
/v1/projects/{projectId}/milestones
Create a project milestone
/v1/daily-logs
Create a daily log
/v1/files/upload
Upload a file
/v1/webhookSubscriptions
Create a webhook subscription
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Houzz Pro by hand means running the OAuth 2.0 client credentials exchange, requesting the right per-operation scopes such as write:projects or admin:leads, and paging list calls with limit and offset. Through Jentic you install once, import Houzz Pro from the API Directory, store the client credentials once, and your agent calls it.
Permission scoping
Houzz Pro puts the project id in the URL path for tasks, milestones, notes, and the punchlist (/v1/projects/{projectId}/...), so a rule can pin your agent to one project and the operations you pick. You choose the operations it may call, so destructive ones like project deletion or team member removal are not included unless you add them.
Credential isolation
Your Houzz Pro client credentials are stored once, encrypted, by your own Jentic One instance and used to fetch tokens at execution time. They never enter the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'convert a lead to a project' or 'log site work', and Jentic returns the matching Houzz Pro operation with its input schema so the agent sends the right projectId and fields without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Houzz Pro API v1 API through Jentic.
What authentication does the Houzz Pro API use?
Per its OpenAPI spec, the Houzz Pro API uses OAuth 2.0 with the client credentials flow: you exchange your client id and secret at the auth.houzz.com token endpoint for a bearer token. Tokens are issued per scope such as read:projects, write:leads, or admin:projects, and each operation lists the scope it requires. Through Jentic the client credentials are stored by your own instance, which handles the token exchange at call time.
Can I convert a lead into a project with the Houzz Pro API?
Yes. POST /v1/leads/{id}/convertToProject turns a lead into a project and requires both the write:projects and write:leads scopes. Before that, POST /v1/leads/{id}/updatePhase moves the lead to a phaseId from GET /v1/lead-phases, and retire or reactivate change whether the lead is active.
What are the rate limits for the Houzz Pro API?
The OpenAPI spec does not specify rate limits. Check https://developer.houzz.com for current limits; list endpoints page with limit and offset, so large exports should page rather than repeat full reads.
Is there a Houzz Pro MCP server?
You don't need an MCP server to give your agent Houzz Pro. Jentic connects it directly from the API Directory: import it, store your client credentials once, and your agent calls the lead, project, and task operations it needs, discovered on demand rather than loaded into its context up front.
How do I add a task to a project through Jentic?
Search Jentic for 'add a task to a Houzz Pro project', load POST /v1/projects/{projectId}/tasks, and pass a title with an optional dueDate and milestoneId. The token is attached by your instance. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the Houzz Pro API?
Yes. For example, allow only the task list and task create operations under /v1/projects/123/tasks plus POST /v1/daily-logs, and the agent can plan work and log site days for that one job but cannot delete leads, remove team members, or touch other projects, and every call it makes is logged.
Can I get notified when Houzz Pro records change?
Yes. GET /v1/webhookTriggers lists the available triggers, and POST /v1/webhookSubscriptions registers a url with the triggers you want, optional headers, and a maxAttempts retry setting. Subscriptions can be paused or edited later with PATCH /v1/webhookSubscriptions/{id}.
For Agents
Create and track Houzz Pro leads, convert them to projects, and manage project tasks, milestones, daily logs, files, contacts, and vendors for a contracting business.
Use for: Create a new lead for a kitchen remodel inquiry, Convert a won lead into a Houzz Pro project, List all open tasks on a project, Add a milestone for cabinet install to the project schedule
Not supported: Does not handle homeowner design browsing, product shopping, or payment processing. Use for running a contractor's Houzz Pro leads, projects, tasks, and records only.
The Houzz Pro API gives verified partners access to the records remodelers, builders, and designers run their business on in Houzz Pro: projects, leads, contacts, tasks, milestones, daily logs, punchlists, files, vendors, subcontractors, and team members. A lead moves through phases and converts into a project with one call, and each project carries its own milestones, tasks, punchlist, and notes. Custom fields, entity assignments, and webhook subscriptions let an integration extend records, assign work to people, and react to changes, with list endpoints paged by limit (up to 300) and offset.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>