Websites had their WordPress moment. SaaS is having its BuildWithHQ moment. See the new BuildWithHQ homepage →
Model Context Protocol

Give AI the right amount of access at every layer

BuildWithHQ exposes four distinct MCP surfaces: one for your BuildWithHQ account, one inside the isolated developer VM, one for a specific SaaS application, and one you can offer to your own end customers. Each surface has a different identity, a different authority boundary, and a different job.

Four MCP layers

From building the product to letting your customer bring their own AI

MCP is not one unrestricted connection into BuildWithHQ. The platform exposes the capabilities appropriate to the person, application, and environment making the request.

01 · Control plane

Builder Account MCP

Manage your BuildWithHQ account and SaaS portfolio: applications, domains, backups, API clients, integrations, marketplace products, capacity, security and account-level audit.

02 · Development

Developer VM MCP

Build code inside an isolated development machine with Codex, DeepSeek Harness or another agent, local PostgreSQL, local services, testing and controlled BuildWithHQ development capabilities.

03 · Application

SaaS Application MCP

Build and operate one SaaS application as one logical system across its runtime data, compliance logs and AI/vector data—without giving an agent raw database selection.

04 · Your customer

End-Customer MCP

Let your customers safely connect their preferred AI to your product, limited to the records, files, knowledge, workflows and actions that specific user is allowed to access.

BUILDER ACCOUNT MCP → DEVELOPER VM MCP → SAAS APPLICATION MCP → END-CUSTOMER MCP Manage the platform Build the code Build + operate the SaaS Use the finished product CustomerAccount scope Isolated VM scope SaaSApp scope AppAccount + User scope
01 · Builder Account MCP

Run your BuildWithHQ portfolio from the agent you already use

The Builder Account MCP operates at the control-plane level. It is for the people building and owning SaaS products on BuildWithHQ—not for the users inside those SaaS products.

Manage SaaS applications

List applications, inspect configuration and capacity, create or manage environments, and resolve app-level administration without manually navigating every screen.

Domains, backups and API clients

Add or verify domains, create backups, rotate scoped API credentials, and inspect integrations through the same permission-aware builder identity.

Marketplace and appliances

Find, install and manage approved templates, harnesses, integrations and custom-service packages across the builder's portfolio.

Account-level evidence

Search account audit activity, review capacity and security state, and answer operational questions across the SaaS products the builder actually owns.

Example tools

builder.apps.listbuilder.domains.managebuilder.backups.createbuilder.api_clients.rotate

Security boundary

The authenticated builder account and user establish scope. The agent does not get to choose a different customer account simply by placing another ID in a tool call.

02 · Developer VM MCP

A full AI development workstation without giving the VM open internet access

Each developer VM is an isolated workshop. Developers can write ordinary code, run AI coding agents, use their own local PostgreSQL database, launch local services and test aggressively. Crossing the VM boundary happens through controlled BuildWithHQ services.

VM & database architecture

Code with AI

Use Codex, DeepSeek Harness, local models or other approved developer agents against the source tree and BuildWithHQ development tools.

Your own PostgreSQL

The VM includes developer-controlled PostgreSQL for custom application data, migrations, experiments, pgvector, queues and private services.

Local freedom

Compile .NET, Node or Python, run tests, start localhost services, create APIs, use Git, create branches, break the dev database and restore it.

Controlled boundary services

AI models, package repositories, documentation, external integrations, deployment and BuildWithHQ services are reached through approved internal gateways instead of arbitrary internet access.

DEVELOPER VM ├─ source code + Git ├─ Codex / DeepSeek / AI tooling ├─ local PostgreSQL ├─ local APIs + tests │ └─ BuildWithHQ Developer MCP ├─ schema + app metadata ├─ docs + knowledge ├─ actions + validation ├─ packages + artifacts └─ deployment requests NO UNRESTRICTED VM → INTERNET ROUTE
03 · SaaS Application MCP

One SaaS application becomes an AI-operable system

The agent works with application capabilities rather than database credentials. BuildWithHQ resolves the correct runtime database, compliance-log database and AI/vector database behind the tool call.

Data model and records

Describe modules and fields, create and update records, search authorized data, and work with the same record model used by the visual application.

Recursive relationships

Discover and traverse the graph around a record—customer to contacts to conversations to opportunities to projects—without requiring a bespoke API for every relationship.

Pages, permissions and workflows

Create or modify application structure, configure workflows, inspect permission rules, preview role-specific experiences and prepare a release for validation.

Logs, knowledge and AI actions

Search application activity, retrieve permission-aware knowledge, propose governed AI actions and inspect outcomes without exposing the physical data stores to the model.

Build and operate

app.schema.describeapp.records.searchapp.relationships.traverseapp.pages.updateapp.workflows.create

Observe and reason

app.activity.searchapp.audit.searchapp.knowledge.searchapp.actions.proposeapp.validate
04 · End-Customer MCP

Let your customers bring their own AI to the SaaS you sell them

A builder can turn on a customer-facing MCP surface for the product they sell. The end customer's preferred AI can search, reason and act through the SaaS—but only inside that customer's user, role, location, record and field permissions.

Ask the business questions

“Which customers have gone quiet?” “Show my overdue invoices.” “Find every file and conversation related to this project.”

Take permitted actions

Create a follow-up, start an approved workflow, update a permitted record or draft a response through actions the SaaS builder has explicitly exposed.

Bring the AI you prefer

The product can work with compatible MCP clients instead of forcing every customer into one AI assistant or requiring the builder to create a new integration per model.

AI sees what the user sees

The MCP layer does not become a database backdoor. Hidden fields, unauthorized records and other customer accounts remain outside the caller's capability envelope.

A new reseller revenue stream

Charge for customer MCP access. Then sell skills on top of it.

You decide whether customer MCP is included, reserved for a higher plan, or sold as a monthly add-on. Because you own the SaaS relationship, MCP access can become another recurring line item in your customer's subscription.

Recurring add-onCustomer MCP AccessAdd an MCP surcharge to the customer's monthly SaaS plan for secure external AI connectivity.
Higher-value plansAI-Connected TierBundle MCP, higher AI usage, advanced actions and automation into a premium edition of your SaaS.
Vertical upsellCustomer Skill PacksCreate reusable AI skills for the workflows and jobs your specific industry performs, then include or sell those skills to customers.
Skills

Turn your SaaS knowledge into installable AI skills

An MCP connection exposes capabilities. A skill tells an AI how to combine those capabilities to perform a useful job in your product.

Collections Follow-Up SkillFind overdue invoices → review recent customer conversations → identify disputes → draft the appropriate follow-up → create a task or propose an approved message.
Field Service Dispatch SkillFind unassigned work orders → inspect technician skills and location → review current schedule → recommend assignments → start the dispatch workflow.
Account Growth SkillTraverse customer records, orders, opportunities, support history and AI knowledge → surface likely expansion opportunities → create approved sales follow-ups.

A skill can package

Instructions, permitted MCP tools, record and knowledge scope, workflow/action contracts, validation rules, approval expectations and domain-specific operating guidance.

A builder can monetize it

Include skills with premium plans, sell industry-specific skill packs, create custom skills for larger customers, or use skills to differentiate a white-label SaaS offering.

One capability layer

MCP is another way into the same governed application—not a second backend

A record update should not have one security implementation for the UI and a different one for AI. BuildWithHQ projects the same capability through whichever interface is calling it.

BUILDWITHHQ CAPABILITY │ ┌─────────────────┼─────────────────┐ │ │ │ ▼ ▼ ▼ UI REST MCP │ │ │ └─────────────────┼─────────────────┘ ▼ ACTION / SERVICE LAYER │ identity → permissions → policy │ validation → execution │ audit + correlation │ ▼ APPLICATION DATA

One permission result

The same caller should receive the same authorization outcome whether they arrive through the visual UI, REST, workflow automation or MCP.

One audit trail

AI tool calls can carry the same correlation, identity and action evidence as normal application activity.

One action definition

A business capability can be surfaced to UI buttons, REST clients, workflows, agents and MCP without reimplementing its business rules five times.

Authority stays server-side

The model can request or propose an operation. BuildWithHQ still decides whether the authenticated caller has permission to execute it.

Common questions

Questions about MCP in BuildWithHQ

Does the developer VM need unrestricted internet access for AI development?

No. The VM can use local development tools, its own PostgreSQL instance and approved BuildWithHQ gateways for AI, packages, documentation, integrations and deployment while remaining isolated from arbitrary internet destinations.

Can an MCP client directly choose one of the application's three databases?

No. The client requests application capabilities such as records, audit activity or knowledge. BuildWithHQ resolves the correct physical database behind that request.

Can the SaaS builder decide what end customers expose to AI?

Yes. Customer-facing MCP capabilities are selected by the SaaS builder and are further constrained by the authenticated end user's normal application permissions.

Can I charge my SaaS customers for MCP?

Yes. Customer MCP can be packaged as a paid add-on or premium plan feature, and builders can create specialized skills that use those MCP capabilities as additional customer value.

Build for humans, software and agents

Your SaaS doesn't just have an API. It can become an AI-operable business system.

Build visually, extend with code, develop with AI, expose governed capabilities through MCP, and decide how much of that power reaches each customer.

Start building today

Create the application first. The same records, relationships, permissions, workflows, knowledge and actions become the foundation for its MCP surface.

Get started freeExplore the platform