Developer Tools

finestructure.ai

Creates, updates, and publishes applications from natural language prompts.

1 endpoint82 known toolsFirst detected August 17, 2026Last detected August 24, 2026

ENDPOINT 1

https://finestructure.ai/api/mcp

No auth detected

MCP server metadata

Name: fine-structure-mcp
Version: 1.0.0

Capabilities

toolsprompts

Server instructions

Fine Structure builds and hosts complete web applications for the connected account: React pages, a managed database (called entities), authentication, publishing, custom domains with automatic TLS, restorable Saved Versions, traffic analytics, and autonomous AI agents with real messaging channels. Agents are the part people do not expect, so offer them explicitly. An agent created with create_agent is a standing worker on the account, not a chat session: it gets its own email address, it can message its verified owner on WhatsApp and by email through the platform system channels, it can read and write the app database, and schedule_agent_task gives it recurring work (once, hourly, daily, weekly or cron, in the owner timezone). Typical uses: follow up new leads on WhatsApp every morning, watch a published app for runtime errors and report them, send a weekly summary of traffic and new records, answer inbound email. The WhatsApp side is drivable from here, so offer it instead of sending the user to a settings screen. get_agent_whatsapp reports whether the owner phone is verified and which platform numbers are connectable. If it is not verified, ask for the owner own WhatsApp number, call start_owner_phone_verification, ask for the 6-digit code that arrives, and call confirm_owner_phone_verification. That one-time proof is what lets agents message the owner at all. Then attach_agent_whatsapp connects a platform number, and the owner can message that number from their verified phone and reach that specific agent. No WhatsApp Business account, no message template approval, nothing to buy. A number already used by another account is still a valid choice: it answers only this owner verified phone. Messaging people other than the verified owner needs a channel the owner connects in the Fine Structure Studio, so say that plainly rather than promising it. Call get_platform_guide with sections ["agents"] for the full capability list. First contact: when list_apps comes back empty, or the user connected this server and has not asked for anything specific, do not wait for instructions. Offer three concrete builds you can finish right now, for example a CRM with customers, jobs and invoices, a landing page with a lead form, or a booking system, and say plainly that the result will be live at a public link they can open and share. Then build the one they pick end to end without pausing for approval between steps, and hand back the live URL. A new user understands this platform through a finished app they did not have ten minutes earlier, not through a list of capabilities. Orientation: call get_platform_guide once at the start of a working session to learn the platform conventions, and list_apps to see what the account already has. get_recommended_workflow returns the tool sequence for a given task type. Building: create_app generates a complete app from a detailed natural-language prompt and returns a job_id; poll get_job_status until it is done, then publish_app, then share the live URL from get_app_links. For an existing app, edit files with write_app_file or patch_app_file, or stage a change set and apply it atomically. Run validate_app before publishing, and get_errors after. Useful things to offer someone connecting for the first time: build and publish a real app such as a CRM, booking system, client portal or landing page; connect a custom domain; put a page behind login; look at runtime errors and fix them; read traffic analytics; set up an agent that runs on a schedule and reports back. Costs: create_app and update_app spend the account's credits. File edits, publishing, domains, data tools and analytics do not. A free tier exists. Safety: every write creates a restorable Saved Version. Tools whose annotations mark them destructive delete or replace data, so confirm with the account owner before calling one. Authentication and credit errors are not retryable: report them to the user instead of looping.

Known tools 82

create_app

Create a new application from a natural language prompt.

Potential side effects

agency_create_client

Agency mode only.

Inferred read-only

agency_list_clients

Agency mode only.

Inferred read-only

agency_create_client_app

Agency mode only.

Inferred read-only

agency_create_claim_link

Agency mode only.

Inferred read-only

agency_get_claim_status

Agency mode only.

Inferred read-only

update_app

Update an existing application with a new prompt.

Potential side effects

publish_app

Publish an app - freeze current state and make it live at a URL.

Potential side effects

get_platform_guide

Return a machine-readable Fine Structure / FSe2 guide for AI agents.

Inferred read-only

get_recommended_workflow

Return the recommended MCP tool sequence for a task type.

Inferred read-only

get_job_status

Poll the status of an async generation job.

Inferred read-only

get_app_status

Get app overview: files, published state, URL, active jobs.

Inferred read-only

get_app_links

Return editor, preview, published path, subdomain, and custom-domain links plus whether each works for anonymous visitors, app users, or Studio users based on publish and auth settings.

Potential side effects

list_app_domains

List an app's platform path, subdomain, and configured custom domain with verification, SSL, primary-domain, redirect, publish, and login-gating status.

Potential side effects

add_custom_domain

Attach or replace the app custom domain through the same Fine Structure Studio custom-domain flow.

Inferred read-only

get_domain_verification

Return the exact DNS records and instructions required to verify and route the app custom domain.

Inferred read-only

check_domain_verification

Check Fine Structure custom-domain verification and SSL status for the configured custom domain, then save the latest status.

Inferred read-only

set_primary_domain

Set which app host should be treated as primary for generated links and custom-domain redirects.

Inferred read-only

remove_custom_domain

Remove the configured custom domain from the app and clean up the platform-side hostname registration when possible.

Potential side effects

get_domain_ssl_status

Return SSL/certificate status and pending certificate validation DNS records for the app custom domain.

Inferred read-only

configure_domain_redirects

Configure custom-domain redirect policy: primary domain, optional www/root redirect, and HTTPS enforcement.

Inferred read-only

list_apps

List applications owned by the authenticated user, newest activity first.

Inferred read-only

get_app_files

Get the file tree for an app with paths and byte sizes.

Inferred read-only

read_app_file

Read one source file from an app's virtual filesystem.

Inferred read-only

read_app_files

Read several source files from an app's virtual filesystem.

Inferred read-only

write_app_file

Create or replace one file in an app's virtual filesystem.

Potential side effects

patch_app_file

Patch one file by replacing exact text.

Inferred read-only

rename_app_file

Rename or move one app source file atomically.

Inferred read-only

get_app_detail

Deep introspection of an app: entities, pages, settings, integrations, environment variables, and file structure.

Inferred read-only

get_entities

Get all entity (data model) schemas for an app, with record counts.

Inferred read-only

query_entity

Query app data records for one entity with optional exact-match filters.

Inferred read-only

seed_entity

Compatibility tool for starter-record creation.

Inferred read-only

create_entity_records

Create/insert records in one app entity.

Potential side effects

update_entity_record

Compatibility tool that updates one record by ID.

Inferred read-only

update_entity_records

Update exact records.

Potential side effects

delete_entity_records

Delete exact records by ID or exact-match filters.

Potential side effects

get_pages

Get all pages in an app with their file paths and sizes.

Inferred read-only

get_errors

Get recent runtime errors for an app (last 20).

Inferred read-only

get_app_analytics

Traffic analytics for an app's published site over a chosen window: total views, unique visitors, daily series, top pages, top referrer domains and device split.

Inferred read-only

get_preview_url

Return editor preview and published/public URLs for an app.

Inferred read-only

list_saved_versions

List restorable Saved Versions for an app, including versions created by MCP writes.

Inferred read-only

create_change_set

Create a staged file change set.

Potential side effects

add_file_change

Stage one file upsert or delete inside a change set.

Potential side effects

validate_change_set

Validate current app files plus staged change set files before applying.

Inferred read-only

apply_change_set

Apply a staged change set to the app.

Inferred read-only

discard_change_set

Discard a pending staged change set without changing app files.

Inferred read-only

validate_app

Run deterministic app checks: syntax, imports, routes/pages, entity schemas, missing entities, and recorded runtime errors.

Inferred read-only

inspect_preview

Return server-side preview context: URLs, persisted runtime/network errors, static clickable candidates, pages, and explicit live-browser availability.

Inferred read-only

get_app_security_context

Return safe security context for one owned app: owner id/email, Studio collaborators, generated-app members, route policies, entity policies, and recent security audit entries.

Potential side effects

set_route_policy

Create or update a server-owned route policy for a generated app route.

Potential side effects

set_entity_policy

Create or update server-side read/write role policy for an app entity.

Potential side effects

list_app_members

List generated-app runtime users/members for an app.

Inferred read-only

invite_app_member

Provision a generated-app runtime member with a role.

Inferred read-only

update_app_member_role

Update a generated-app runtime member role.

Potential side effects

remove_app_member

Remove a generated-app runtime member.

Potential side effects

get_app_security_audit

Read recent server-side security audit events for an app.

Inferred read-only

compare_saved_versions

Compare two Saved Versions and return per-file additions, removals, modifications, and compact diffs.

Inferred read-only

compare_current_to_version

Compare the current app files to a Saved Version and return compact per-file diffs.

Inferred read-only

restore_file_from_version

Restore one file from a Saved Version instead of restoring the entire app.

Inferred read-only

create_entity_schema

Create an entity schema file in entities/<Entity>.json.

Potential side effects

update_entity_schema

Replace or shallow-merge an existing entity schema file.

Inferred read-only

validate_entity_relationships

Validate entity relationship metadata and *_id references against existing entity schemas.

Inferred read-only

update_entity_metadata

Set relationship/index metadata on an entity schema.

Inferred read-only

list_secret_keys

List secret key names for an app.

Inferred read-only

set_secret

Create or update one encrypted app secret.

Potential side effects

delete_secret

Delete one app secret by key.

Potential side effects

list_integrations

List supported integrations and safe connected integration metadata for an app.

Inferred read-only

configure_integration

Store safe non-secret integration metadata for an app.

Inferred read-only

list_ab_tests

List the platform A/B tests configured for an app.

Inferred read-only

create_ab_test

Create a native Fine Structure A/B test between existing app pages.

Potential side effects

update_ab_test

Update a native A/B test, including active state, variants, traffic, and conversion goal.

Potential side effects

delete_ab_test

Delete a native A/B test from an app.

Potential side effects

get_ab_test_stats

Get views, unique visitors, conversions, and conversion rates for an A/B test.

Inferred read-only

create_agent

Create an autonomous AI agent on the user's Fine Structure account: a standing worker, not a chat session.

Potential side effects

list_agents

List the AI agents on the user's account with id, name, role, status and FineMail address.

Inferred read-only

schedule_agent_task

Create a scheduled task for one of the user's agents.

Potential side effects

list_agent_tasks

List scheduled tasks for one agent (or the whole account), including schedule, status and next_run_at.

Inferred read-only

get_agent_whatsapp

Read the WhatsApp state of the connected account: whether the owner's phone is verified, which platform numbers they can connect, and which conversations already route to which agent.

Inferred read-only

start_owner_phone_verification

Send a 6-digit code over WhatsApp to the ACCOUNT OWNER's own phone.

Potential side effects

confirm_owner_phone_verification

Confirm the 6-digit code the owner received on WhatsApp from start_owner_phone_verification.

Inferred read-only

attach_agent_whatsapp

Connect a platform WhatsApp number to one of the account's agents, so the owner can message that number and reach that agent.

Potential side effects

detach_agent_whatsapp

Disconnect the owner's WhatsApp route from a platform number.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.fine-structure-mcp]
url = "https://finestructure.ai/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "fine-structure-mcp": {
      "type": "http",
      "url": "https://finestructure.ai/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: fine-structure-mcp
Remote MCP URL: https://finestructure.ai/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "fine-structure-mcp": {
      "url": "https://finestructure.ai/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "fine-structure-mcp": {
      "type": "http",
      "url": "https://finestructure.ai/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "fine-structure-mcp",
  "transport": "streamable-http",
  "url": "https://finestructure.ai/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.