Home / MCP registry index / ai.finestructure/fine-structure
Fine Structure
ai.finestructure/fine-structure in the official MCP registry.
Endpoint https://finestructure.ai/api/mcp.
The registry describes it as: Build and host full-stack apps from a prompt, with agents that reach you on WhatsApp and email.
We read its 99 tools on 2026-10-21. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
create_app agency_create_client agency_list_clients agency_create_client_app agency_create_claim_link agency_get_claim_status update_app publish_app get_platform_guide get_recommended_workflow get_job_status get_app_status get_app_links list_app_domains set_app_subdomain check_subdomain_available add_custom_domain get_domain_verification check_domain_verification set_primary_domain remove_custom_domain get_domain_ssl_status configure_domain_redirects list_apps get_app_files read_app_file read_app_files write_app_file patch_app_file rename_app_file get_app_detail get_entities query_entity seed_entity create_entity_records update_entity_record update_entity_records delete_entity_records get_pages get_errors get_app_analytics get_preview_url list_saved_versions create_change_set add_file_change validate_change_set apply_change_set discard_change_set validate_app inspect_preview get_app_security_context set_route_policy set_function_policy invoke_function create_platform_request get_platform_request list_platform_requests reply_platform_request update_platform_request set_entity_policy and 39 more
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/ai-finestructure-fine-structure)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.