Home / MCP registry index / com.latchbell/latchbell
Latchbell
com.latchbell/latchbell in the official MCP registry.
Endpoint https://latchbell.com/mcp/agents.
The registry describes it as: Ask, book and buy from local businesses; owners run calls, texts, bookings and their website.
We read its 96 tools on 2026-11-11. 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 about every two weeks.
Connect it
The endpoint answers MCP over HTTP; that is how we read it. Add it to your client:
claude mcp add --transport http latchbell https://latchbell.com/mcp/agents{
"mcpServers": {
"latchbell": {
"url": "https://latchbell.com/mcp/agents"
}
}
}code --add-mcp '{"name":"latchbell","type":"http","url":"https://latchbell.com/mcp/agents"}'Some servers ask you to sign in the first time a client connects, or want a key from the people who run them; the server's own docs say which.
Let Claude Code check servers as it adds them
With the free lazaretto-guard plugin installed, when Claude Code adds a server for you or writes one into an MCP config, the plugin reads the server's tools first and asks you if one of our rules matches. Install it, restart Claude Code, then ask it to run the command above.
claude plugin marketplace add lazaretto-ai/lazaretto-plugins
claude plugin install lazaretto-guard@lazaretto-pluginsTools it advertises
find_services find_businesses business_info find_times book request_booking booking_status my_bookings reschedule_booking cancel_booking check_in products estimate_order request_order checkout_order catalog quote contact_business refresh_business_website search_business_info read_business_info inquiry_status update_conversation_customer follow_up_business ask_business my_inquiries register_business confirm_business_email my_business call_brief set_customer_notes receptionist_readiness receptionist_service receptionist_checkout cancel_receptionist_checkout receptionist_top_up receptionist_buy_minutes receptionist_billing_portal receptionist_limits customer_payment_onboarding receptionist_refresh receptionist_call_voice phone_numbers activate_phone_number phone_portability prepare_number_port place_phone_call phone_call coach_phone_call phone_calls pair_phone text_phones send_text service_setup update_team update_booking_rules update_catalog update_products front_desk update_front_desk and 36 more
Tool changes
We compare every full read of this server with the one before. No change in what its tools say has been seen since we started keeping this record on 2026-10-30.
Fingerprint of its tools at our last full read (2026-11-11):
d25b464371866524. A client can hash the tools it is served the same way and compare;
the full value and a hash per tool are in this page as JSON.
Rather than checking back: subscribe to this server's tool changes (a feed, no account and no address needed). Tool names and dates only, never what a tool says.
Run this server? Show the check in your README
The badge reflects the latest read: 
[](https://lazaretto.dev/mcp-registry/com-latchbell-latchbell)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. How tool poisoning works. What we found across the registry. Check another server.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.