Home / MCP registry index / com.odilelabs/odile
Odile Labs
com.odilelabs/odile in the official MCP registry.
Endpoint https://odilelabs.com/mcp. Source: github.com/tolga-boop/odile-mcp.
The registry describes it as: OdileM2M: agents reach businesses by phone number through Direct; Gate keys, limits and audit.
We read its 24 tools on 2026-10-28. 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
get_m2m_network get_agent_services find_business_agent send_to_business get_direct_usage get_direct_payment get_answering_line_offer try_answering_line set_up_answering_line get_sip_address get_answering_line get_line_calls get_line_messages get_receptionist_benchmark get_catalog estimate_media_job get_balance get_job get_downloads prepare_upload create_media_job unlock_job buy_pack estimate_meal_photo
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/com-odilelabs-odile)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.