Home / MCP registry index / io.github.rwaldman/agentbits
Agent Bits
io.github.rwaldman/agentbits in the official MCP registry.
Endpoint https://agentbits.dev/mcp. Source: github.com/rwaldman/agentbits.
The registry describes it as: Machine-readable utilities and datasets for AI agents.
We read its 18 tools on 2026-10-27. Nothing in them matched our tool-poisoning rules.
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
base64_decode base64_encode countries_bulk country_lookup currency_lookup http_status_lookup isbn_validate json_validate language_lookup luhn_validate mime_lookup timestamp_convert timezone_convert tld_lookup unit_convert url_decode url_encode uuid_validate
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/io-github-rwaldman-agentbits)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.