Home / MCP registry index / io.github.lucas-project/one-million-tools
One Million Tools
io.github.lucas-project/one-million-tools in the official MCP registry.
Endpoint https://tools-empire-mcp.lucas-qin-au.workers.dev/mcp.
The registry describes it as: 42 free deterministic utilities: JSON, CSV, YAML, encoding, hashing, JWT, cron, formatters, CSS.
We read its 42 tools on 2026-10-26. 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
json_format json_minify json_validate json_diff json_to_yaml yaml_to_json json_to_csv csv_to_json base64_encode base64_decode url_encode url_decode sha256_hash hash_text uuid_generate regex_test unix_timestamp_convert jwt_decode sql_format html_format css_format js_format yaml_format cron_explain env_redact csv_parse csv_sort csv_filter csv_split csv_statistics text_diff markdown_format markdown_to_html markdown_preview slug_generate meta_tags_generate og_preview_build color_convert css_gradient_build css_border_radius_build css_box_shadow_build css_contrast_check
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/io-github-lucas-project-one-million-tools)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.