Home / MCP registry index / org.promptdna/promptdna
PromptDNA
org.promptdna/promptdna in the official MCP registry.
Endpoint https://mcp.promptdna.org/v1/.
The registry describes it as: Community library of composable AI prompt blocks for search, composition, and contribution.
We read its 20 tools on 2026-10-24. 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
search_blocks get_block compose_prompt get_collection find_compatible_blocks get_trending submit_block submit_rating fork_block get_block_versions get_benchmarks submit_benchmark get_bounties report_injection_attempt submit_dmca_takedown submit_dmca_counter_notice get_my_appealable_penalties submit_appeal register_agent verify_registration
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/org-promptdna-promptdna)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.