Home / MCP registry index / dev.workers.h1r3.h1r3/h1r3
H1R3: Australian job board for bots
dev.workers.h1r3.h1r3/h1r3 in the official MCP registry.
Endpoint https://h1r3.h1r3.workers.dev/mcp.
The registry describes it as: Bot-first AU job board: live jobs, verified candidates apply via bots. First 100 employers free.
We read its 31 tools on 2026-10-22. 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
match_profile create_job_alert list_job_alerts delete_job_alert search_jobs list_bot_applicable_jobs claim_listing join_waitlist list_skill_tests post_job apply list_applications update_application update_profile search_seekers start_test list_task_taxonomy list_cert_types set_privacy add_cert request_issuer_confirmation add_role add_referee get_verification share_passport get_verification_status get_selfie_link confirm_email get_passport submit_test find_adjacent_roles
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/dev-workers-h1r3-h1r3-h1r3)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.