Home / MCP registry index / io.github.tang-vu/keryx
io.github.tang-vu/keryx
io.github.tang-vu/keryx in the official MCP registry.
Endpoint https://keryx.cc/mcp. Source: github.com/tang-vu/keryx.
The registry describes it as: Budgeted research with cited evidence and visible payment state on the selected Arc network.
We read its 25 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
evidence_draft draft_check evidence_procurement deliverable_acceptance_read deliverable_acceptance_submit operator_obligations_read paper_lookup research keryx_status research_monthly keryx_operator_status keryx_public_job_ledger keryx_purchase_outcomes keryx_source_learning profile_read profile_update history_read history_owned_read history_export history_private_jobs_list history_private_jobs_detail history_private_jobs_export run_privacy_read run_owner_export profile_identities_read
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/io-github-tang-vu-keryx)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.