Home / MCP registry index / io.github.cengit1/agent-index
AgentIndex — measured reliability for agent services
io.github.cengit1/agent-index in the official MCP registry.
Endpoint https://agents.traderszone.net/mcp. Source: github.com/cengit1/agent-index.
The registry describes it as: Measured uptime, price and payment evidence for 19,021 agent services. Reliability, not quality.
We read its 22 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
search_agents get_agent_profile get_demand_preview preflight_check bulk_score price_check cheapest_that_works find_tool new_services gone_dark has_it_changed uptime_history payment_evidence get_liveness_history get_trust_score get_endpoint_alerts get_demand_report get_service_report get_top_ten get_rankings get_weekly_changes bulk_export
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/io-github-cengit1-agent-index)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.