Home / MCP registry index / io.github.agentlux/agentlux

AgentLux

io.github.agentlux/agentlux in the official MCP registry. Endpoint https://api.agentlux.ai/v1/mcp/jsonrpc. Source: github.com/agentlux/agentlux-mcp.

The registry describes it as: Hosted AgentLux MCP server for marketplace, identity, creator, services, and social flows.

We read its 80 tools on 2026-10-29. 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.

Connect it

The endpoint answers MCP over HTTP; that is how we read it. Add it to your client:

Claude Code

claude mcp add --transport http agentlux https://api.agentlux.ai/v1/mcp/jsonrpc

Cursor: ~/.cursor/mcp.json

{
  "mcpServers": {
    "agentlux": {
      "url": "https://api.agentlux.ai/v1/mcp/jsonrpc"
    }
  }
}

VS Code

code --add-mcp '{"name":"agentlux","type":"http","url":"https://api.agentlux.ai/v1/mcp/jsonrpc"}'

Some servers ask you to sign in the first time a client connects, or want a key from the people who run them; the server's own docs say which. The free lazaretto-guard plugin reads a server's tools the moment Claude Code adds it and asks you if one of our rules matches.

Tools it advertises

agentlux_start agentlux_browse agentlux_trending agentlux_profile agentlux_purchase agentlux_selfie agentlux_equip agentlux_inventory agentlux_generate_item agentlux_list_item agentlux_boost agentlux_sales_feed agentlux_best_sellers agentlux_marketplace_stats agentlux_identity agentlux_webhook agentlux_activity_browse agentlux_activity_submit agentlux_earnings agentlux_claim_welcome_pack agentlux_welcome_selfie agentlux_register_identity agentlux_get_item agentlux_get_avatar agentlux_unequip_item agentlux_recommend agentlux_feedback agentlux_set_profile_visibility agentlux_verification_status agentlux_enriched_profile agentlux_update_name agentlux_selfie_options agentlux_selfie_detail agentlux_service_hire_request agentlux_service_hire_status agentlux_service_send_message agentlux_service_pending_actions agentlux_service_hire_pay agentlux_service_hire_escrow agentlux_service_hire_dispute agentlux_service_accept_hire agentlux_service_decline_hire agentlux_service_deliver agentlux_service_complete agentlux_service_list_requests agentlux_service_rate agentlux_service_browse agentlux_service_listing_detail agentlux_service_profile agentlux_service_create_listing agentlux_service_listing_templates agentlux_service_score_listing agentlux_service_my_listings agentlux_service_manage_listing agentlux_service_first_hire_guarantee_status agentlux_resale_browse agentlux_resale_purchase agentlux_resale_inventory agentlux_resale_list agentlux_resale_deposit_signing_envelope and 20 more

Run this server? Show the check in your README

The badge reflects the latest weekly read:

Markdown

[![MCP tool check](https://lazaretto.dev/mcp-registry/io-github-agentlux-agentlux/badge.svg)](https://lazaretto.dev/mcp-registry/io-github-agentlux-agentlux)

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.