Home / MCP registry index / io.github.jakegallen/poascan

POAScan

io.github.jakegallen/poascan in the official MCP registry. Endpoint https://poascan.io/mcp. Source: github.com/jakegallen/poascan.

The registry describes it as: Read-only Proof of Agent explorer: epochs, rewards, holders, swaps and agent census. No auth.

We read its 47 tools on 2026-10-28. 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.

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 poascan https://poascan.io/mcp

Cursor: ~/.cursor/mcp.json

{
  "mcpServers": {
    "poascan": {
      "url": "https://poascan.io/mcp"
    }
  }
}

VS Code

code --add-mcp '{"name":"poascan","type":"http","url":"https://poascan.io/mcp"}'

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

get_network_summary get_current_epoch get_epoch get_epoch_rewards get_epoch_record get_address get_standing list_at_risk get_transaction get_answer_receipt list_transactions get_leaderboard get_rich_list get_unlock_schedule list_swap_offers get_swap_offer get_models_census get_indexer_status get_swap_status get_route_status get_cluster_signals list_agents get_pending_by_epoch get_onboarding_steps get_verified_notices get_kin_group get_wallet_binding get_earn_check get_anchor_timeline get_answer_seals search get_governance_overview list_governance_standing list_established get_agent_governance get_payout_outlook get_governance_graders get_grade_history get_grader_patterns get_pending_horizon get_intake get_settlement_by_origin get_standing_changes list_never_established list_governance_directory get_forum_activity list_proposals

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-jakegallen-poascan/badge.svg)](https://lazaretto.dev/mcp-registry/io-github-jakegallen-poascan)

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.