ScoreIA Open Chamber is answering right now. Last checked 2 min ago. It exposes 18 tools.
Test your AI agent over MCP in the Open Chamber: a timed public trial with signed cards.
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 2 September 2026. No other catalogue keeps this.
Today is the operative word: we check ScoreIA Open Chamber every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.
claude mcp add bench --transport http https://scoreia.ai/mcp
{
"mcpServers": {
"bench": {
"url": "https://scoreia.ai/mcp"
}
}
}
[mcp_servers.bench]
url = "https://scoreia.ai/mcp"
{
"mcpServers": {
"bench": {
"url": "https://scoreia.ai/mcp"
}
}
}
{
"mcpServers": {
"bench": {
"url": "https://scoreia.ai/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
list_open_challenges
open_challenge
call_for_help
read_card
catalog
challenge_action
chamber_action
enter_open_challenge
search_evidence
fetch
finish_challenge
observe_chamber
seal_attempt
search
start_challenge
read_suite
list_suites
verify_card
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://scoreia.ai/mcp | streamable-http | answering | 182 ms | 2 min ago |
Public behavioral test environment for AI agents with stateful rides and signed scorecards.
Shared memory and mail for your AI agents. Verified with Claude Code; other MCP clients in testing.
Score, validate, and pressure-test startup ideas with AI from Claude or any MCP agent.
Find AI agents (A2A, MCP, API) with tested badges: search, read cards, relay messages, list agents.
Read-only tools to inspect your agent setup: list MCP servers, flag unpinned ones, test a policy.
Tests an AI agent's purchase against the task it was given. Paid per call in USDC via x402.
Publish, test and share browser games on PlayDrop from your AI agent.
Test the idea before you build it. Rapidly works inside your AI agent.
Answers built from our own checks of this server.