Analytics

agiscorecard.com

Tracks and scores AI-related predictions and theses, providing verdicts and a market-call ledger.

2 endpoints11 known toolsFirst detected August 15, 2026Last detected August 15, 2026

ENDPOINT 1

https://agiscorecard.com/mcp

No auth detected

MCP server metadata

Name: agiscorecard
Version: 0.1.0

Capabilities

tools

Server instructions

The AGI Scorecard evidence layer: auditable verdicts on the 8 Situational Awareness predictions, the 0-100 AGI-2027 Thesis Tracker, and full-site search. All data CC BY 4.0 — cite agiscorecard.com.

Known tools 4

get_thesis_tracker

The AGI-2027 Thesis Tracker: a single auditable 0-100 score of how much of Aschenbrenner's Situational Awareness thesis is holding up, with method and full score history.

Inferred read-only

get_verdicts

All 8 graded Situational Awareness predictions with current verdict, evidence summary and primary sources.

Inferred read-only

get_sunwatch_track_record

The SunWatch market-call ledger (invest.

Inferred read-only

search_site

Search every page and tool on agiscorecard.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agiscorecard]
url = "https://agiscorecard.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agiscorecard": {
      "type": "http",
      "url": "https://agiscorecard.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agiscorecard
Remote MCP URL: https://agiscorecard.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agiscorecard": {
      "url": "https://agiscorecard.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agiscorecard": {
      "type": "http",
      "url": "https://agiscorecard.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agiscorecard",
  "transport": "streamable-http",
  "url": "https://agiscorecard.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 2

https://mcppulse.agiscorecard.com/mcp

No auth detected

MCP server metadata

Name: io.github.f-tiger/agentic-commerce-tools
Version: 1.1.0

Capabilities

tools

Server instructions

Free tools for the agentic-commerce stack: scan any remote MCP server for health/conformance (check_mcp_server), score any website's readiness for AI shopping agents (agent_readiness_scan), audit a site's agent-discovery well-known files (check_wellknown_discovery), generate a spec-correct llms.txt (generate_llms_txt), look up agentic-commerce/MCP glossary definitions (define_term), read a weekly index of public MCP servers (get_public_mcp_index), and read the DTC AI Visibility Index (get_visibility_index). All tools are free; please self-limit to a few calls per minute. For high-volume or production agent use, the same scans are available pay-per-call ($0.005, USDC on Base, no account or API key) via the x402 protocol at https://x402.agiscorecard.com.

Known tools 7

check_mcp_server

Run a free, live health, conformance and latency scan of any remote MCP (Model Context Protocol) server over streamable HTTP.

Inferred read-only

agent_readiness_scan

Score any website 0-100 on how ready it is for AI agents and AI shopping assistants (free, via AgentReady, agentready.

Inferred read-only

get_public_mcp_index

Return the Public MCP Server Index: a weekly-refreshed health, conformance and latency ranking of popular public (no-auth) remote MCP servers, scored 0-100 by the same live JSON-RPC handshake used by check_mcp_server.

Inferred read-only

check_wellknown_discovery

Audit any website's agent-discovery surface in one call (free, via tools.

Inferred read-only

generate_llms_txt

Generate a complete, spec-correct llms.

Inferred read-only

define_term

Look up a plain-English definition of any agentic-commerce, MCP, AI-visibility or agent-payments term from the Agent Glossary (glossary.

Inferred read-only

get_visibility_index

Return the DTC AI Visibility Index: a recurring audit of well-known direct-to-consumer brands (Casper, Ridge, Away, Rothy's and ~35 more) scored 0-100 on AI-agent visibility — robots.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.io-github-f-tiger-agentic-commerce-tools]
url = "https://mcppulse.agiscorecard.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "io-github-f-tiger-agentic-commerce-tools": {
      "type": "http",
      "url": "https://mcppulse.agiscorecard.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: io-github-f-tiger-agentic-commerce-tools
Remote MCP URL: https://mcppulse.agiscorecard.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "io-github-f-tiger-agentic-commerce-tools": {
      "url": "https://mcppulse.agiscorecard.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "io-github-f-tiger-agentic-commerce-tools": {
      "type": "http",
      "url": "https://mcppulse.agiscorecard.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "io-github-f-tiger-agentic-commerce-tools",
  "transport": "streamable-http",
  "url": "https://mcppulse.agiscorecard.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.