INDIVIDUAL MCP TOOL

get_desk

The agent’s own basket of the index it ranks: the paper book and the live book with every position (entry price, latest price, value, result, the Herd Score then and now, the reason), every fill with its transaction when live, the basket the rules pick right now, every listed coin held against the entry rules with the rules it fails, the same rules replayed over the record from the first Herd Score, and the caps herd-actor checks before any live swap.

herdsol.comnone authenticationAvailability not checked

LIVE ENDPOINT

https://herdsol.com/mcp

No auth detected

Connect to this endpoint to inspect the live schema for get_desk and invoke it with your own arguments.

Indexed input schema

{}

Risk classification

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

Parent server

herdsol.com

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.herd]
url = "https://herdsol.com/mcp"
enabled = true

Claude Code

.mcp.json

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

Claude Desktop

Settings → Connectors → Add custom connector

Name: herd
Remote MCP URL: https://herdsol.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": {
    "herd": {
      "url": "https://herdsol.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

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

Generic MCP

Client-specific MCP configuration

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

MCP Inspector

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

Related tools

get_scores — Every listed $ANSEM-ecosystem project with its Herd Score (0–100), pillars (on-chain, Herd’s own read, community), data coverage and AI/community disagreement, plus the weights used.
get_project — One listing’s Herd Score with all eight components and their inputs and evidence links, the Analyst’s class, the latest on-chain reading, score history and the agent’s predictions about it.
check_impersonators — The one real $ANSEM mint, and every token Herd has flagged for copying its name or ticker from another mint, with Solscan links.
get_discoveries — Tokens the Scout discovered around $ANSEM (pools against it, names that mention it) that are not listed and not flagged.
get_leads — Pages the agent reached by following links the listed projects publish: what it listed, what it refused and why.
get_predictions — Predictions with their probability, factors, resolution rule and — once resolved — the outcome, including misses.
get_track_record — Totals, accuracy, Brier score and calibration of every prediction, by type and horizon.
verify_commitment — The exact JSON of one daily batch, its SHA-256 and its Solana anchor.