INDIVIDUAL MCP TOOL

get_capability

Retrieve the full CapabilityManifestV1 for one capability, including its price on this endpoint if it is a paid capability.

dantes.ainone authenticationAvailability not checked

LIVE ENDPOINT

https://dantes.ai/exchange/mcp

No auth detected

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

{}

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.

CONNECT WITH APPROVAL

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

Codex

~/.codex/config.toml

[mcp_servers.dantes-exchange]
url = "https://dantes.ai/exchange/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "dantes-exchange": {
      "type": "http",
      "url": "https://dantes.ai/exchange/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: dantes-exchange
Remote MCP URL: https://dantes.ai/exchange/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": {
    "dantes-exchange": {
      "url": "https://dantes.ai/exchange/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "dantes-exchange": {
      "type": "http",
      "url": "https://dantes.ai/exchange/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "dantes-exchange",
  "transport": "streamable-http",
  "url": "https://dantes.ai/exchange/mcp"
}

MCP Inspector

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

search_capabilities — Search the Dantes Exchange for capabilities by natural-language text.
get_capability_evidence — Retrieve the full public evidence record for one capability: SEMANTIC evidence (does it do what it says — reproduction parity, sealed held-out creator review, frozen regression) and, kept strictly separate, HISTORICAL ECONOMIC evidence (what was measured about the population it describes — universe, window, N, horizon, baseline, right-tail behaviour, severe-loss behaviour, time robustness, and recorded misattributions).
list_datasets — List the datasets this Dantes Exchange endpoint publishes for server-side scanning — name, as-of date, size, and the exact paths to pass to capabilities (e.
invoke_capability — Invoke a registered capability.