← qbuntu.ai

INDIVIDUAL MCP TOOL

similar_strategies

Strategies nearest in meaning to a given one — the neighbourhood around an idea.

qbuntu.ainone authenticationAvailability not checked

LIVE ENDPOINT

https://mcp.qbuntu.ai/mcp

No auth detected

Connect to this endpoint to inspect the live schema for similar_strategies 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

qbuntu.ai

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.qbuntu]
url = "https://mcp.qbuntu.ai/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "qbuntu": {
      "type": "http",
      "url": "https://mcp.qbuntu.ai/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: qbuntu
Remote MCP URL: https://mcp.qbuntu.ai/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": {
    "qbuntu": {
      "url": "https://mcp.qbuntu.ai/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "qbuntu": {
      "type": "http",
      "url": "https://mcp.qbuntu.ai/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "qbuntu",
  "transport": "streamable-http",
  "url": "https://mcp.qbuntu.ai/mcp"
}
MCP Inspector

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

Related tools

  • corpus_overview — Current scale and composition of the qbuntu corpus.
  • search_strategies — Find strategies by meaning — the tool to reach for when someone describes a trading idea and wants to know whether it has already been tested.
  • list_strategies — Browse the corpus by filter (no query).
  • get_strategy — Full public record for one strategy: hypothesis, methodology, verdict reasoning, median metrics across the parameter grid, categories and runs.
  • what_doesnt_work_for — The inverse of every other finance source: strategies in this direction that did NOT hold up (verdict rejected or marginal), with the reason.
  • facts_for — Atomic, individually citable facts — the surface to use when quoting a number.
  • list_categories — All strategy categories with how many strategies sit in each.
  • get_stock — Per-stock analysis for one ticker: how qbuntu's tested models predicted THIS stock (hit rate, contribution, the model that produced it).