canli-mcp / What failed

Where can AI read about quant strategies that failed?

canli-mcp's search_research reads Canli Capital's open research record, including every candidate that failed its tests. A search for momentum returned five failed candidates, among them 52-week-high momentum and residual momentum, each with a page saying what was tried. It is free with no key. It is our own record, so weigh that.

Price: $0 to run. Updated 2026-11-08. Free and MIT-licensed, with no account and no API key. Or run claude mcp add canli -- npx -y canli-mcp in Claude Code.

Ask it

What has been tried on momentum and failed?

The agent finds the tool through canli-mcp's find_tool and runs it through run_tool. This is the call:

{
  "name": "search_research",
  "arguments": {
    "query": "killed momentum",
    "limit": 5
  }
}

What came back

Recorded from canli-mcp 0.16.1 on 2026-11-02, with no API key set. The model read 1,274 characters.

What search_research returned, every row
slugtitleyearurlarchival
kill-alphamax-betaneutralBeta-Neutral Momentum Construction (campaign): a killed candidate2026sourcefalse
kill-eq-52whigh52-Week-High Momentum (campaign): a killed candidate2026sourcefalse
kill-eq-mom-marginEquity Momentum (with Margin Costs): a killed candidate2026sourcefalse
kill-prereg-momentumPre-Registered Momentum (deep history): a killed candidate2026sourcefalse
kill-residual-momentumResidual (beta-neutral) Momentum (campaign): a killed candidate2026sourcefalse
The result search_research sent back, in full form
{
  "ref": "r2",
  "query": "killed momentum",
  "matched": 5,
  "columns": [
    "slug",
    "title",
    "year",
    "url",
    "archival"
  ],
  "rows": [
    [
      "kill-alphamax-betaneutral",
      "Beta-Neutral Momentum Construction (campaign): a killed candidate",
      "2026",
      "https://canlicapital.com/research/kill-alphamax-betaneutral",
      false
    ],
    [
      "kill-eq-52whigh",
      "52-Week-High Momentum (campaign): a killed candidate",
      "2026",
      "https://canlicapital.com/research/kill-eq-52whigh",
      false
    ],
    [
      "kill-eq-mom-margin",
      "Equity Momentum (with Margin Costs): a killed candidate",
      "2026",
      "https://canlicapital.com/research/kill-eq-mom-margin",
      false
    ],
    [
      "kill-prereg-momentum",
      "Pre-Registered Momentum (deep history): a killed candidate",
      "2026",
      "https://canlicapital.com/research/kill-prereg-momentum",
      false
    ],
    [
      "kill-residual-momentum",
      "Residual (beta-neutral) Momentum (campaign): a killed candidate",
      "2026",
      "https://canlicapital.com/research/kill-residual-momentum",
      false
    ]
  ],
  "next": "get_paper with a slug returns the paper, which states its own claim boundary; an archival publication has no slug and is read at its url.",
  "limits": [
    "These are research documents as Canli Capital published them; each paper states its own claim boundary, and a finding holds only within it.",
    "Paper execution only: nothing here is funded performance or investment advice."
  ]
}

Prices, filings and statistics are as the sources published them on that day; run the call again for today's. Nothing here is investment advice.

The tools behind the answer

From canli-mcp's tool index
ToolPackWhat it does
search_researchresearchFind Canli Capital research papers (strategy tests, killed candidates, literature reviews, feasibility protocols) by words in their titles and summaries. Use it to find a paper's slug, then read it with get_paper; to browse by subject instead, use list_topics.

Add canli-mcp

Claude Code
claude mcp add canli -- npx -y canli-mcp
Cursor, Claude Desktop or any MCP client
{ "mcpServers": { "canli": { "command": "npx", "args": ["-y", "canli-mcp"] } } }
claude.ai, ChatGPT or any client that takes a URL
https://canlicapital.com/mcp/canli

Everything canli-mcp does · How it compares with other finance MCP servers

Related questions