Paper Search

Available as MCP tools: paper_search + paper_read — call directly from Claude / Cursor / any MCP client. See MCP Server for the 60-second setup.

Live 1 credit · search free · read

What it does for your agent

paper_search returns the most relevant Quant Paper knowledge cards for a natural-language query — research on factors, anomalies, microstructure, ML for finance, and more. Use it as a literature entry point: when an agent needs to ground a claim in academic work (“is the momentum crash effect real?”, “what does the factor zoo paper actually say?”), call paper_search to surface candidate paperCardIds + availableSections, then paper_read to load the exact sections that answer the question. The vectors are built from title + abstract + summary + tags, so a card-level hit is a green light to call paper_read for sections — paper_search deliberately does not return full text.

Agent flow

Response

`paper_search` response

PaperCard[]

required

Ranked array of paper cards (highest relevance first).

Show PaperCard fields

string

required

Stable identifier. Pass to paper_read to load section content.

string

required

Identifier from the original source (e.g. arXiv ID).

string

required

Paper title.

string[]

required

List of paper authors.

string

required

Original abstract of the paper.

string

required

LLM-generated 2–3 sentence summary. Use this to decide whether to spend a paper_read call on full sections.

string[]

required

Research topic tags (e.g. factor, momentum, deep-learning).

object[]

required

Section manifest. Each entry has section_key, section_type, title, char_count, section_order. Use the section_key values when calling paper_read.

number

required

Total number of available sections.

number

required

Total character count across all sections.

string

required

Direct URL to the paper PDF.

number

Credits consumed by this call (always 1 for search).

number

Account credits remaining.

200 OK · paper_search

{
  "data": [
    {
      "paperCardId": "card_abc123",
      "sourcePaperId": "arxiv:1404.4944",
      "title": "Momentum Crashes",
      "authors": ["Kent Daniel", "Tobias J. Moskowitz"],
      "abstract": "Despite their strong positive abnormal returns, momentum strategies experience infrequent but severe crashes...",
      "summary": "Documents that momentum portfolios crash following bear-market rebounds. The crashes are forecastable in real time using market-state and volatility variables.",
      "tags": ["factor", "momentum", "crash"],
      "availableSections": [
        { "section_key": "introduction", "section_type": "introduction", "title": "Introduction", "char_count": 18420, "section_order": 1 },
        { "section_key": "methodology", "section_type": "method", "title": "Methodology", "char_count": 22150, "section_order": 2 }
      ],
      "sectionCount": 6,
      "fullTextCharCount": 102345,
      "pdfUrl": "https://arxiv.org/pdf/1404.4944"
    }
  ],
  "meta": { "creditsUsed": 1, "remainingCredits": 99 }
}

`paper_read` response

PaperReadResult

required

The selected sections of one paper card.

Show PaperReadResult fields

string

required

Stable identifier.

string

required

Identifier from the original source.

string

required

Paper title.

string[]

required

List of paper authors.

string

required

Original abstract.

string

required

LLM summary.

string[]

required

Topic tags.

string

required

Direct URL to the paper PDF.

object[]

required

Section manifest (same shape as in paper_search).

number

required

Total number of available sections.

number

required

Total character count across all sections.

object[]

required

The requested sections, in section_order. Each entry has section_key, section_type, title, content (Markdown), char_count, section_order.

number

Always 0 for read.

number

Account credits remaining.

Notes

Two-step lookup is canonical: paper_search returns IDs + summaries + section manifest cheaply (1 credit), then paper_read loads only the section(s) you actually need (free). Read top-1’s introduction + methodology first; pull more sections only when you need to verify a specific claim.

Decide which sections to read before calling paper_read by inspecting availableSections[i].char_count from paper_search. Avoid ["all"] for long papers — pull 1-2 targeted sections to keep agent context small.

Queries longer than 2,000 characters are rejected with 400. Summarize long agent context before calling.

topK is capped at 10 for paper_search. Higher values are silently clamped.

paper_search returns card-level metadata only — no full text. To get section content, you must call paper_read.

Direct invocation

HTTP / SDK examples

// 1) Search
{
  "method": "tools/call",
  "params": {
    "name": "paper_search",
    "arguments": { "query": "momentum crash", "topK": 5 }
  }
}

// 2) Read targeted sections from the top hit
{
  "method": "tools/call",
  "params": {
    "name": "paper_read",
    "arguments": {
      "paperCardId": "card_abc123",
      "sections": ["introduction", "methodology"]
    }
  }
}

import os, requests

base = "https://api.llmquantdata.com"
headers = {
    "Authorization": f"Bearer {os.environ['LLMQUANT_API_KEY']}",
    "Content-Type": "application/json",
}

# 1) Search
hits = requests.post(
    f"{base}/api/paper/search",
    headers=headers,
    json={"query": "momentum crash", "topK": 5},
).json()["data"]

# 2) Read targeted sections from the top hit
top = hits[0]
paper = requests.post(
    f"{base}/api/paper/read",
    headers=headers,
    json={
        "paperCardId": top["paperCardId"],
        "sections": ["introduction", "methodology"],
    },
).json()["data"]

for section in paper["sections"]:
    print(f"## {section['title']} ({section['char_count']} chars)")
    print(section["content"][:500])

# 1) Search
curl -X POST "https://api.llmquantdata.com/api/paper/search" \
  -H "Authorization: Bearer $LLMQUANT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "momentum crash", "topK": 5}'

# 2) Read targeted sections
curl -X POST "https://api.llmquantdata.com/api/paper/read" \
  -H "Authorization: Bearer $LLMQUANT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"paperCardId": "card_abc123", "sections": ["introduction", "methodology"]}'

Full parameter reference

paper_search — request parameters

string

required

Natural-language search query. Max 2,000 characters.

number

default:5

Maximum results to return. Range 1–10.

paper_read — request parameters

string

required

The paperCardId returned by paper_search.

string[]

default:["all"]

Section keys from availableSections[].section_key. Pass ["all"] (the default when omitted) to read every section.

Wiki Search

Same two-step pattern over the curated Quant Wiki corpus (concepts, formulas, factors).

MCP Server setup

Connect Claude / Cursor / any harness in 60 seconds.

Getting Started

Connect

Personal Context

Knowledge Data

Crypto Prices

Prediction Markets

Equity Prices

ETF

Macro Indicators

SEC Filings

News

SEC Form 13F

What it does for your agent

Agent flow

Response

`paper_search` response

`paper_read` response

Notes

Direct invocation

Full parameter reference

Wiki Search

MCP Server setup

​What it does for your agent

​Agent flow

​Response

​paper_search response

​paper_read response

​Notes

​Direct invocation

​Full parameter reference

​Related

Wiki Search

MCP Server setup

What it does for your agent

Agent flow

Response

`paper_search` response

`paper_read` response

Notes

Direct invocation

Full parameter reference

Related