研究表格生成与验证工具

# Download all examples at once
curl -O https://subindex-storage.s3.amazonaws.com/website_downloads/examples/subindex_client.py \
     -O https://subindex-storage.s3.amazonaws.com/website_downloads/examples/01_validate_table.py \
     -O https://subindex-storage.s3.amazonaws.com/website_downloads/examples/02_generate_table.py \
     -O https://subindex-storage.s3.amazonaws.com/website_downloads/examples/03_update_table.py \
     -O https://subindex-storage.s3.amazonaws.com/website_downloads/examples/04_reference_check.py
pip install requests
export SUBINDEX_API_KEY=sbx_live_...

claude mcp add subindex \
  --transport http \
  https://mcp-server-subindex-production.up.railway.app/ \
  --header "X-Api-Key: sbx_live_your_key_here"

{
  "mcpServers": {
    "subindex": {
      "type": "http",
      "url": "https://mcp-server-subindex-production.up.railway.app/",
      "headers": {
        "X-Api-Key": "sbx_live_your_key_here"
      }
    }
  }
}

claude mcp add subindex uvx mcp-server-subindex \
  -e SUBINDEX_API_KEY=sbx_live_your_key_here

{
  "mcpServers": {
    "subindex": {
      "command": "uvx",
      "args": ["mcp-server-subindex"],
      "env": {
        "SUBINDEX_API_KEY": "sbx_live_your_key_here"
      }
    }
  }
}

{
  "mcpServers": {
    "subindex": {
      "command": "uvx",
      "args": ["mcp-server-subindex"],
      "env": {
        "SUBINDEX_API_KEY": "${SUBINDEX_API_KEY}"
      }
    }
  }
}

[mcp_servers.subindex]
command = "uvx"
args = ["mcp-server-subindex"]

[mcp_servers.subindex.env]
SUBINDEX_API_KEY = "sbx_live_your_key_here"

codex mcp list

npx -y @smithery/cli@latest login
npx -y @smithery/cli@latest mcp add subindex/subindex --client claude-code

upload_file(filename, file_type, file_size [, file_path])   ← omit file_path on HTTP/Railway transport; run returned curl_command instead
  → start_table_validation(session_id, s3_key, filename)
      ┌── match found (score ≥ 0.85) → [preview auto-queued; response has preview_queued=true + job_id]
      └── no match → interview auto-started
            → wait_for_conversation / poll get_conversation
              → send_conversation_reply  (if AI asks questions)
              → [interview complete → preview auto-queued]

  → wait_for_job(job_id or session_id)  ← blocks until preview_complete
      → [optional] refine_config(conv_id, session_id, instructions)
      → approve_validation(job_id, cost_usd)
      → wait_for_job(job_id)            ← blocks until completed
      → get_results(job_id)

start_table_validation(session_id, s3_key, filename,
  instructions="This table lists hedge funds. Validate AUM, strategy, and HQ city. Use Bloomberg and SEC filings.")
  → response includes instructions_mode=true
  → wait_for_job(session_id)          ← config generation + preview tracked automatically
  → approve_validation(job_id, cost_usd)
  → wait_for_job(job_id)
  → get_results(job_id)

refine_config(conversation_id, session_id,
  "Use SEC filings as the primary source for revenue. Require exact match for ticker symbols.")

export SUBINDEX_API_KEY=sbx_live_...
python examples/01_validate_table.py companies.xlsx
python examples/01_validate_table.py companies.xlsx --refine "Add LinkedIn URL column"

 Fire-and-forget: provide instructions to skip the interview entirely
python examples/01_validate_table.py companies.xlsx \
    --instructions "This table lists hedge funds. Validate AUM, strategy, and HQ city."

start_table_maker("Top 20 US biotech companies: name, ticker, market cap, lead drug, phase")
  → wait_for_conversation / poll get_conversation
    → send_conversation_reply  (if AI asks clarifying questions)
    → [table builds → preview auto-queued]

  → wait_for_job(session_id)          ← spans table-maker + preview phases
    → approve_validation(job_id, cost_usd)
    → wait_for_job(job_id)
    → get_results(job_id)

start_table_maker(
  "Top 20 US hedge funds: fund name, AUM, primary strategy, founding year, HQ city",
  auto_start=True)
  → wait_for_conversation(conversation_id, session_id)
      ← returns trigger_execution=true on first response (no Q&A)
  → wait_for_job(session_id)          ← table building + preview
  → approve_validation(job_id, cost_usd)
  → wait_for_job(job_id)
  → get_results(job_id)

python examples/02_generate_table.py "Top 10 US hedge funds: fund name, AUM, strategy, HQ city"
python examples/02_generate_table.py --prompt-file my_spec.txt

 Fire-and-forget: skip clarifying Q&A and generate immediately from the prompt
python examples/02_generate_table.py --auto-start "Top 10 US hedge funds: fund name, AUM, strategy, HQ city"

update_table(source_job_id)           ← re-validates existing enriched output
  → wait_for_job(new_job_id)          ← blocks until preview_complete
    → approve_validation(new_job_id, cost_usd)
    → wait_for_job(new_job_id)
    → get_results(new_job_id)

python examples/03_update_table.py session_20260217_103045_abc123
python examples/03_update_table.py session_20260217_103045_abc123 --version 2

start_reference_check(text="...")           ← inline text (or auto_approve=True to skip the gate)
  or
upload_file(filename, "pdf", file_size [, file_path])   ← upload PDF/document first
  → start_reference_check(s3_key=s3_key)

→ wait_for_job(job_id)                ← spans extraction + 3-row preview; stops at preview_complete
  → preview_table (3 validated sample claims) + cost_estimate shown in response
  → approve_validation(job_id, approved_cost_usd=X)   ← triggers Phase 2
  → wait_for_job(job_id)              ← waits for completed
  → get_results(job_id)               ← download_url (XLSX) + interactive_viewer_url + metadata_url

# Fact-check inline text
python examples/04_reference_check.py --text "Bitcoin was created by Satoshi Nakamoto in 2009."

# Fact-check a PDF
python examples/04_reference_check.py --file analyst_report.pdf

# Fact-check multiple documents concatenated
cat doc1.txt doc2.txt | python examples/04_reference_check.py --stdin

{
  "success": true,
  "data": { ... },
  "meta": { "request_id": "...", "timestamp": "..." }
}

import os, requests

BASE_URL = "https://api.subindex.ai/v1"
HEADERS  = {"Authorization": f"Bearer {os.environ['SUBINDEX_API_KEY']}"}

def api_get(path, **kwargs):
    r = requests.get(f"{BASE_URL}{path}", headers=HEADERS, **kwargs)
    r.raise_for_status()
    return r.json()["data"]

def api_post(path, **kwargs):
    r = requests.post(f"{BASE_URL}{path}", headers=HEADERS, **kwargs)
    r.raise_for_status()
    return r.json()["data"]

{
  "filename": "companies.xlsx",
  "file_size": 2048000,
  "file_type": "excel",
  "content_type": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
}

{
  "session_id": "session_20260305_...",
  "s3_key": "results/.../file.xlsx",
  "filename": "companies.xlsx",
  "instructions": "Validate AUM, strategy, and HQ city. Use Bloomberg and SEC filings as sources.",
  "config_id": "session_20260217_103045_abc123_config_v1_..."
}

{
  "message": "Top 20 US hedge funds: fund name, AUM, primary strategy, founding year, HQ city",
  "auto_start": true
}

{ "error": "insufficient_balance", "required_usd": 4.20, "current_balance_usd": 1.50 }