mcp-server-subindex
MCP server for Subindex β generate, validate, and fact-check research tables with AI
Ask AI about mcp-server-subindex
Powered by Claude Β· Grounded in docs
I know everything about mcp-server-subindex. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
Subindex
Verified Research Engine Β· subindex.ai Β· Launch App
Subindex generates, validates, and updates research tables by synthesizing hundreds of calls to Perplexity and Claude. Give it a prompt or an existing table and it returns structured, verified answers across an entire research domain β not just a single query, but a complete field of questions answered at once.
| What you want to do | How | Live example |
|---|---|---|
| Gather everything β survey a complete research domain at once | Prompt β structured verified table | 50+ Phase 3 oncology trials |
| Monitor anything β news, analyst projections, time-sensitive data | Upload or generate β keep current | Market info for 10 stocks |
| See everywhere β run the same questions across many entities | One table, many subjects | GenAI adoption across Fortune 500 |
How to Access
| You want to⦠| Use |
|---|---|
| Try it out or iron out your use case | subindex.ai/app β web GUI for table validation and generation |
| Fact-check text or documents interactively | subindex.ai/chex β web GUI for reference checks |
| Let an AI agent drive a workflow autonomously | MCP server β install once, describe your task in plain English |
| One-off automation without writing code | MCP server via Claude Code, Claude Desktop, or any MCP-compatible client |
| Run repeatable pipelines or batch jobs | REST API + example scripts |
| Integrate into a product or SaaS | REST API directly |
GUI β API: The web GUIs are ideal for exploring and refining your use case. Once you know what you want, the MCP server or REST API is the better path β faster, repeatable, and fully automatable.
Table of Contents
- Get Your API Key
- Download Examples
- Quick Start: MCP
- Workflows
- Environment Variables
- Direct REST API
- MCP Prompts
- MCP Tool Reference
- Key Behaviors
- Pricing
- Links
Get Your API Key
Get your API key at subindex.ai/account. New accounts receive $20 in free credits.
Download Examples
All scripts require Python 3.10+ and
pip install requests.
| Script | Description | Download |
|---|---|---|
subindex_client.py | Shared REST client (required by all examples) | download |
01_validate_table.py | Validate an existing table | download |
02_generate_table.py | Generate a table from a prompt | download |
03_update_table.py | Re-run validation on a completed job | download |
04_reference_check.py | Fact-check text or documents | download |
Or clone the full example set:
# 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_...
Quick Start: MCP
The MCP server lets any AI agent drive the full Subindex workflow autonomously β no scripting required.
Option A β Direct HTTP connection to Railway (recommended for Claude Code)
Connects directly to the hosted Subindex server over HTTP. No local install, no uvx, no package management β just one command.
Claude Code:
claude mcp add subindex \
--transport http \
https://mcp-server-subindex-production.up.railway.app/ \
--header "X-Api-Key: sbx_live_your_key_here"
Via config file (.mcp.json in your repo root, or claude_desktop_config.json):
{
"mcpServers": {
"subindex": {
"type": "http",
"url": "https://mcp-server-subindex-production.up.railway.app/",
"headers": {
"X-Api-Key": "sbx_live_your_key_here"
}
}
}
}
Why HTTP over uvx? The HTTP connection runs on Railway β always up to date, no local Python environment needed, and no version drift between the package you installed and the live server. Recommended for Claude Code and any project-level config.
Option B β Local install via uvx
Runs the server locally on your machine using uvx. Useful for Claude Desktop or offline/air-gapped environments.
Claude Code:
claude mcp add subindex uvx mcp-server-subindex \
-e SUBINDEX_API_KEY=sbx_live_your_key_here
Claude Desktop β add to claude_desktop_config.json:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"subindex": {
"command": "uvx",
"args": ["mcp-server-subindex"],
"env": {
"SUBINDEX_API_KEY": "sbx_live_your_key_here"
}
}
}
}
Project config (shared repo) β add .mcp.json to your repo root. Each person uses their own key; no key is committed to the repo:
{
"mcpServers": {
"subindex": {
"command": "uvx",
"args": ["mcp-server-subindex"],
"env": {
"SUBINDEX_API_KEY": "${SUBINDEX_API_KEY}"
}
}
}
}
OpenAI Codex CLI β add to your Codex config file (~/.codex/config.toml on macOS/Linux, %USERPROFILE%\.codex\config.toml on Windows):
[mcp_servers.subindex]
command = "uvx"
args = ["mcp-server-subindex"]
[mcp_servers.subindex.env]
SUBINDEX_API_KEY = "sbx_live_your_key_here"
Then restart Codex and verify:
codex mcp list
Option C β Smithery
Smithery is an MCP registry that works with Claude Code and other MCP-compatible clients including OpenClaw.
Step 1 β Install and log in:
npx -y @smithery/cli@latest login
npx -y @smithery/cli@latest mcp add subindex/subindex --client claude-code
Step 2 β Authenticate with your API key:
Open your MCP client (e.g. Claude Code), go to /mcp, click subindex β Authenticate, and enter your Subindex API key in the Smithery page that opens.
Smithery login is a one-time step. You must log in before adding servers, or authentication will not be set up correctly.
What to Ask Your Agent
Once the MCP server is installed, describe your task in plain English. The agent drives the full workflow, pausing only when your input is genuinely needed.
Validate a table:
"Validate
companies.xlsxusing Subindex. Interview me about what each column means, then run the preview. If the results look good, approve the full validation."
Generate a table:
"Use Subindex to generate a table of the top 20 US hedge funds with columns: fund name, AUM, primary strategy, founding year, and HQ city. Approve the full validation when the preview looks right."
Re-run validation on the same table:
"Re-run update_table on job
session_20260217_103045_abc123to get an updated validation pass."
Fact-check a document:
"Use Subindex to fact-check this analyst report." (paste the text or share the file path)
Workflows
1. Validate an Existing Table
Minimum rows: Subindex is designed for tables with 4 or more data rows. Fewer rows may produce low-quality results.
Full flow: upload β interview β preview β refine β approve β download
upload_file(filename, file_type, file_size [, file_path]) β omit file_path on HTTP/Railway transport; run returned curl_command instead
β start_table_validation(session_id, s3_key, filename)
βββ match found (score β₯ 0.85) β [preview auto-queued; response has preview_queued=true + job_id]
βββ no match β interview auto-started
β wait_for_conversation / poll get_conversation
β send_conversation_reply (if AI asks questions)
β [interview complete β preview auto-queued]
β wait_for_job(job_id or session_id) β blocks until preview_complete
β [optional] refine_config(conv_id, session_id, instructions)
β approve_validation(job_id, cost_usd)
β wait_for_job(job_id) β blocks until completed
β get_results(job_id)
Key behavior: The preview is always auto-queued β after the interview finishes (
trigger_config_generation=true), or when a config match is found (match_score β₯ 0.85, response includespreview_queued: trueandjob_id). Callwait_for_job(session_id)directly in all cases (see Config reuse).
Upload interview auto-approval: The interview may auto-approve in a single turn. If the conversation response has
user_reply_needed: falseandstatus: approved, proceed towait_for_job(session_id)immediately β no reply is needed, even if the AI's message appears to ask for confirmation.
Skip the interview with instructions (fire-and-forget config generation):
Pass instructions to start_table_validation to bypass the interactive interview. The AI reads the table structure + your instructions and generates a config directly, then auto-triggers the preview β no clarifying questions needed.
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.")
β response includes instructions_mode=true
β wait_for_job(session_id) β config generation + preview tracked automatically
β approve_validation(job_id, cost_usd)
β wait_for_job(job_id)
β get_results(job_id)
Cost gate: Config generation and the 3-row preview are free. Full validation is charged at
approve_validationβ you always see the cost estimate atpreview_completebefore anything is billed. If your balance is insufficient,approve_validationreturns aninsufficient_balanceerror with the required amount.
Refine the config before approving by calling refine_config. This adjusts how columns are validated (sources, strictness, interpretation) β it cannot add or remove columns:
refine_config(conversation_id, session_id,
"Use SEC filings as the primary source for revenue. Require exact match for ticker symbols.")
A new preview runs automatically after refinement.
Python script: examples/01_validate_table.py
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."
Which mode to use: Always try
file_pathfirst. If the server can read the file (stdio/uvx transport), upload completes in one step. If you get "File not found" (HTTP/Railway transport β server is remote), call again withoutfile_pathto receive a presigned S3 URL and a ready-to-runcurl_command. The two-step path requires shell access to run curl; Claude Desktop users should use the uvx transport sofile_pathworks.
2. Generate a Table from a Prompt
Describe the table you want β rows, columns, scope β and Subindex builds and validates it from scratch. Designed for tables with 4 or more rows.
start_table_maker("Top 20 US biotech companies: name, ticker, market cap, lead drug, phase")
β wait_for_conversation / poll get_conversation
β send_conversation_reply (if AI asks clarifying questions)
β [table builds β preview auto-queued]
β wait_for_job(session_id) β spans table-maker + preview phases
β approve_validation(job_id, cost_usd)
β wait_for_job(job_id)
β get_results(job_id)
Auto-approve: The agent can auto-approve the preview and proceed to full validation without human intervention. The preview table is included inline in the
preview_completeresponse.
Cost: ~$0.05/cell (standard), up to ~$0.25/cell (advanced). $2 minimum per run.
Skip confirmation with auto_start=True (fire-and-forget generation):
Pass auto_start=True to skip the AI's clarifying questions and structure-confirmation step. The AI generates the table immediately from the message alone. Use when your message fully describes the desired table.
start_table_maker(
"Top 20 US hedge funds: fund name, AUM, primary strategy, founding year, HQ city",
auto_start=True)
β wait_for_conversation(conversation_id, session_id)
β returns trigger_execution=true on first response (no Q&A)
β wait_for_job(session_id) β table building + preview
β approve_validation(job_id, cost_usd)
β wait_for_job(job_id)
β get_results(job_id)
Why
wait_for_conversationwithauto_start=True? Even though there is no Q&A,wait_for_conversationis still required β it returnstrigger_execution: truein a single blocking call (no reply needed), signaling that the table-maker has started. Callingwait_for_jobbefore this call returns would be premature, as the table-maker may not have been triggered yet.
Cost gate: Table building and the 3-row preview are free. Full validation is charged at
approve_validationβ you always see the cost estimate atpreview_completebefore anything is billed. If your balance is insufficient,approve_validationreturns aninsufficient_balanceerror with the required amount.
Python script: examples/02_generate_table.py
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"
3. Update a Table (Re-run Validation Pass)
Re-run validation on a completed job β no re-upload or manual edits needed. The table iterates automatically, re-validating the same data with the same config to pick up any changes in source data.
If you want to incorporate manual edits to the output file, re-upload the edited file via upload_file + start_table_validation β a matching config will be found automatically (score β₯ 0.85).
update_table(source_job_id) β re-validates existing enriched output
β wait_for_job(new_job_id) β blocks until preview_complete
β approve_validation(new_job_id, cost_usd)
β wait_for_job(new_job_id)
β get_results(new_job_id)
Python script: examples/03_update_table.py
python examples/03_update_table.py session_20260217_103045_abc123
python examples/03_update_table.py session_20260217_103045_abc123 --version 2
4. Fact-Check Text or Documents (Chex)
Submit any text, report, or document. Subindex checks each factual claim against authoritative sources and returns the same output format as standard table validation: an Excel (XLSX) file, an interactive viewer URL, and a metadata JSON.
Minimum claims: Subindex is designed for text with 4 or more factual claims. Fewer claims may produce low-quality results.
start_reference_check(text="...") β inline text (or auto_approve=True to skip the gate)
or
upload_file(filename, "pdf", file_size [, file_path]) β upload PDF/document first
β start_reference_check(s3_key=s3_key)
β wait_for_job(job_id) β spans extraction + 3-row preview; stops at preview_complete
β preview_table (3 validated sample claims) + cost_estimate shown in response
β approve_validation(job_id, approved_cost_usd=X) β triggers Phase 2
β wait_for_job(job_id) β waits for completed
β get_results(job_id) β download_url (XLSX) + interactive_viewer_url + metadata_url
Three-phase flow: Phase 1 (claim extraction, free) runs automatically, then a 3-row preview validates sample claims (free, auto-triggered). Both phases are tracked by a single
wait_for_jobcall that stops atstatus=preview_complete. Reviewpreview_table(3 validated sample claims with support level and citations) andcost_estimate, then callapprove_validationto start Phase 2 (full validation, charged). Passauto_approve=Trueto skip the gate and run straight through tocompleted.
Progress tracking:
get_job_messagesreturns empty during claim extraction (Phase 1). Progress messages are available during the preview validation phase.wait_for_jobhandles both phases automatically.
Output: Excel (XLSX) file with per-claim rows. Support levels: SUPPORTED / PARTIAL / UNSUPPORTED / UNVERIFIABLE. Share interactive_viewer_url with human stakeholders β it renders sources and confidence scores in a clean UI.
Python script: examples/04_reference_check.py | Sample output: sample_outputs/reference_check_output.json
# 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
--stdin: Concatenates all piped content as a single inline text payload. All claims are attributed to the combined document.
Environment Variables
| Variable | Description |
|---|---|
SUBINDEX_API_KEY | API key from subindex.ai/account. Required. New accounts get $20 free. |
SUBINDEX_API_URL | Override the API base URL (useful for dev/staging environments). |
Direct REST API
All tools in the MCP server are thin wrappers over the REST API. You can call it directly from any language.
Base URL: https://api.subindex.ai/v1
Auth: Authorization: Bearer sbx_live_your_key_here
Response envelope:
{
"success": true,
"data": { ... },
"meta": { "request_id": "...", "timestamp": "..." }
}
Python client (minimal)
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"]
A full standalone client module is in examples/subindex_client.py.
API Endpoint Reference
Uploads
| Method | Path | Description |
|---|---|---|
POST | /uploads/presigned | Get a presigned S3 URL to upload a file |
PUT | <presigned_url> | Upload file bytes directly to S3 (no auth header) |
POST | /uploads/confirm | Confirm upload; detect config matches; auto-start interview if no match |
Presigned upload request:
{
"filename": "companies.xlsx",
"file_size": 2048000,
"file_type": "excel",
"content_type": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
}
Content types: excel β .xlsx, csv β .csv, pdf β .pdf
Confirm upload request (optional fields):
{
"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_..."
}
instructions β if provided, bypasses the interactive upload interview. The AI generates the config directly from the table structure + instructions. Response includes instructions_mode: true and conversation_id. Use wait_for_job(session_id) to track progress β do NOT poll the conversation.
config_id β if provided, skips matching and the interview entirely. The specified config is applied immediately and the preview is auto-queued. Response includes preview_queued: true and job_id. Use wait_for_job(job_id) to track progress. The configuration_id for any completed job is returned by GET /jobs/{id}/results under job_info.configuration_id.
Conversations
| Method | Path | Description |
|---|---|---|
POST | /conversations/table-maker | Start a Table Maker session with a natural language prompt |
GET | /conversations/{id}?session_id= | Poll conversation for status / AI messages |
POST | /conversations/{id}/message | Send a reply to the AI |
POST | /conversations/{id}/refine-config | Refine the config with natural language instructions |
Table Maker request body:
{
"message": "Top 20 US hedge funds: fund name, AUM, primary strategy, founding year, HQ city",
"auto_start": true
}
auto_start β if true, the AI skips clarifying questions and the structure-confirmation step, proceeding directly to table generation. The first get_conversation response will have trigger_execution: true. Use when your message fully describes the desired table.
Jobs
| Method | Path | Description |
|---|---|---|
GET | /jobs/{id} | Get job status and progress |
GET | /jobs/{id}/messages | Fetch live progress messages (paginated by since_seq) |
POST | /jobs/{id}/validate | Approve full validation β credits charged here |
GET | /jobs/{id}/results | Fetch download URL, metadata, viewer URL |
POST | /jobs/update-table | Re-validate enriched output after corrections |
POST | /jobs/reference-check | Submit text or file for claim verification |
Job status values:
| Status | Meaning |
|---|---|
queued | Accepted, waiting to start |
processing | Actively running |
preview_complete | Free preview done β review results and approve full run |
completed | Full validation complete, results ready |
failed | Error β check error.message |
Account
| Method | Path | Description |
|---|---|---|
GET | /account/balance | Current credit balance and this-month usage |
GET | /account/usage | Billing history (supports start_date, end_date, limit, offset) |
MCP Prompts
Three built-in prompts act as workflow starters β select them from the prompt picker in your MCP client (Claude Code: / menu; Claude Desktop: the prompt icon) and fill in the arguments.
| Prompt | Arguments | What it does |
|---|---|---|
generate_table | description (required), columns (optional) | Builds a step-by-step instruction for creating a new research table from a natural language description |
validate_file | file_path (required), instructions (optional) | Generates the full validation workflow for an existing Excel or CSV file |
fact_check_text | text (required) | Generates the reference-check workflow for fact-checking a text passage |
MCP Tool Reference
Every tool response includes a _guidance block with a plain-English summary and the exact next tool call(s) β enabling fully autonomous agent workflows.
| Tool | Description |
|---|---|
upload_file | Upload Excel, CSV, or PDF. Try with file_path first (one step, stdio/uvx). If the server can't read the local path, call again without file_path to get a presigned S3 URL + curl command (HTTP/Railway transport β requires shell to run curl). |
start_table_validation | Confirm upload; detect config matches; auto-start interview if needed |
start_table_maker | Start an AI conversation to generate a table from a prompt |
get_conversation | Poll a conversation for AI responses or status changes |
send_conversation_reply | Reply to AI questions during an interview or table-maker session |
wait_for_conversation | Block until conversation needs input or finishes (emits live progress) |
refine_config | Refine the validation config with natural language instructions (adjusts sources, strictness, interpretation β cannot add or remove columns) |
wait_for_job | Block until preview_complete, completed, or failed (preferred progress tracker) |
get_job_status | One-shot status poll |
get_job_messages | Fetch progress messages with native percentages (paginated) |
approve_validation | Approve preview β start full validation (credits charged here) |
get_results | Download URL, inline metadata, interactive viewer URL |
update_table | Re-validate enriched output after analyst corrections |
start_reference_check | Submit text or file for claim and citation verification |
get_balance | Check credit balance |
get_usage | Review billing history |
Key Behaviors
Auto-queued preview
The preview is automatically queued in all three paths after start_table_validation:
| Path | Trigger | What to call next |
|---|---|---|
| Config match (score β₯ 0.85) | preview_queued: true in response | wait_for_job(job_id) |
instructions= provided | instructions_mode: true in response | wait_for_job(session_id) |
| Interview ran | trigger_config_generation=true from conversation | wait_for_job(session_id) |
To reuse a config from a different session, pass config_id to start_table_validation β the preview will be auto-queued immediately.
Config reuse
If start_table_validation returns match_score β₯ 0.85, the preview is automatically queued using the matched config. The response includes preview_queued: true and job_id β call wait_for_job(job_id) directly, no interview needed.
The configuration_id from any completed job's get_results response can be reused on future uploads of similar tables.
Cost confirmation gate
approve_validation requires approved_cost_usd matching the preview estimate. This prevents surprise charges. The estimate is in the preview_complete job status response under cost_estimate.estimated_total_cost_usd.
This gate applies regardless of whether instructions or auto_start was used β both only skip the interview/confirmation conversation, not the cost approval step. If your balance is insufficient when approve_validation is called, the API returns:
{ "error": "insufficient_balance", "required_usd": 4.20, "current_balance_usd": 1.50 }
Fire-and-forget shortcuts
Two optional flags let fully automated pipelines skip interactive steps:
| Flag | Tool | Skips | Next step |
|---|---|---|---|
instructions="..." | start_table_validation | Upload interview Q&A | wait_for_job(session_id) |
auto_start=True | start_table_maker | Structure confirmation | wait_for_conversation β wait_for_job |
These flags use different terminal signals: instructions= (a config-gen flow) causes trigger_config_generation: true on the conversation response; auto_start=True (a table-maker flow) causes trigger_execution: true. Both skip interactive Q&A but produce different fields β do not wait for trigger_execution when using the instructions= upload path. The preview_complete cost gate and approve_validation still apply.
Consuming results: humans vs AI agents
Output files generated per run:
| File | Format | Description |
|---|---|---|
| Preview table | Markdown (inline) | First 3 rows as markdown text; returned inline in the preview_complete job status response (not a separate download). Also available in metadata.json under markdown_table. |
| Enriched results | Excel (.xlsx) | Ideal for sharing with humans; sources and citations are embedded in cell comments |
| Full metadata | metadata.json | Complete per-cell detail for every row; use the row_key field to drill into specific rows programmatically |
get_results returns:
| Field | Type | Best for |
|---|---|---|
results.interactive_viewer_url | URL | Humans β web viewer with confidence indicators (requires login at subindex.ai with the same email as your API key) |
results.download_url | Presigned URL | Humans β download the enriched Excel (.xlsx) directly |
results.metadata_url | Presigned URL | AI agents β JSON file with all rows, per-cell details, and source citations |
Recommended AI agent workflow:
- At
preview_complete: read the inlinepreview_table(markdown, 3 rows) fromGET /jobs/{id}to survey the table structure and spot-check values. The AI agent can review this inline table and callapprove_validationdirectly β no human approval step is required. - After full validation: fetch
results.metadata_urlβtable_metadata.json. This contains every validated row. - Use
rows[].row_key(stable SHA-256) to cross-reference rows between the markdown summary and the detailed JSON. - Per-cell fields in
table_metadata.json:cells[col].valueβ validated value (legacy files may usefull_value)cells[col].confidenceβHIGH/MEDIUM/LOW/IDcells[col].comment.validator_explanationβ reasoningcells[col].comment.key_citationβ top authoritative sourcecells[col].comment.sources[]β all sources withurlandsnippet
Pricing
| Mode | Cost |
|---|---|
| Preview (first 3 rows) | Free |
| Standard validation | ~$0.05 / cell |
| Advanced validation | up to ~$0.25 / cell |
| Minimum per run | $2.00 |
| Reference check | TBD β contact support |
Credits are prepaid. Get $20 free at subindex.ai/account.
Standard validation is used for most tables. Advanced validation is selected automatically when the table requires more sophisticated reasoning (e.g., scientific data, complex financial metrics, or cells with high ambiguity).
Links
- MCP server (HTTP, recommended):
claude mcp add subindex --transport http https://mcp-server-subindex-production.up.railway.app/ --header "X-Api-Key: sbx_live_..."β no install needed - MCP server (PyPI/uvx):
uvx mcp-server-subindexβ for Claude Desktop or offline use - Source: github.com/EliyahuAI/mcp-server-subindex
- Documentation: subindex.ai/mcp
- API reference: subindex.ai/api
- Account & credits: subindex.ai/account
