ZBS Index What actually exists in applied AI, with the source next to it

mcp server

Unquant

Financial data MCP for market, company, news, macro, and US Congress research.

Description as published by the maintainer. Source

  • version 3.0.0
  • active
  • retrieval

active — Registry entry last updated 2026-08-04. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.

What this server can do

28 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

account_request_upgrade(value_summary, request_summary, next_step_summary)
Create a human-reviewed Agent Pro request after Unquant delivers useful work. The result contains a confirmation link. Required: request_summary, value_summary, next_step_summary.
account_upgrade_status(upgrade_id)
Return the current state of an Agent Pro request by upgrade identifier. Required: upgrade_id.
catalog_describe(entry_id)
Return the purpose, access state, inputs, and next action for one catalog entry. Required: entry_id.
catalog_list(limit, query, theme, cursor, job_id, status, item_type, geo_archetype)
List data, signals, tools, and workflows. Filter the catalog by the agent job, theme, item type, status, or geography.
catalog_preview(inputs, entry_id)
Return a labeled preview for one catalog entry with optional symbols, dates, and filters. Required: entry_id.
catalog_request(action, inputs, contact, entry_id, use_case, organization, expected_volume)
Save demand for a catalog entry after a preview, with the user goal and the preview action. Required: entry_id, action, use_case.
datasets_describe(dataset_id)
Return the schema, filters, limits, freshness, and access details for one dataset identifier. Required: dataset_id.
datasets_list
List available datasets with access, freshness, and coverage details for dataset selection.
datasets_search(query)
Search dataset identifiers, names, and descriptions with a plain-language financial-data query. Required: query.
feedback_submit(request, category, use_case)
Save a product request for a missing tool, dataset, or feature. Examples include backtesting and options pricing. This request helps improve coverage. Required: category, request.
macro_calendar(limit, impact, country, end_day, start_day)
Return economic events in chronological order for a date range, with optional country and impact filters. Required: start_day, end_day.
macro_current_conditions
Return generated themes for current United States macroeconomic conditions. The result includes its time and method version.
macro_indicator(name, limit, end_day, start_day)
Return observations for one economic indicator, with optional dates for the observation period. Required: name.
market_analyst_ratings(limit, symbol)
Return the analyst rating consensus and recent rating changes for one ticker. The results are third-party opinions. Required: symbol.
market_company_profile(symbol)
Return the company name, industry, exchange, market value, and basic profile fields for one ticker. Required: symbol.
market_earnings(limit, symbol, end_day, start_day)
Return reported or scheduled earnings events in a date range, with an optional ticker filter.
market_etf_holdings(limit, symbol, min_weight_percent)
Return the largest reported holdings for one ETF, with an optional minimum weight filter. Required: symbol.
market_fundamentals(limit, period, symbol)
Return reported financial statements, ratios, and metrics for one company by quarterly or annual period. Required: symbol.
market_price_history(limit, order, cursor, symbol, end_day, start_day)
Return daily prices and volume for one ticker by date range or latest trading-session count. Required: symbol.
market_quote(symbol)
Return the latest available end-of-day price and volume for one ticker. This tool does not return a real-time quote. Required: symbol.
market_symbol_search(limit, query)
Find ticker symbols by company name or ticker text for security identification. Required: query.
news_article(story_id)
Return one processed news summary by story identifier. The tool does not return full article text or external links. Required: story_id.
news_general(hours, limit, cursor)
Return recent cross-market news summaries with cursor pagination.
news_impacts(hours, limit, cursor, symbols)
Return generated direction, importance, and confidence scores for recent news about selected tickers. These scores do not establish causality. Required: symbols.
news_stock(hours, limit, cursor, symbol)
Return recent news summaries for one ticker. The tool returns summaries and does not return full article text. Required: symbol.
ping
Return the Unquant MCP server status for an availability check.
politics_us_congress_aggregate(days, limit, cursor, symbols)
Return ticker-level totals from reported United States congressional transactions. The totals do not show current holdings or intent.
politics_us_congress_trades(days, limit, cursor, end_day, symbols, start_day, asset_owner, member_names)
Return reported United States congressional transactions. Filter by ticker, member, asset owner, or transaction dates.

Last successful function declaration observed on . Source: https://unquant.ai/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on . Source: https://unquant.ai/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
Latest published version 3.0.0 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-08-04 When the registry record was last updated by its maintainer. point in time Model Context Protocol
First listed in the MCP Registry 2026-08-04 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
mcp tools declared 28 tools Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. as of probe unquant.ai
mcp endpoint status ok The server listed 28 functions when asked. as of probe unquant.ai

Where to get it

This record as data

Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.

GET /api/v1/entries/mcp_server.json

Sources

  1. Official MCP Registry — Model Context Protocol, observed , trust tier 1.
  2. Tools declared by the MCP server at https://unquant.ai/mcp — unquant.ai, observed , trust tier 1.