QuantGist MCP Server
OfficialAllows creation of Stripe Checkout sessions for plan upgrades, enabling users to upgrade their QuantGist subscription via Stripe.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@QuantGist MCP Servershow me today's high-impact economic events"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
QuantGist MCP Server
Exposes QuantGist macro-economic event data as Model Context Protocol (MCP) tools so Claude and other AI agents can query calendars, check event proximity, and assess trade safety — all within a conversation.
What it does
The server registers 22 tools that any MCP-compatible client (Claude Desktop, Claude Code, custom agents) can call:
Macro economic events
Tool | Description |
| Events scheduled in the next N hours, filtered by impact |
| Events in a date range with optional country/symbol/impact filters |
| Full day macro calendar from |
| Full details for one event by ID (actual, forecast, previous, symbols) |
Earnings
Tool | Description |
| Next upcoming earnings reports across all tickers, with EPS/revenue estimates |
| Earnings history for one ticker (estimate vs actual, beat/miss, EDGAR links) |
| Beat / miss / in-line counts and overall beat rate for a ticker |
| Largest EPS surprises across the market in the latest reports |
| Index-level summary of the current earnings season |
Markets
Tool | Description |
| End-of-day quotes for major indices and instruments (S&P 500, Nasdaq, gold, oil…) |
Discovery & help (read-only, no API key required)
Tool | Description |
| Plans, prices, and feature gates (free → enterprise) + the Bot Usage Add-On |
| Per-plan caps: request quotas, history window, data delay, WS, watchlists, rate limiting |
| Map a natural-language use case to the best REST endpoint + MCP tool |
| Check API reachability and link the public status page |
| Estimate which plan fits a request volume + overage / Bot Usage Add-On notes |
Account (webhooks, API keys, billing)
Tool | Description |
| Current plan, status, and billing period (read-only) |
| Registered webhook endpoints (read-only; Pro plan) |
| Register an HTTPS webhook endpoint — confirm-gated; signing secret shown once |
| Permanently delete a webhook endpoint — confirm-gated, destructive |
| Send a signed synthetic test delivery to verify your consumer |
| Create a (optionally scoped) API key — confirm-gated; key shown once |
| Create a Stripe Checkout session for a plan upgrade — confirm-gated; never charges |
Write tools & consent model
Mutating tools follow an explicit human-in-the-loop pattern:
confirm: truerequired. Called without it, a mutating tool makes no API call and returns a preview of exactly what would happen, so the agent can get the user's approval first.Billing mandate.
create_checkout_sessionnever charges anything — it returns a Stripe-hosted checkout URL that a human must open in a browser and complete. No card data ever passes through the tool or QuantGist's API. The plan upgrades automatically after payment.Once-only secrets. New API keys and webhook signing secrets are returned exactly once, with a warning to store them in an env var or secrets manager — never in committed files.
Server-side enforcement stands. Plan gates (webhooks require Pro) and key scopes are enforced by the QuantGist API itself; the tools surface actionable hints on 403s rather than bypassing anything.
Related MCP server: MCP Financial Data Gateway
Requirements
Python 3.10+ (for the local/stdio install — not needed for the hosted server)
A QuantGist API key — get one at quantgist.com (free tier: 100 calls/day)
Connect to the hosted server (no install)
The MCP server is hosted over HTTP at https://api.quantgist.com/mcp — no install, no
Python. Any client that supports the streamable-HTTP transport can connect by sending your
QuantGist key in an X-API-Key header (multi-tenant: billed to your own quota).
Claude Code, in one command:
claude mcp add --transport http quantgist https://api.quantgist.com/mcp \
--header "X-API-Key: qg_live_YOUR_KEY"Any streamable-HTTP MCP client:
{
"mcpServers": {
"quantgist": {
"type": "streamable-http",
"url": "https://api.quantgist.com/mcp",
"headers": { "X-API-Key": "qg_live_YOUR_KEY" }
}
}
}Connectors that only accept a URL (e.g. ChatGPT): if you can't set a custom header, put the
key in the URL instead — https://api.quantgist.com/mcp?apiKey=qg_live_YOUR_KEY (also accepts
Authorization: Bearer <key>). The header is preferred where possible, since a key in the URL can
be recorded in proxy/server logs.
Prefer to run it yourself? Install locally (below) or self-host the HTTP server — see DEPLOY.md.
Installation
Option A — install from the package (recommended)
pip install quantgist-mcp
# or with uv:
uv pip install quantgist-mcpOption B — install from source (development)
git clone https://github.com/QuantGist-Technologies/QuantGist_MCP
cd QuantGist_MCP
uv sync # installs all dependencies into a venv
uv run quantgist-mcp # start the serverClaude Desktop configuration
Locate your Claude Desktop config file:
Platform | Path |
macOS |
|
Windows |
|
Linux |
|
Add the quantgist server block (see claude_desktop_config_example.json):
{
"mcpServers": {
"quantgist": {
"command": "quantgist-mcp",
"env": {
"QUANTGIST_API_KEY": "qg_live_YOUR_KEY_HERE"
}
}
}
}Restart Claude Desktop after saving. The tools will appear in the tool list.
Using uv run instead of a global install
If you prefer not to install globally, point Claude Desktop at uv run:
{
"mcpServers": {
"quantgist": {
"command": "uv",
"args": ["run", "--directory", "/absolute/path/to/Quangist_MCP", "quantgist-mcp"],
"env": {
"QUANTGIST_API_KEY": "qg_live_YOUR_KEY_HERE"
}
}
}
}Claude Code configuration
Add to .claude/mcp_settings.json in your project (or the global ~/.claude/mcp_settings.json):
{
"mcpServers": {
"quantgist": {
"command": "quantgist-mcp",
"env": {
"QUANTGIST_API_KEY": "qg_live_YOUR_KEY_HERE"
}
}
}
}Self-hosting (HTTP transport)
Besides the stdio transport above, the server can run as a hosted HTTP service via the
quantgist-mcp-http entry point (GET /health, MCP at /mcp). It accepts a per-request
X-API-Key header (multi-tenant) or a server-side QUANTGIST_API_KEY env var.
docker build -t quantgist-mcp .
docker run -p 8000:8000 -e QUANTGIST_API_KEY=qg_live_YOUR_KEY quantgist-mcp
curl http://localhost:8000/healthSee DEPLOY.md for Docker, Docker Compose, and Coolify deployment.
Tool reference
get_upcoming_events
Returns events in the next N hours.
Parameter | Type | Default | Description |
| integer (1–168) | 24 | Look-ahead window in hours |
| high | medium | low | all | high | Impact filter |
get_events_range
Returns events in a date range.
Parameter | Type | Required | Description |
| ISO string | Yes | Start date/datetime |
| ISO string | Yes | End date/datetime |
| string | No | 2-letter country code (e.g. "US") |
| enum | No | high | medium | low | all |
| string | No | Trading symbol (e.g. "XAUUSD") |
get_economic_calendar
Returns the day's macro calendar grouped by release time. This tool calls
GET /v1/calendar?envelope=true, not the broad /events feed, so general
financial-news headlines are not mixed into scheduled macro releases.
The structured output preserves the backend envelope:
events/count/returned_counttotal_countcoveragewarningstruncatedschema_version
If the backend response is partial, stale, truncated by the MCP safety cap, or
missing the required calendar envelope, the tool surfaces that in warnings and
does not fall back to /events.
Parameter | Type | Default | Description |
| ISO date | today (UTC) | Date to fetch |
| enum | high | Impact filter |
get_event_detail
Returns full detail for one event.
Parameter | Type | Required | Description |
| string | Yes | Event ID from any other tool |
get_earnings_upcoming
Returns the next upcoming earnings reports across all tickers, ordered by report date.
Parameter | Type | Default | Description |
| integer (1–100) | 20 | Number of upcoming reports to return |
get_earnings_for_ticker
Returns earnings history for a single ticker (EPS estimate vs actual, revenue, beat/miss, EDGAR links).
Parameter | Type | Default | Description |
| string | required | Stock ticker, e.g. "AAPL" |
| integer (1–50) | 10 | Number of historical reports to return |
get_earnings_summary
Returns beat / miss / in-line counts and overall beat rate for a ticker.
Parameter | Type | Required | Description |
| string | Yes | Stock ticker, e.g. "AAPL" |
get_earnings_surprises
Returns the largest EPS surprises across the market in the most recent reports.
Parameter | Type | Default | Description |
| integer (1–50) | 20 | Number of top surprises to return |
get_earnings_season_summary
Returns the index-level summary of the current earnings season (total reports, overall beat rate, average EPS surprise, season label). No parameters.
get_markets_overview
Returns end-of-day quotes for major market indices and instruments (S&P 500, Nasdaq, Dow Jones, gold, oil, etc.). No parameters.
get_subscription
Returns the authenticated account's plan, status, and billing period. No parameters. Read-only.
list_webhooks
Lists the account's registered webhook endpoints. No parameters. Read-only; webhooks require the Pro plan.
create_webhook
Registers an HTTPS webhook endpoint (Pro plan). Confirm-gated: without confirm: true it returns a preview and makes no API call. The signing secret is returned once only.
Parameter | Type | Default | Description |
| string (required) | — | HTTPS URL that will receive event POSTs |
| string[] |
| Event types: |
| string[] | — | Only deliver events with these impact levels, e.g. |
| boolean |
| Must be |
delete_webhook
Permanently deletes a webhook endpoint and its delivery history. Confirm-gated and destructive.
Parameter | Type | Default | Description |
| string (required) | — | Endpoint ID from |
| boolean |
| Must be |
test_webhook
Sends a signed synthetic test event to a webhook endpoint so you can verify reachability and X-QuantGist-Signature verification.
Parameter | Type | Default | Description |
| string (required) | — | Endpoint ID from |
create_api_key
Creates a new API key, optionally scoped. Confirm-gated. The full key is returned once only — store it securely.
Parameter | Type | Default | Description |
| string |
| Human-readable label |
|
|
| Production data vs sandbox |
| string[] |
| Prefer least privilege: |
| boolean |
| Must be |
create_checkout_session
Creates a Stripe Checkout session for a plan upgrade. Never charges — returns a Stripe-hosted checkout URL a human must open and complete. Confirm-gated.
Parameter | Type | Default | Description |
|
| — | Target plan |
| boolean |
| Must be |
Example prompts
These prompts work out of the box once the server is connected:
"What high-impact events are in the next 4 hours?"
"Show me today's full economic calendar"
"Show me this week's high-impact USD events"
"What macro events affect EURUSD this Friday?"
"Get me details on event ID abc123"
"Which companies report earnings soon?"
"Show me AAPL's earnings beat rate"
"What were the biggest EPS surprises this season?"
"Give me a quick market overview"
"What plan am I on?"
"Set up a webhook to https://my-bot.example.com/hooks for high-impact USD events"
"Create a read-only test API key for my backtester"
"I want to upgrade to Pro" (the agent hands you a Stripe checkout link — payment always stays with you)
Environment variables
Variable | Required | Description |
| Yes | Your QuantGist API key ( |
Development
uv sync
uv run quantgist-mcp # run the MCP server
uv run pytest # run tests (if present)
uv run ruff check src/ # lint
uv run ruff format src/ # formatAPI rate limits
The free tier allows 100 API calls/day with up to 365 days of event history. Each tool invocation makes 1–2 API calls. Upgrade at quantgist.com/pricing for higher limits.
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Real SEC, 13F, insider, congress & macro data your AI agent can cite. Hosted MCP, 24 tools.
Real-time market events, sentiment, and technical analysis as MCP tools, backed by real data.
The financial MCP for AI agents - 90+ financial tables, SEC filings, signals, alt-data.
Macroeconomic and FX time-series data for AI agents: indicators, calendars, COT, forex, commodities.
Related MCP Servers
- AlicenseBqualityCmaintenanceEnables access to ForexFactory economic calendar data through MCP resources and tools. Supports retrieving economic events by time periods for integration with trading assistants and agentic workflows.111MIT
- AlicenseNot gradedqualityDmaintenanceProvides 10 financial data tools (market data, economic indicators, news, insider trades, and calendars) via a single MCP layer, enabling any MCP-compatible LLM to access diverse financial data through a unified interface.MIT
- AlicenseNot gradedqualityCmaintenanceProvides AI agents access to 336 real-time and historical market, quant, SEC filing, insider trading, fundamentals, and macro data tools via MCP Streamable HTTP.MIT
- FlicenseNot gradedqualityCmaintenanceProvides MCP tools that let AI agents retrieve stock price data, validate data quality, analyze chart trends and volatility, and fetch news sentiment, enabling structured financial analysis workflows.-