Analytics
zdte.ai
Provides educational analytics on dealer positioning and institutional flow for trading decisions.
ENDPOINT 1
https://api.zdte.ai/mcp
MCP server metadata
- Name
- zdte-agent
- Version
- 1.0.0
Start with get_access_options for prices and accountless onboarding. list_history_dates is free metadata; historical datasets require credits. create_guest_key returns a key once: save it securely, configure the HTTP Bearer header, and reconnect. Then use get_credit_balance and create_credit_checkout. Checkout creates a link; payment requires payer authorization and verified confirmation. zdte.ai provides computed SPX market-structure DATA (dealer positioning, walls, gamma flip, GEX, implied-range bands) for the caller's own decision-making. Nothing on this surface is investment advice or a trade recommendation; no directional signals are provided. Realtime requires a funded X-API-Key (create one at https://zdte.ai/agent/credits); without a key, get_field_guide is free and get_regime / get_market_structure serve a delayed headline preview. Accountless prepaid access and payment capabilities are published at https://api.zdte.ai/api/agent/pricing. Check availability before creating a key. Market structure is recomputed approximately every 10 seconds during US market hours (typical data age under 15 seconds); polling faster than 10s returns unchanged data. Call get_field_guide once per session for field units, value sets, and semantics.
Known tools 13
get_market_structureCurrent computed SPX dealer market structure (walls, gamma flip, net GEX, regime), recomputed ~every 10s during market hours: scored pressure-point strike ladder, implied 50%/80% forecast-band ranges, strike activity (volume/OI), and VIX term-structure context.
Inferred read-onlylist_history_datesFree catalog of available historical SPX market-structure replay dates.
Inferred read-onlyget_dayPer-day SPX market-structure timeline + summary for one replay date (YYYY-MM-DD).
Inferred read-onlyget_regime_segmentsCompressed dealer-regime segment tape for one replay date (YYYY-MM-DD).
Inferred read-onlysubscribe_eventSubscribe a callback URL to a market-structure event (zero_gamma_flip | new_wall | regime_transition).
Inferred read-onlyget_field_guideStatic, versioned dictionary of every field this surface emits: unit, value set where the producer has one, and a one-sentence meaning, plus the shared response conventions (tier, delay, timestamps, and how missing data is reported).
Inferred read-onlyget_credit_balanceFree balance check for the API key in this connection's HTTP header.
Inferred read-onlycreate_credit_checkoutCreate a Stripe Checkout link for the authenticated key.
Potential side effectsCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.zdte-agent]
url = "https://api.zdte.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"zdte-agent": {
"type": "http",
"url": "https://api.zdte.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: zdte-agent
Remote MCP URL: https://api.zdte.ai/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"zdte-agent": {
"url": "https://api.zdte.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"zdte-agent": {
"type": "http",
"url": "https://api.zdte.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "zdte-agent",
"transport": "streamable-http",
"url": "https://api.zdte.ai/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for zdte.ai was fetched 2026-08-28T23:17:33.243Z and is being refreshed.
zdte.ai is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.