DEHY — SEC & Market Intelligence

Real time SEC and market intelligence, structured at the source.

Community: Submitted by a user or imported; check the owner before granting accessOnlineAPI key requiredGlobalFreeRead-only

What it can do

  • Recent Insider Filings: Most recent open-market insider trades (Form 4 P/S) across all issuers, newest first, with ticker, buy/sell, dollar value, role, and DEHY conviction score (0–100). Use for "wha
  • Top Conviction Trades: Highest DEHY-scored insider trades in the last 14 days (ranked by conviction score, not recency). Use for "best insider signals" or "highest-conviction buys".
  • Cluster Buys: Issuers where 2+ distinct insiders bought on the open market in the last 21 days — the cluster-buying signal (multiple insiders buying the same name). Returns ticker, number of buyers, t

What data it sees

Do you need an account

An API key from the service settings is required

Real time SEC and market intelligence, structured at the source.

DEHY turns SEC filings and macro data into a live, queryable layer including insider trades, institutional ownership, activist stakes, fundamentals, credit, and positioning. It is structured within approximately 60 seconds of filing and scored. Ask it directly from your agent.

Tools include:

• top conviction trades, recent insider filings, cluster buys — scored insider Form 4 activity • institutional top positions, net insider flow — 13F holdings and quarter over quarter flow • activist filings, csuite changes, congress trades — 13D and 13G filings, executive changes, congressional trades • company snapshot, company financials — price, conviction index, 10 year fundamentals • credit health, credit regime — issuer debt service score, maturity walls, spread and curve regime • cross asset positioning, central bank stance, positioning brief — CFTC CoT, central bank data, macro positioning

Grounded in live data, never invents a number. Mint an API key at dehy.io/settings.

How to connect

How to connect DEHY — SEC & Market Intelligence to Claude

The server address to paste into Claude settings:

https://dehy--dehyinbox.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect DEHY — SEC & Market Intelligence to ChatGPT

The server address to paste into ChatGPT settings:

https://dehy--dehyinbox.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect DEHY — SEC & Market Intelligence to Cursor

The server address to paste into Cursor settings:

https://dehy--dehyinbox.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (15)

Raw names from tools/list. Only developers need these.

recent_insider_filingsMost recent open-market insider trades (Form 4 P/S) across all issuers, newest first, with ticker, buy/sell, dollar value, role, and DEHY conviction score (0–100). Use for "what are insiders doing right now".
top_conviction_tradesHighest DEHY-scored insider trades in the last 14 days (ranked by conviction score, not recency). Use for "best insider signals" or "highest-conviction buys".
cluster_buysIssuers where 2+ distinct insiders bought on the open market in the last 21 days — the cluster-buying signal (multiple insiders buying the same name). Returns ticker, number of buyers, total dollars.
institutional_top_positionsMarquee hedge funds' single largest disclosed U.S. equity position from their latest 13F (Berkshire, Pershing Square, Tiger Global, Coatue, ARK). Returns firm, holding, value.
activist_filingsRecent Schedule 13D / 13G activist & 5%-owner stakes, newest first — filer, subject company, ownership %.
csuite_changesRecent C-suite / executive changes from 8-K Item 5.02 — ticker, role, change type (appointment, departure, etc.).
congress_tradesRecent U.S. Congress member stock trades — representative, ticker, buy/sell, amount range.
net_insider_flowDaily net insider dollar flow (open-market buys minus sells) over a window of days. Use for "are insiders net buying or selling lately".
company_snapshotSnapshot for one company by ticker: latest price + change, DEHY conviction index, market cap, revenue (TTM), net margin.
company_financialsMulti-year annual financial statements for one company by ticker — revenue, gross/operating/net income, EPS, balance sheet, cash flow, derived margins & FCF. Use for fundamentals questions.
cross_asset_positioningCFTC Commitments-of-Traders positioning across FX, commodities, rates, and the S&P. Per market: COT Index (0–100 over a 3y window; ≥80 = the crowd is crowded long, ≤20 = crowded short), the commercial (hedger / smart-money) COT Index, 4-week COT-Index change, and a specs-vs-commercials divergence flag. Optional asset-class filter. Use for "what positioning is stretched / crowded / diverging" in FX, commodities, or rates. A crowding/triage read, not a forecast.
central_bank_stanceLatest monetary-policy statement per central bank (Fed, ECB, BoE): the rate decision (hike/cut/hold), the policy rate, a labelled hawkish/dovish language lean (a heuristic, NOT a forecast), and the date. Use for 'what did the Fed/ECB just do' or 'did any central bank shift'.
positioning_briefThe cross-asset Positioning & Policy desk brief: what's crowded (positioning extremes), what's diverging (specs vs commercials), the biggest 4-week positioning swings, and recent central-bank policy. Use for 'give me the macro/positioning read' or 'what should a currencies/commodities desk watch right now'. Crowding context, never a buy/sell call.
credit_healthAn issuer's credit profile by ticker: the DEHY Credit Health score (0–100, higher = healthier; a triage read on debt-service capacity anchored to rating-agency thresholds, NOT a credit rating), its sub-scores (cash-flow-to-debt, leverage, liquidity, profitability, trend) and raw metrics, event flags (negative equity, bankruptcy/acceleration/delisting from 8-Ks, recent insider buying), the debt MATURITY WALL by calendar year (the refi-cliff view), and recent fixed-coupon debt issuance. Use for 'how healthy is X's credit', 'who has a refinancing cliff', 'has X issued debt recently'.
credit_regimeThe credit-regime read: ICE BofA credit-spread OAS by rating (AAA → CCC) with the weekly change and percentile within history, the Treasury yield curve (2/5/10/30Y), and the 10y-2y slope with an inversion flag. Use for "where are credit spreads / are they tight or wide", "is the curve inverted", "what is the credit/rates backdrop". Levels and ranges, not a forecast.