MCP server that gives coding agents typed 0xArchive market data tools across Hyperliquid (perps, HIP-3, HIP-4, spot) and Lighter.xyz
Run a query through MarketIntell's brain (auto-routes to T1 fast agent or T2 CoT pipeline based on intent). Returns synthesized analysis with citations and trade setup when relevant.
ArgumentsA call is made on an account: it counts against an allowance and the publisher sees it, which is why this one asks who you are first.
What it does
AI analyst desk for stocks, options & crypto with sourced trade setups and a public accuracy record.
Quickstart
# 1 — install (mcprush login holds a key from your dashboard)
npx mcprush@latest add marketintell-mcp
# 2 — ask your agent something
> AI analyst desk for stocks, options & crypto with sourced trade setups and a public accuracy record.
Marketintell is free: there is no plan to choose, no cap to set and nothing that can bill you.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine — this server runs on the publisher’s own infrastructure behind our gateway, and what you install is the connection to it.
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add --transport http marketintell-mcp https://api.marketintell.ai/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing at the gateway. The server itself runs on the publisher’s own infrastructure, so nothing from this listing executes on your machine.
17 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Run a query through MarketIntell's brain (auto-routes to T1 fast agent or T2 CoT pipeline based on intent). Returns synthesized analysis with citations and trade setup when relevant.
Takes no parameters.
Run a query through MarketIntell's T3 supervisor — parallel specialists across technical/derivatives/macro/social/onchain/etc. plus synthesis. Slower (~25-40s) and costlier than `chat`. Pro tier only.
Takes no parameters.
Fetch recent alpha signals — automated market intelligence. Crypto signals every ~10 min; equities (Beta) every ~30 min during US market hours. Filter by domain to narrow.
Takes no parameters.
Realized signal accuracy — rolling 30-day win rate over CLOSED trade signals, where a win is a real take-profit / in-profit expiry (net positive after fees & leverage) and a loss is a real stop-loss / losing expiry. Win-rate is over resolved signals only; flat (break-even) and cancelled/no-fill/ambiguous signals are reported but excluded from the rate. Broken down by timeframe and direction.
Takes no parameters.
Token screening — find trending tokens, top gainers, and top losers. Use this to discover what's moving in the market right now.
Takes no parameters.
List all portfolios owned by the authenticated key. Returns id, name, holdings, timestamps.
Takes no parameters.
Create a new portfolio for the authenticated key. Holdings are token symbol + amount (+ optional entry_price and notes).
Takes no parameters.
Compute PnL + risk assessment for a portfolio you own. Returns per-holding pnl, risk_assessment, and top_risks.
Takes no parameters.
List the authenticated key's recent chat sessions. Useful to resume prior conversations.
Takes no parameters.
Return the authenticated key's plan, daily quota usage, monthly LLM-cost-cents, and cap. Mirrors GET /v1/billing/status.
Takes no parameters.
MarketIntell system health — uptime, cache stats, memory, provider circuit-breaker states.
Takes no parameters.
Step 1 of MCP self-signup. Returns a proof-of-work challenge. Solve locally (find a nonce whose sha256 has the required leading zero hex chars), then call `register` with { challenge_id, nonce, name }.
Takes no parameters.
Step 2 of MCP self-signup. Submit the challenge id + solved nonce to provision a fresh Free-tier API key. The key is shown ONCE — store it. Pro upgrades go through Stripe checkout; this tool only issues Free keys.
Takes no parameters.
Propose a trade intent to the user's connected broker. Writes a pending row the user reviews + approves. Requires `trade` scope. Use this when an agent wants to act on a signal without placing the order itself.
Takes no parameters.
Approve a pending trade intent and place the order at the broker. Returns the executed_order audit row. Requires `trade` scope.
Takes no parameters.
List the caller's recent trade intents (pending, executed, rejected). Requires `trade` scope.
Takes no parameters.
Read the caller's connected broker account snapshot — equity, cash, buying power, open positions. Requires `trade` scope.
Takes no parameters.
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Marketintell costs nothing to install and nothing to call, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is a hosted endpoint: the publisher runs it and we connect to it. The scanner reads packages and source, and neither exists to read here, so there is no grade — not a withheld one, an unmeasured one. What can be checked instead is on Installation: what it asks to reach and what it writes.
Release history
Pinned to 0.1.0 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
No release note was published with this version.
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Writing one takes an account with at least 50 real tool calls against Marketintell in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.