Polymarket and Predict.fun historical tick data, plus backtest quotes and status, over MCP
Strasmore market data is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
US stocks and options data via SQL: bars, ticks, greeks, fundamentals, filings. No key.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http strasmore-market-data-mcp https://ai.strasmore.com/mcp
# 2 — ask your agent for something these tools do
# list_tables, describe_table, get_price_bars and 6 more
Strasmore market data costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
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 and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http strasmore-market-data-mcp https://ai.strasmore.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
9 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.
List every table in the Strasmore US market-data warehouse (equities, options, corporate actions, fundamentals, SEC filings, news, macro) with a one-line description, the column its history window filters on, and whether this no-key access can read it. Call this first.
No parameter schema on file.
Columns of one table with their ClickHouse types, plus notes on columns whose meaning is not obvious from the name and known data caveats. Call before writing SQL against a table.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| table | string | yes | Table name, e.g. stocks_daily_aggs |
OHLCV bars for one US stock or ETF over a date range, at 1min, 5min, 1h or 1d. Aggregated server-side to a coarser interval when the range would exceed the 500-row limit, and the result says when it did, so a long range comes back complete instead of truncated. No-key access reads from 2025-01-01; all times are UTC. Example: {"ticker": "AAPL", "start": "2026-09-28", "end": "2026-10-02", "interval"
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ticker | string | yes | One symbol, e.g. AAPL or BRK.B. |
| start | string | yes | YYYY-MM-DD, or YYYY-MM-DD HH:MM (UTC) for an intraday window. |
| end | string | yes | YYYY-MM-DD (the whole day is included), or YYYY-MM-DD HH:MM (UTC). |
| interval | string | no | Bar size. 1d comes from the daily table and carries vwap. |
Exchange-reported short interest for one ticker (shares short, average daily volume, days to cover — published twice a month) together with daily FINRA short volume, labelled in the series column. No-key access reads from 2025-01-01. start and end are optional and default to the last 365 days. Example: {"ticker": "GME"}. Docs: https://ai.strasmore.com/llms.txt?utm_source=mcp&utm_campaign=pm21
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ticker | string | yes | One symbol, e.g. GME. |
| start | string | no | YYYY-MM-DD. Optional. |
| end | string | no | YYYY-MM-DD. Optional. |
Declared dividends (ex-date, record date, pay date, cash amount, frequency) and stock splits for one ticker, labelled in the event column. No-key access reads from 2025-01-01. start and end are optional and default to the last 365 days plus the next 365, so an already-declared future ex-date is included. Example: {"ticker": "KO"}. Docs: https://ai.strasmore.com/llms.txt?utm_source=mcp&utm_campai
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ticker | string | yes | One symbol, e.g. KO. |
| start | string | no | YYYY-MM-DD. Optional. |
| end | string | no | YYYY-MM-DD. Optional. |
US exchange holidays and early closes in a date range, per exchange. This is an UPCOMING-sessions table, not a historical calendar and not a list of normal sessions: an empty result means none are recorded for that range, not that every day was a full session. Example: {"start": "2026-11-01", "end": "2027-01-31"}. Docs: https://ai.strasmore.com/llms.txt?utm_source=mcp&utm_campaign=pm21
| Parameter | Type | Required | Notes |
|---|---|---|---|
| start | string | yes | YYYY-MM-DD. |
| end | string | yes | YYYY-MM-DD. |
SEC Form 4 insider transactions for one ticker — who, their role, the transaction code, shares, price and the filing link. Back to 2003 on every tier (this table is not history-windowed), at most 500 rows per call. start and end are optional and default to the last 365 days. Example: {"ticker": "NVDA", "start": "2026-01-01"}. Docs: https://ai.strasmore.com/llms.txt?utm_source=mcp&utm_campaign=pm21
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ticker | string | yes | One symbol, e.g. NVDA. |
| start | string | no | YYYY-MM-DD. Optional. |
| end | string | no | YYYY-MM-DD. Optional. |
Run one read-only ClickHouse SELECT against the global_markets database and get the rows back. No key needed. Limits on this access: 500 rows and 20 seconds per query, history from 2025-01-01, and some tick-level tables excluded — each result states which limit, if any, it ran into. Connected with an API key, it runs at that key's plan instead. Docs: https://ai.strasmore.com/llms.txt (tables and l
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sql | string | yes | A single SELECT statement. |
What this no-key access includes, what a free account and each paid plan add (history depth, datasets, row limits, price), and the link to start each one.
No parameter schema on file.
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Strasmore market data or to call it, 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 an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Strasmore market data can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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 a signed-in account that does not publish it, and nothing else.