# TheStrat for agents (remote · mcp.thestrat.ai)

Quant price analysis for agents: TheStrat price action, multi-timeframe signals, simultaneous breaks

- Trust score: 68/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `mcp.thestrat.ai`: 68/100 (this document), [markdown](https://verifymcp.io/servers/ai-thestrat-thestrat/mcp.md), [page](https://verifymcp.io/servers/ai-thestrat-thestrat/mcp)

## Channel facts

- Endpoint: `https://mcp.thestrat.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.3.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 16 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 72/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 4742 tokens (~263/item across 18 items; 16 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the TheStrat for agents MCP server?

TheStrat for agents is a hosted endpoint at https://mcp.thestrat.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ai-thestrat-thestrat 'https://mcp.thestrat.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-thestrat-thestrat": {
      "url": "https://mcp.thestrat.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-thestrat-thestrat": {
      "type": "http",
      "url": "https://mcp.thestrat.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-thestrat-thestrat]
url = "https://mcp.thestrat.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-thestrat-thestrat": {
      "type": "remote",
      "url": "https://mcp.thestrat.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-thestrat-thestrat --url 'https://mcp.thestrat.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-thestrat-thestrat:
    url: "https://mcp.thestrat.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-thestrat-thestrat": {
      "Transport": "http",
      "Url": "https://mcp.thestrat.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-thestrat-thestrat -t streamable-http -u 'https://mcp.thestrat.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-thestrat-thestrat": {
      "type": "http",
      "url": "https://mcp.thestrat.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-03 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 65, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “describe_price” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 3914 → 4742
- [functional] New prompt “protect_portfolio”
- [functional] New resource “protect-portfolio”
- [functional] Server version: 0.2.0 → 0.3.1
- [functional] New tool “portfolio_check”

### 2026-10-27 (score 64, +3)

- [functional improvement] Stability: unverified → 0.03
- [functional] First check of Schema quality: 100
- [functional] New prompt “how_thestrat_thinks”
- [functional] New resource “how-we-think”

### 2026-10-26 (score 61)

First indexed and scored.

## MCP tools (16)

### `classify_bars` (~252 tokens)

Label every bar as TheStrat scenario 1, 2u, 2d or 3 (Truth #1).

    Rule: compare each bar with the bar before it. Took the prior high only = 2u. Took the
    prior low only = 2d. Took both = 3. Took neither = 1 (inside bar). Equal to the prior
    high/low is NOT a take-out (still a 1). The first bar has no scenario (null).
    Also returns color, hammer/shooter shape, failed-2 flags (2u red / 2d green = potential 3)
    and 3u/3d when the bar has first_side data. Use this instead of reading a chart.

Input parameters:

- `bars` (array, required): OHLC bars, oldest first. Each bar is an object {t, o, h, l, c, v?} (also accepts open/high/low/close/time) or a row [t, o, h, l, c, v?]. t = bar START time, ISO 8601 (New York time if no offset). Dai…

### `timeframe_continuity` (~238 tokens)

Full timeframe continuity (FTFC, Truth #2): is the last sale above (up) or below (down)
    the open of every timeframe in the group, or mixed (conflict)?

    Returns per-timeframe side, color and aggression (above an open: buyers more aggressive,
    willing to buy at higher prices; below: sellers more aggressive), state up/down/mixed,
    override (day and 60 agree against the week/month) and the profit-taking note (only the
    60 red). FTFC is a state, not a signal.

Input parameters:

- `group` (string): standard = M W D 60 (default), intraday = 60 30 15 5, investing = Y Q M W, all = Y Q M W D 60 30 15 5.
- `opens` (object, required): Open price of the CURRENT bar per timeframe, e.g. {"M": 650.1, "W": 662.0, "D": 665.2, "60": 666.0}.
- `price` (number, required): The last sale.

### `find_signals` (~410 tokens)

Find TheStrat actionable signals on one timeframe.

    Patterns: 2-2 reversal, 1-2-2 rev strat, 3-2-2, 2-1-2, 3-1-2, 3-2, hammer, shooter,
    momo hammer/shooter, inside bar, outside bar reversal (2d-3u / 2u-3d), 1-3 rev strat,
    1-3-2, I-O-I. Each signal has: trigger, target (magnitude, null if the pattern has
    none), level_of_reclaim, invalidation, status, sequence, kind (reversal/continuation)
    and source_url (the docs page for the rule).

    Status: setup (trigger not taken), in_force (taken, target not hit, still active),
    triggered (taken, bar closed, no target), hit_target, failed. Timing: a signal is in
    force only while its bar is open; D fires stay active until the next session open;
    the W is closed from Friday close to Monday open.

Input parameters:

- `bars` (array, required): OHLC bars, oldest first. Each bar is an object {t, o, h, l, c, v?} (also accepts open/high/low/close/time) or a row [t, o, h, l, c, v?]. t = bar START time, ISO 8601 (New York time if no offset). Dai…
- `include_history` (boolean): Also list older setups and what happened to them (evidence of participation).
- `now`: Current time, ISO 8601. Decides if the last bar is still open. Default: the server clock.
- `timeframe` (string): Timeframe of the bars: 5, 15, 30, 60, D, W, M, Q or Y.

### `exhaustion` (~171 tokens)

Exhaustion risk: how much time is left in the signal's bar (session minutes,
    wall-clock minutes, sessions left, fraction left), and until when the fire stays active.

    Docs example: a 60-minute hammer that triggers at 9:32 has 58 minutes; at 10:25 it has 5.
    Once the bar closes, the signal is gone. The tool reports time; it does not grade it.

Input parameters:

- `now`: Current time, ISO 8601. Decides if the last bar is still open. Default: the server clock.
- `signal` (object, required): A signal from find_signals, or {"timeframe": "60", "trigger_bar_t": "2026-10-23T09:30:00-04:00"}.

### `describe_price` (~254 tokens)

Multi-timeframe price analysis in plain language for one symbol (quant price action,
    technical signals, timeframe continuity) from your own bars.

    Returns `text` (one short line per timeframe, e.g. "SPY day: 2u, above the day open
    (green). Last 3 bars: 2d 1 2u. In force: bullish 2-1-2 ...") and the same facts as
    JSON: scenario, color, last 3 bars, signals in force, setups, and FTFC (M W D 60).
    Start here, then quote the text to the user. Hosted server: free, no cooldown.
    Fair-use limit: 60 calls per minute.

Input parameters:

- `bars_by_timeframe` (object, required): Bars per timeframe, e.g. {"M": [...], "W": [...], "D": [...], "60": [...]}. Give at least 3 bars per timeframe; more gives more signals.
- `now`: Current time, ISO 8601. Decides if the last bar is still open. Default: the server clock.
- `symbol` (string, required): Ticker, e.g. SPY.

### `resample_bars` (~219 tokens)

Build higher-timeframe bars from smaller bars (US equities session 09:30-16:00 New York;
    60-minute bars start at 09:30; extended hours are dropped; a partial first period is
    dropped). Each bar gets first_side (which prior side it took first) for 3u/3d.

Input parameters:

- `bars` (array, required): OHLC bars, oldest first. Each bar is an object {t, o, h, l, c, v?} (also accepts open/high/low/close/time) or a row [t, o, h, l, c, v?]. t = bar START time, ISO 8601 (New York time if no offset). Dai…
- `from_timeframe`: Input timeframe: 1, 5, 15, 30, 60 or D.
- `to_timeframe` (string, required): 60, 30, 15, D, W, M, Q or Y.

### `define_term` (~96 tokens)

Define a TheStrat term with a quote from the docs and its source_url (67-term glossary:
    definition, machine_rule where the docs state one, status "needs Alex" where the docs
    conflict). If the term is not in the glossary, returns the best docs_search hits.

Input parameters:

- `term` (string, required): A TheStrat word, e.g. 'FTFC', 'rev strat', 'level of reclaim'.

### `docs_search` (~83 tokens)

Search TheStrat docs (titles and descriptions from https://thestrat.ai/llms.txt,
    cached 24 h). Returns title, URL, section and description. Read the URL for detail.

Input parameters:

- `limit` (integer): Max results.
- `query` (string, required): Words to find, e.g. 'shooter trigger' or 'full timeframe continuity'.

### `sim_breaks` (~436 tokens)

Simultaneous breaks: find which symbols in a basket broke their setup bar in the same
    direction in the same bar (2d-2u, 1-2u, 3-1-2u up / 2u-2d, 1-2d down). Quant price action
    and sector rotation from your own OHLC data, no third-party feed.

    Docs: "A simultaneous break is multiple correlated assets breaking 2 in the same direction
    at the same time." No threshold: the count and the % of the basket, ranked. At 80%+ the
    group gets the label "80%+ concentration: evidence of algorithmic buying (selling) in this
    group". Returns a ranked list per direction with count, % of basket,
    symbols, and per symbol the trigger, target and level of reclaim, plus the as-of time
    and a `text` line to quote.

Input parameters:

- `as_of`: Optional ISO time. Use only bars that start at or before this time (replay a past bar).
- `basket` (object, required): Bars per symbol on ONE timeframe, oldest first: {"XLE": [...], "XOM": [...], ...}. Same bar format as find_signals. Limits: 60 symbols, 500 bars per symbol (10 to 50 are enough). Swing: a sector ETF…
- `now`: Current time, ISO 8601. Decides if the last bar is still open. Default: the server clock.
- `strict_setup_bar` (boolean): True (default): count only the setup bars on the owner list (2d green / 2d hammer for longs, 2u red / 2u shooter for shorts, inside bars both ways). False: any docs reversal setup.
- `timeframe` (string): Timeframe of the bars: 5, 15, 30, 60, D, W, M, Q or Y.

### `sim_setups` (~338 tokens)

Simultaneous setups (before the break): a concentration of setup bars in one direction
    across a basket of symbols. A technical signals screener on your own data, any timeframe.

    Docs: "A concentration of signals in the same sector or index identifies a potential
    simultaneous break: it fires if all of the signals go in force." Returns a ranked list per
    direction: count, % of basket, symbols, each with trigger, target and level of reclaim.

Input parameters:

- `as_of`: Optional ISO time. Use only bars that start at or before this time (replay a past bar).
- `basket` (object, required): Bars per symbol on ONE timeframe, oldest first: {"XLE": [...], "XOM": [...], ...}. Same bar format as find_signals. Limits: 60 symbols, 500 bars per symbol (10 to 50 are enough). Swing: a sector ETF…
- `now`: Current time, ISO 8601. Decides if the last bar is still open. Default: the server clock.
- `strict_setup_bar` (boolean): True (default): count only the setup bars on the owner list (2d green / 2d hammer for longs, 2u red / 2u shooter for shorts, inside bars both ways). False: any docs reversal setup.
- `timeframe` (string): Timeframe of the bars: 5, 15, 30, 60, D, W, M, Q or Y.

### `sector_analysis` (~300 tokens)

Sector rotation by participation: a sector ETF + its holdings on one timeframe.

    Returns the ETF's own state (scenario, color, last 3 bars, signals in force), the most-2s
    split of the holdings (1 / 2u / 2d / 3, 2u red, 2d green), simultaneous breaks and
    simultaneous setups across ETF + holdings with majority flags, and a `text` summary.

Input parameters:

- `as_of`: Optional ISO time. Use only bars that start at or before this time (replay a past bar).
- `basket` (object, required): Bars per symbol on ONE timeframe, oldest first: {"XLE": [...], "XOM": [...], ...}. Same bar format as find_signals. Limits: 60 symbols, 500 bars per symbol (10 to 50 are enough). Swing: a sector ETF…
- `etf` (string, required): The sector ETF ticker, e.g. XLE. Include its bars in the basket.
- `now`: Current time, ISO 8601. Decides if the last bar is still open. Default: the server clock.
- `timeframe` (string): Timeframe of the bars: 5, 15, 30, 60, D, W, M, Q or Y.

### `signals_in_force` (~232 tokens)

Technical signals in force across a basket: every TheStrat actionable signal whose trigger
    is taken while its bar is open, grouped by direction and pattern, with % of basket and the
    trigger, target and level of reclaim per symbol.

Input parameters:

- `as_of`: Optional ISO time. Use only bars that start at or before this time (replay a past bar).
- `basket` (object, required): Bars per symbol on ONE timeframe, oldest first: {"XLE": [...], "XOM": [...], ...}. Same bar format as find_signals. Limits: 60 symbols, 500 bars per symbol (10 to 50 are enough). Swing: a sector ETF…
- `now`: Current time, ISO 8601. Decides if the last bar is still open. Default: the server clock.
- `timeframe` (string): Timeframe of the bars: 5, 15, 30, 60, D, W, M, Q or Y.

### `potential_signals_next_bar` (~239 tokens)

Potential signals for the next bar across a basket: every setup whose trigger the next bar
    (or the open bar) can take, grouped by direction and pattern, with trigger, target and level
    of reclaim per symbol. A price action watchlist for agents.

Input parameters:

- `as_of`: Optional ISO time. Use only bars that start at or before this time (replay a past bar).
- `basket` (object, required): Bars per symbol on ONE timeframe, oldest first: {"XLE": [...], "XOM": [...], ...}. Same bar format as find_signals. Limits: 60 symbols, 500 bars per symbol (10 to 50 are enough). Swing: a sector ETF…
- `now`: Current time, ISO 8601. Decides if the last bar is still open. Default: the server clock.
- `timeframe` (string): Timeframe of the bars: 5, 15, 30, 60, D, W, M, Q or Y.

### `buy_sell_list` (~242 tokens)

Buy list and sell list: reversal signals in force across timeframes (technical signals
    screener on your own data). Buy: hammer, 2d-2u, 3-2u, 1-2u in force. Sell: shooter, 2u-2d,
    3-2d, 1-2d in force. Continuations (2u-2u, 2d-2d) do not count. Per timeframe: symbols,
    count, % of basket, trigger, target and level of reclaim; plus which timeframes each
    symbol is on.

Input parameters:

- `as_of`: Optional ISO time. Use only bars that start at or before this time (replay a past bar).
- `basket_by_timeframe` (object, required): Bars per timeframe, then per symbol: {"M": {"AAPL": [...], ...}, "W": {...}}. Up to 4 timeframes; 60 symbols and 500 bars per symbol each.
- `now`: Current time, ISO 8601. Decides if the last bar is still open. Default: the server clock.

### `open_decisions` (~38 tokens)

Rules the docs do not state exactly, with the default this server uses. Read this before
    you present a borderline result as a rule.

### `portfolio_check` (~725 tokens)

Protect-your-assets check for one portfolio, from your own bars: measurable conditions on the
    losing side of the user's positions, with the evidence. Read the playbook first: MCP resource
    thestrat://playbooks/protect-portfolio (or the prompt protect_portfolio).

    Returns (1) the market condition: "Algorithmic buying identified in VIX while algorithmic selling in
    4 major indexes" (VIX symbol over its M W D 60 opens, SPY QQQ IWM DIA each under all 4), confirmed or
    not at a 60-minute close, plus the VIX futures curve state if given; (2) per position, the opens on
    the holder's losing side (long: under the open = buyers on that timeframe are losing; short: over the
    open = sellers are losing), reversals in force against the position (buy/sell list rule) and setups
    against it (trigger not taken), with trigger, target and level of reclaim; (3) concentration: the %
    of the user's basket (and of each ETF basket) whose current bar took the prior bar's low or high,
    labelled at 80%+. Each part has `text` to quote and source URLs. Conditions only: not a buy or sell
    signal. Quote `footer` at the end.

Input parameters:

- `as_of`: Optional ISO time. Use only bars that start at or before this time (replay a past bar).
- `bars_by_timeframe` (object, required): Bars per timeframe, then per symbol: {"M": {"NVDA": [...], "VIXY": [...], "SPY": [...]}, "W": {...}, "D": {...}, "60": {...}}. Each position on the user's timeframes (investor Y; position trader Q M;…
- `etf_baskets`: Optional, up to 3: the holdings of an ETF the user owns, {"WGMI": {"IREN": [...], ...}}, on etf_timeframe. For the concentration check.
- `etf_timeframe` (string): Timeframe of the etf_baskets bars: D (default) or W.
- `now`: Current time, ISO 8601. Decides if the last bar is still open. Default: the server clock.
- `position_timeframes`: The user's timeframes for the positions: ["Y"] investor, ["Q", "M"] position trader, ["W", "D", "60"] swing or day trader. Positions are checked only on these. Ask the user.
- `positions` (required): The user's positions: {"NVDA": "long", "TSLA": "short"} or [{"symbol": "NVDA", "side": "long"}]. Up to 25. Sizes are not needed.
- `vix_curve`: Optional VIX futures prices {"front": 18.2, "second": 19.0}. Front over second = backwardation. Leave out if you have no curve data (the reply then says: no data).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-thestrat-thestrat/mcp#diagnostics

## Score history

- 2026-11-05: 68
- 2026-11-04: 68
- 2026-11-03: 68
- 2026-11-02: 67
- 2026-11-01: 67
- 2026-10-31: 66
- 2026-10-30: 66
- 2026-10-29: 65
- 2026-10-28: 65
- 2026-10-27: 64
- 2026-10-26: 61

## Common questions

### What is the TheStrat for agents MCP server?

TheStrat for agents is an MCP server listed in the public MCP registry as ai.thestrat/thestrat. Quant price analysis for agents: TheStrat price action, multi-timeframe signals, simultaneous breaks. This page covers its hosted endpoint (https://mcp.thestrat.ai/mcp).

### Is the TheStrat for agents MCP server safe to use?

TheStrat for agents scores 68 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the TheStrat for agents MCP server expose?

TheStrat for agents exposes 16 tools: classify_bars, timeframe_continuity, find_signals, exhaustion, describe_price, and 11 more. Their descriptions and schemas cost roughly 4,273 tokens of context every time the server is loaded.

### Does the TheStrat for agents MCP server require authentication?

No. We connected to TheStrat for agents without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the TheStrat for agents MCP server still maintained?

TheStrat for agents is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.thestrat.ai/mcp
- Website: https://thestrat.ai/agents/
- Changelog RSS feed: https://verifymcp.io/servers/ai-thestrat-thestrat/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-thestrat-thestrat/mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-thestrat-thestrat/mcp
