Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@tradefloor-structure What is ETH doing structurally on the 1h?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Smart-money market structure as an MCP server. Ask your AI assistant what the structure of a market is, and get a real answer: trend, character shifts, liquidity sweeps, fair value gaps, order blocks and pullback zones.
This is the same engine that runs in production at TradeFloor, extracted from the production monorepo rather than reimplemented for show.
> What is ETH doing structurally on the 1h?
SHORT structure over 1000 candles: 4 character shift(s), 11 continuation
break(s), 2 break(s) since the last shift. Price is inside: discount, ote,
golden_retriever.The package makes no request to TradeFloor, ever. There is no key, no
account, no telemetry, no usage ping. Read candles.py: the only outbound call
in the whole package is to Hyperliquid's public endpoint, it happens only when
you ask for a coin by name, and it leaves from your own machine and your own IP.
Analysing the bundled sample or your own candles touches the network zero times.
The package has exactly one dependency, the MCP SDK itself. The one HTTP call it can make uses the standard library, so there is no HTTP client in your install to audit or to trust.
Related MCP server: Coinversaa Pulse
claude mcp add tradefloor-structure -- uvx tradefloor-mcpOr by hand, in any MCP client:
{
"mcpServers": {
"tradefloor-structure": {
"command": "uvx",
"args": ["tradefloor-mcp"]
}
}
}Nothing else to configure. It works immediately.
Each takes candles the same way: name a coin, or pass your own candles, or
pass neither and get a worked example on the bundled ETH-15m data.
analyze_structureTrend, plus every structural break with its time and price. Character shifts (ChoCh, called MSS internally) are separated from continuation breaks (BOS), and you get the last validated swing high and low, the potential levels a pullback is forming against, and the impulse peak of the current leg.
find_liquidity_sweepsStop-hunts. A sweep is a break whose candle first ran the liquidity resting past one or more prior swing levels before closing back inside. Each result names the sweeping candle and every level it took out, which is what tells an engineered break apart from a clean one.
find_blocksFair value gaps and order blocks on the current impulse leg, then again per Fibonacci pullback zone (discount, equilibrium, premium, golden pocket), plus which zones price is sitting in right now.
Every answer carries definitions for the terms it actually used. A model reading
golden_retriever would otherwise guess, and that one it would guess wrong: it
is this engine's name for the golden pocket. Standard terms travel too, so what
reaches the person is the real meaning rather than a plausible one.
Ask for a chart and you get one. Pass include_candles: true and the response
carries the candles themselves, on the same time scale as the levels and blocks,
so your assistant can draw the structure it just described.
> show me ETH 4h structure and draw itAny venue, any source. Compact or verbose keys both work:
[{"t": 1778300100000, "o": "2320.9", "h": "2321.2", "l": "2315.9", "c": "2316.7"}]
[{"time": 1778300100000, "open": 2320.9, "high": 2321.2, "low": 2315.9, "close": 2316.7}]Candles are validated on the way in. A malformed high raises instead of being read as zero, because a zero high is not a degenerate answer, it is a wrong one.
Windows are capped at 20,000 candles. Structure does not get better past that, and an unbounded window means an unbounded reply into your context.
Symbols are checked before anything leaves your machine: perps are bare (BTC), tokenised equities are prefixed (xyz:AAPL), and anything else is refused here rather than sent to the venue to be refused there.
The bundled sample is the exact fixture TradeFloor's own test suite pins its market structure against: 6000 ETH-15m candles, which the engine resolves to 50 structural events and 23 liquidity sweeps (11 bullish, 12 bearish). Those numbers are asserted both in this repository and upstream, so if they ever diverge, one of the two is broken and CI says so.
uv run pytestNot here, and deliberately so. This package analyses; it never places an order, holds a key, or gives advice. There is no code path in it that reaches money.
TradeFloor runs a separate, account-scoped MCP server for that. It authorises through your browser, where you pick which wallet an agent may touch and what its spending ceilings are, and every write goes through server-side risk limits. An agent there cannot loosen a stop, and cannot open a position without one.
It is invitation-gated while it settles. If you want in: tradefloor.co.
src/tradefloor_mcp/engine/That directory is generated. It is extracted verbatim from the TradeFloor monorepo, where the same code is a money path, and a CI gate on both sides keeps the two byte-identical. Pull requests against it cannot be merged.
Everything else here is authored in this repository and contributions are welcome: the server, the tools, the docs, the examples.
Best-effort on response times, and honest about it: this is maintained alongside a product, so an issue may sit for a while.
The tool contracts are a different matter. They follow semantic versioning strictly, so you can build on them: a breaking change to the three tools only ever ships in a major version.
Apache 2.0.
Market structure analysis is not investment advice, and past structure does not predict future price. Trading leveraged instruments can lose you more than you put in.
Read market structure: trend, character shifts (ChoCh) and continuation breaks (BOS).
Returns the current trend, every structural break in the window with its time and price, the last validated swing high and low, the potential swing levels a pullback is forming against, and the impulse peak or trough of the current leg.
Give a coin (BTC, ETH, SOL; tokenised equities as xyz:AAPL) to fetch candles from Hyperliquid's public endpoint, or pass your own candles, or neither to see a worked example on bundled ETH-15m data.
Set include_candles=true when you intend to DRAW the result: the response then carries the candles themselves, on the same time scale as the levels.
| Name | Required | Description | Default |
|---|---|---|---|
| coin | No | ||
| limit | No | ||
| candles | No | ||
| interval | No | 1h | |
| include_candles | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden, and it does well: it states the read-only nature, the Hyperliquid public endpoint source, the fallback example behavior, and the effect of include_candles. It does not cover edge cases like conflicting coin and candles inputs, but the core behavior is clearly disclosed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well structured: a one-line summary, a list of return contents, input-mode instructions, and a targeted note about drawing. Every sentence carries useful information, and the most important behavioral details are front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 5-parameter tool with no annotations, the description covers return values, data sources, input modes, and the include_candles use case, while the output schema handles return structure. It is slightly incomplete regarding sibling-tool routing and ambiguity when both coin and candles are supplied, but overall an agent can invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It explains coin formats and their effect, the candles alternative, the neither/default example, and include_candles semantics. Limit and interval are not explicitly described, but the default values are in the schema and the example hints at interval formatting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource: 'Read market structure' and immediately names the core outputs: trend, ChoCh, and BOS. This makes the tool's function unmistakable and semantically distinguishes it from siblings focused on liquidity sweeps and blocks.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear conditional guidance for input modes: supply a coin, supply your own candles, or supply neither for an example. It also explains when to set include_candles=true. However, it never mentions when to choose this tool over find_liquidity_sweeps or find_blocks, so alternative-tool selection is left implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find fair value gaps, order blocks and the pullback zones holding them.
Reports blocks on the current impulse leg, then again per Fibonacci pullback zone (discount, equilibrium, premium, golden pocket), and says which zones price is sitting in right now.
Same input options as analyze_structure.
| Name | Required | Description | Default |
|---|---|---|---|
| coin | No | ||
| limit | No | ||
| candles | No | ||
| interval | No | 1h | |
| include_candles | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the disclosure burden. It explains the analysis sequence (current impulse leg, then per Fibonacci zone) and that the tool reports the zone price is currently in. This makes the read-only, analytical behavior concrete, even though it does not explicitly state side-effect status or data dependencies.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences with the core purpose front-loaded, followed by useful behavioral detail and a cross-reference. No filler. The cross-reference is terse but earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The output schema presumably covers return values, and the behavior is well described. However, with 5 optional parameters, no annotations, and no selection guidance versus siblings, the description leaves the agent to infer input constraints and when this tool is the right choice.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description provides no explanation of coin, limit, candles, interval, or include_candles. The only parameter-related hint is 'Same input options as analyze_structure,' which defers to another tool rather than clarifying defaults, constraints, or formats.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names specific objects (fair value gaps, order blocks, pullback zones) and a concrete reporting behavior (impulse leg, Fibonacci zones, current price zone). It does not explicitly contrast itself with analyze_structure or find_liquidity_sweeps, but the resource and scope are clear enough for an agent to tell it apart.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when block locations within Fibonacci zones are needed, but it does not state when to prefer this tool over its siblings or when not to use it. The note 'Same input options as analyze_structure' addresses input compatibility, not selection criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find stop-hunts: breaks that first ran the liquidity resting past a level.
A sweep is a structural break whose candle pushed through one or more prior swing levels before closing back inside. Each result names the sweeping candle and every level it took out, which is what separates an engineered break from a clean one.
Same input options as analyze_structure.
| Name | Required | Description | Default |
|---|---|---|---|
| coin | No | ||
| limit | No | ||
| candles | No | ||
| interval | No | 1h | |
| include_candles | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and does a solid job: it explains the exact behavioral condition for a sweep and what the result contains (the sweeping candle and every level it took out). It does not explicitly state that the tool is read-only or has no side effects, but the analytical nature and result-focused wording make the behavior reasonably transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and front-loaded with the core concept, followed by a clear definition and result behavior. It avoids unnecessary filler, though the first sentence's phrasing is slightly awkward. Overall, every sentence earns its place and the structure is easy for an agent to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The output schema exists, so return values do not need to be fully explained, and the description gives the key concept and result contents. However, because there are no annotations, no explicit usage exclusions, and no real parameter semantics, the description leaves meaningful gaps for a 5-parameter tool with two siblings.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% and there are 5 parameters, so the description needed to compensate. Instead it only says 'Same input options as analyze_structure,' which points elsewhere rather than explaining coin, limit, candles, interval, or include_candles. This is minimal added semantic value over the raw schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the action ('Find stop-hunts') and defines the resource precisely: a sweep is a structural break that pushes through prior swing levels and closes back inside. It also distinguishes the tool's result by stating each result names the sweeping candle and every level taken out, which makes it distinct from generic structure analysis.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use the tool (when you need to identify liquidity sweeps/stop-hunts) and references 'Same input options as analyze_structure,' but it does not explicitly state when to prefer this over find_blocks or analyze_structure. There are no exclusions or alternative routing conditions, so the usage guidance is mostly implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0analyze_structurefind_blocksfind_liquidity_sweepsScored across 3 tools
Each tool targets a distinct analysis type: general market structure, liquidity sweeps, and block/fair-value zones. Shared concepts like breaks and swings are presented as different outputs, so an agent can select based on the specific question without confusion.
All tool names follow a clear snake_case verb_noun pattern: analyze_structure, find_liquidity_sweeps, find_blocks. The verbs are semantically appropriate and the pattern is consistent across the entire set.
Three tools is compact but appropriate for a specialized market-structure analysis server. Each tool covers a distinct core concept and they share a consistent input contract, so nothing feels redundant or thin.
The surface covers the main structure-analysis workflows: trend/breaks/swings, stop-hunts, and blocks/zones. A minor gap is the lack of an explicit current-liquidity-pools tool, but agents can work around this using sweeps and structure outputs.
LuxAlgo Library — the encyclopedia of trading & technical analysis for AI agents. Free, keyless.
Blockchain analytics API for AI agents. Smart Money signals, wallet profiling, token analytics.
Blockchain analytics API for AI agents. Smart Money signals, wallet profiling, token analytics.
Crypto market signals, technical indicators, and sentiment analysis for AI agents.
