Skip to main content
Glama
horustechltd

horus-flow-mcp

by horustechltd

get_equity_flow

Monitor real-time institutional order flow for any US stock. Detect buy/sell pressure, block trades, and dumping signals with confidence scores.

Instructions

Get real-time institutional orderflow for a US equity stock.

Returns signal (BUY_PRESSURE/SELL_PRESSURE/WHALE_EXIT/EMERGENCY_DUMP),
confidence score, large sell orders count, block trades, toxicity,
and flags like WATERFALL_DUMP, PULLED_BID_WALL_SPOOF.

Args:
    symbol: Stock ticker (e.g., "SPY", "AAPL", "TSLA", "NVDA", "MSFT")

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
symbolYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The main handler for the 'get_equity_flow' tool. It is decorated with @mcp.tool() (which also serves as registration), takes a symbol parameter, cleans it to uppercase, calls the _fetch helper to hit the /v1/flow/equity/{symbol} endpoint, and returns JSON.
    # ─── Tool 2: Equity Flow ─────────────────────────────────
    @mcp.tool()
    async def get_equity_flow(symbol: str) -> str:
        """Get real-time institutional orderflow for a US equity stock.
        
        Returns signal (BUY_PRESSURE/SELL_PRESSURE/WHALE_EXIT/EMERGENCY_DUMP),
        confidence score, large sell orders count, block trades, toxicity,
        and flags like WATERFALL_DUMP, PULLED_BID_WALL_SPOOF.
        
        Args:
            symbol: Stock ticker (e.g., "SPY", "AAPL", "TSLA", "NVDA", "MSFT")
        """
        clean = symbol.upper()
        data = await _fetch(f"/v1/flow/equity/{clean}")
        return json.dumps(data, indent=2)
  • Registration of the tool via the @mcp.tool() decorator on the get_equity_flow function.
    @mcp.tool()
  • The _fetch helper function used by get_equity_flow to make the actual HTTP request to the Horus RapidAPI endpoint and handle error/rate-limit responses.
    # ─── Helper ───────────────────────────────────────────────
    async def _fetch(endpoint: str) -> dict:
        """Fetch data from the live RapidAPI endpoint."""
        async with httpx.AsyncClient(timeout=10.0) as client:
            try:
                resp = await client.get(
                    f"{RAPIDAPI_BASE_URL}{endpoint}",
                    headers=HEADERS,
                )
                if resp.status_code == 200:
                    return resp.json()
                elif resp.status_code in [401, 403]:
                    return {
                        "error": True,
                        "signal": "UNAUTHORIZED",
                        "detail": "Invalid or missing RAPIDAPI_KEY. Please verify your RapidAPI subscription."
                    }
                elif resp.status_code == 429:
                    return {
                        "error": True,
                        "signal": "RATE_LIMITED",
                        "detail": "You have exceeded your RapidAPI quota. Please upgrade your plan."
                    }
                return {
                    "error": True,
                    "status_code": resp.status_code,
                    "detail": resp.text,
                }
            except Exception as e:
                return {
                    "error": True,
                    "detail": f"Network Error: {str(e)}"
                }
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses the returned data fields but does not mention latency, data freshness, rate limits, or whether the operation is read-only. The non-destructive nature is implied.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with no wasted words. It uses a clear structure: a one-line purpose, a list of return fields, and an Args section for the parameter. Information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has a single parameter and an output schema (not shown to us). The description covers all returned fields and the parameter's usage. For a simple data retrieval tool, it is fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, but the only parameter 'symbol' is well-described with examples (e.g., 'SPY', 'AAPL'), adding meaning beyond the schema's title and type. This compensates for the lack of schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it retrieves real-time institutional orderflow for US equities, listing specific return fields like signals and flags. This distinguishes it from siblings such as get_crypto_flow (crypto) and get_cross_exchange_flow (cross-exchange).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for US equities but does not explicitly state when to use this tool versus alternatives like get_crypto_flow or get_cross_exchange_flow. No exclusions or alternative conditions are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/horustechltd/horus-flow-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server