get_short_interest

Instructions

Implementation Reference

• src/massive_mcp/tools/financials.py:40-63 (handler)

  The handler function for the 'get_short_interest' tool. It makes an HTTP GET request to '/stocks/v1/short-interest' with ticker, settlement_date_gte, limit, and cursor parameters. Registered via the @mcp.tool() decorator in the register() function.

  async def get_short_interest(
      ticker: str,
      settlement_date_gte: str | None = None,
      limit: int = 12,
      cursor: str | None = None,
  ) -> dict[str, Any]:
      """Bi-monthly short interest reports for a ticker.
  
      Args:
          ticker: Stock symbol.
          settlement_date_gte: Inclusive lower bound on settlement date.
          limit: Max rows. Default 12.
          cursor: Pagination cursor.
      """
      return await client.get(
          "/stocks/v1/short-interest",
          {
              "ticker": ticker,
              "settlement_date.gte": settlement_date_gte,
              "limit": limit,
              "cursor": cursor,
              "order": "desc",
          },
      )

• src/massive_mcp/tools/financials.py:12-13 (registration)

  The register() function that receives the FastMCP server and client. The @mcp.tool() decorator on line 39 registers 'get_short_interest' as an MCP tool. registration is invoked from server.py line 48: module.register(mcp, client).

  def register(mcp: FastMCP, client: MassiveClient) -> None:
      @mcp.tool()

• src/massive_mcp/server.py:37-48 (registration)

  build_server() iterates over tool modules (including 'financials') and calls module.register(mcp, client). This is where the financials module (containing get_short_interest) gets registered with the FastMCP server.

  for module in (
      aggregates,
      quotes,
      snapshots,
      tickers,
      news,
      reference,
      indicators,
      corporate,
      financials,
  ):
      module.register(mcp, client)

• src/massive_mcp/client.py:47-89 (helper)

  The MassiveClient.get() helper called by get_short_interest. Handles HTTP GET requests with retry logic, auth (bearer or query param), error handling, and response trimming.

  async def get(
      self, path: str, params: dict[str, Any] | None = None, *, trim: bool = True
  ) -> dict[str, Any]:
      merged: dict[str, Any] = {k: v for k, v in (params or {}).items() if v is not None}
      if self._settings.auth_mode == "query":
          merged["apiKey"] = self._settings.api_key
  
      last_exc: Exception | None = None
      for attempt in range(MAX_RETRIES):
          try:
              resp = await self._http.get(path, params=merged)
          except httpx.HTTPError as exc:
              last_exc = exc
              await asyncio.sleep(2**attempt)
              continue
  
          if resp.status_code == 429:
              retry_after = float(resp.headers.get("Retry-After", 2**attempt))
              await asyncio.sleep(min(retry_after, 30))
              continue
          if 500 <= resp.status_code < 600 and attempt < MAX_RETRIES - 1:
              await asyncio.sleep(2**attempt)
              continue
  
          if resp.status_code == 401:
              hint = (
                  "auth rejected — verify MASSIVE_API_KEY; "
                  "if you used MASSIVE_AUTH_MODE=bearer, try 'query' (or vice versa)"
              )
              raise MassiveAPIError(401, hint, _strip_secrets(str(resp.request.url)))
  
          try:
              data = resp.json()
          except ValueError:
              data = {"raw": resp.text}
  
          if not resp.is_success:
              msg = data.get("error") or data.get("message") or resp.reason_phrase or "request failed"
              raise MassiveAPIError(resp.status_code, str(msg), _strip_secrets(str(resp.request.url)))
  
          return _trim(data) if trim else data
  
      raise MassiveAPIError(0, f"network error after {MAX_RETRIES} retries: {last_exc}", path)

• src/massive_mcp/tools/financials.py:40-45 (schema)

  The function signature defines the input schema: ticker (str, required), settlement_date_gte (str|None), limit (int, default 12), cursor (str|None). The return type is dict[str, Any]. These are the type annotations and defaults that serve as the tool's parameter schema.

  async def get_short_interest(
      ticker: str,
      settlement_date_gte: str | None = None,
      limit: int = 12,
      cursor: str | None = None,
  ) -> dict[str, Any]: