get_feed_value

Instructions

Implementation Reference

• src/pythia_oracle_mcp/server.py:1335-1381 (handler)

  The `get_feed_value` tool function: fetches the latest computed value of a Pythia indicator feed from the live cache (feed_values_current in feed-status.json). It looks up matching feed names and returns the value, chain, and computed_at timestamp per chain. If not found, returns a diagnostic message.

  @mcp.tool()
  async def get_feed_value(feed_name: str) -> str:
      """Get the latest computed value of a Pythia indicator feed.
  
      Reads from the live cache (feed_values table) populated by the indicator
      pipeline on every cycle. Off-chain AI agents use this when reasoning
      about a Vision context, choosing an Event threshold, or sanity-checking
      a feed's current level. On-chain consumers should request the value
      through oracle.request() to get a Chainlink-attested response — see
      get_integration_guide().
  
      Args:
          feed_name: full feed name (e.g. 'bitcoin_RSI_1H_14', 'pol_EMA_5M_20').
  
      Returns:
          Latest value + computed_at + chain, one block per chain if a feed
          exists on multiple chains. If the feed has no cached value, returns
          a diagnostic pointer (warm-up window, deactivated, or unknown name).
      """
      data = await _fetch_data()
      feeds = data.get("feed_values_current", []) if data else []
  
      matches = [f for f in feeds if f.get("feed_name") == feed_name]
      if not matches:
          return (
              f"Feed '{feed_name}' has no current value in the live cache.\n"
              "Possible reasons:\n"
              "  - Feed name not registered (use list_tokens() + "
              "get_token_feeds(engine_id) to discover)\n"
              "  - Feed inside its warm-up window (1H/1D/1W indicators on "
              "freshly-onboarded tokens)\n"
              "  - Pipeline degraded — check check_oracle_health()"
          )
  
      out = [f"Feed: {feed_name}"]
      for m in matches:
          out.append("")
          out.append(f"  Chain:       {m.get('chain')}")
          out.append(f"  Value:       {m.get('value')}")
          out.append(f"  Computed at: {m.get('computed_at')}")
      out.append("")
      out.append(
          "Cached value updated by the indicator pipeline. For a Chainlink-"
          "attested on-chain value, use oracle.request() — see "
          "get_integration_guide()."
      )
      return "\n".join(out)

• src/pythia_oracle_mcp/server.py:1336-1353 (schema)

  The tool's docstring serves as its schema: defines the 'feed_name' string parameter and describes the return format (value + computed_at + chain). Input is validated implicitly by matching against the live cache.

  async def get_feed_value(feed_name: str) -> str:
      """Get the latest computed value of a Pythia indicator feed.
  
      Reads from the live cache (feed_values table) populated by the indicator
      pipeline on every cycle. Off-chain AI agents use this when reasoning
      about a Vision context, choosing an Event threshold, or sanity-checking
      a feed's current level. On-chain consumers should request the value
      through oracle.request() to get a Chainlink-attested response — see
      get_integration_guide().
  
      Args:
          feed_name: full feed name (e.g. 'bitcoin_RSI_1H_14', 'pol_EMA_5M_20').
  
      Returns:
          Latest value + computed_at + chain, one block per chain if a feed
          exists on multiple chains. If the feed has no cached value, returns
          a diagnostic pointer (warm-up window, deactivated, or unknown name).
      """

• src/pythia_oracle_mcp/server.py:1335-1336 (registration)

  The `@mcp.tool()` decorator registers the function as an MCP tool named 'get_feed_value'.

  @mcp.tool()
  async def get_feed_value(feed_name: str) -> str: