fetch tracks per assembly

Author: t-neumann

src/server/mcp_server.py

@@ -19,7 +19,6 @@ def list_species() -> list:
     genomes = tools.fetch_ucsc_genomes()
     return tools.get_species(genomes)
 
-
 @mcp.tool(
     name="list_assemblies",
     description="Get assemblies for a given species (exact or fuzzy match)",
@@ -47,17 +46,52 @@ def list_assemblies(species_name: str) -> list:
     genomes = tools.fetch_ucsc_genomes()
     return tools.get_assemblies(species_name, genomes)
 
+@mcp.tool(
+    name="list_ucsc_tracks",
+    description="List all UCSC genome browser tracks for a given assembly/genome",
+    output_schema={
+        "type": "object",
+        "properties": {
+            "genome": {"type": "string"},
+            "tracks": {"type": "object"},
+            "error": {"type": "string"},
+        },
+        "required": ["genome", "tracks"]
+    }
+)
+def list_ucsc_tracks_tool(genome: str, timeout: int = 10) -> dict:
+    """
+    MCP tool to fetch all UCSC tracks for a given genome/assembly.
+    
+    Args:
+        genome (str): Assembly name (e.g., hg38, mm10)
+        timeout (int): Request timeout in seconds
+    
+    Returns:
+        dict: {
+            "genome": genome,
+            "tracks": { ... full UCSC tracks JSON ... },
+            "error": "..."  # optional, only if something fails
+        }
+    """
+    tracks = tools.list_ucsc_tracks(genome, timeout=timeout)
+    return {
+        "genome": genome,
+        "tracks": tracks if "error" not in tracks else {},
+        "error": tracks.get("error")
+    }
+
 @mcp.tool(
     name="lift_over_coordinates",
     description="Convert genomic coordinates between assemblies using UCSC liftOver.",
-    output_schema={
+output_schema={
         "type": "object",
         "properties": {
             "input": {"type": "string"},
             "from": {"type": "string"},
             "to": {"type": "string"},
-            "output": {"type": "string"},
-            "error": {"type": "string"},
+            "output": {"type": ["string", "null"]},
+            "error": {"type": ["string", "null"]},
         },
         "required": ["from", "to"],
     },
@@ -127,7 +161,6 @@ def list_species_api():
     genomes = tools.fetch_ucsc_genomes()
     return tools.get_species(genomes)
 
-
 @app.get("/assemblies/{species_name}")
 def list_assemblies_api(species_name: str, exact: bool = Query(True, description="Set to false for partial name matches")):
     """
@@ -138,6 +171,17 @@ def list_assemblies_api(species_name: str, exact: bool = Query(True, description
     genomes = tools.fetch_ucsc_genomes()
     return tools.get_assemblies(species_name, genomes, exact)
 
+@app.get("/tracks/{genome}")
+def list_tracks_api(genome: str, timeout: int = Query(10, description="Request timeout in seconds")):
+    """
+    HTTP endpoint to list all available UCSC genome browser tracks for a given assembly/genome.
+    
+    Example:
+        /tracks/hg38
+    """
+    tracks = tools.list_ucsc_tracks(genome, timeout=timeout)
+    return tracks
+
 @app.post("/refresh-cache")
 def refresh_ucsc_cache():
     """Force-refresh UCSC genome cache."""

src/server/tools.py

@@ -43,6 +43,54 @@ def get_annotations(region: str, genome: str = "hg38", track: str = "knownGene")
         return response.json()
     except ValueError:
         return {"error": "No valid JSON returned", "text": response.text}
+
+def list_ucsc_tracks(genome: str = "hg38", timeout: int = 10) -> Dict[str, Any]:
+    """
+    List all available UCSC genome browser tracks for a given assembly.
+
+    Example:
+        list_ucsc_tracks("hg38")
+
+    Returns:
+        dict: Simplified UCSC track metadata, or {"error": "..."} if something fails.
+    """
+    url = f"{UCSC_BASE}/list/tracks?genome={genome}"
+
+    try:
+        resp = requests.get(url, timeout=timeout)
+        resp.raise_for_status()
+        data = resp.json()
+
+        # The main track data is nested under the genome key, e.g. data["hs1"]
+        if genome not in data:
+            return {"error": f"No track data found for {genome}"}
+
+        tracks = data[genome]
+
+        # Flatten the response into a list of top-level tracks (filter out composite containers)
+        simplified_tracks = []
+        for track_name, track_info in tracks.items():
+            if isinstance(track_info, dict) and "type" in track_info:
+                simplified_tracks.append({
+                    "track_id": track_name,
+                    "shortLabel": track_info.get("shortLabel"),
+                    "longLabel": track_info.get("longLabel"),
+                    "type": track_info.get("type"),
+                    "group": track_info.get("group"),
+                    "bigDataUrl": track_info.get("bigDataUrl"),
+                    "html": track_info.get("html"),
+                })
+
+        return {
+            "genome": genome,
+            "track_count": len(simplified_tracks),
+            "tracks": simplified_tracks,
+        }
+
+    except requests.exceptions.RequestException as e:
+        return {"error": f"Failed to fetch tracks for {genome}: {e}"}
+    except ValueError:
+        return {"error": f"Invalid JSON returned for {genome} tracks"}
 
 # ---------------------------------------------------------------------
 # UCSC genome listing utilities