get_network_groups

What it answers

1. 1Which physician groups and health systems a Medicare Advantage contract's published network covers, and how much of each: for a contract and plan year (2026 or 2027), every billing group its listed clinicians bill Medicare through (or every health system of the hospitals they are affiliated with), with the clinicians the contract lists, the group's own clinician count and the share; or search one group or system by name across every contract.
2. 2Use cases: 'What share of Virginia Mason's doctors does Regence list?'; 'Which MA contracts list most of Optum's physicians in Texas?'; 'Which large groups does H5938 cover?'.
3. 3Groups are CMS's Medicare reassignment (the group a clinician bills through); systems are CMS's hospital affiliation through the hospital system map.
4. 4A clinician in several groups counts in each.
5. 5A share is of the group's Medicare-enrolled clinicians, as listed in the plan's published directory.
6. 6The publish is pinned by dataset_id.
7. 7SOURCE: medicare_silver.ma_network_contract_group_v1 (the Data Tracker's directory table x CMS PECOS reassignment x CMS Doctors and Clinicians facility affiliation x the hospital system map).

Inputs (7)

Call it

# MCP (https://mcp.vladahealth.com/mcp): the tool by name
get_network_groups(name="Virginia Mason", min_clinicians=500, limit=3)

curl -X POST https://api.vladahealth.com/v1/tools/get_network_groups \
  -H "Authorization: Bearer $VLADA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name":"Virginia Mason","min_clinicians":500,"limit":3}'

# the schema, no key
curl https://api.vladahealth.com/v1/tools/get_network_groups/schema

A real answer

{
 "value": {
  "found": false,
  "not_found_reason": "no_row_matches_filters",
  "query": {
   "name": "Virginia Mason",
   "plan_year": 2027,
   "level": "group",
   "min_clinicians": 500,
   "limit": 3
  },
  "dataset_id": "7bceef45cc9e5910e64caa428a1f3e40869f91d149c4e19f08cc55f5e468ba7c",
  "rows": [],
  "query_ids": [
   "7add1d36-0b8a-430f-9532-c0fd2d3afeb0"
  ]
 },
 "unit": "network_groups",
 "vintage": null,
 "source": {
  "dataset": "MA plan networks, 2026 and 2027 (Data Tracker): plan year x CMS plan x NPI x listed location",
  "publisher": "vlada",
  "catalog_updated_at": "2026-11-02"
 },
 "caveats": [],
 "response_hash": "865b1be73ac8247753af5fdf3842c60072ad001422d6e773075a1231685a75b5",
 "semantic_version": 1,
 "tool_version": "get_network_groups@0.2.0",
 "explanation": null,
 "status": "complete",
 "audience": "customer",
 "answer": {
  "value_ref": "value",
  "unit": "network_groups",
  "scope": {
   "tool": "get_network_groups",
   "filters": {
    "name": "Virginia Mason",
    "plan_year": 2027,
    "level": "group",
    "min_clinicians": 500,
    "limit": 3
   }
  }
 },
 "method": "Computed over the filters shown in this answer's scope, from the sources listed in its evidence. Nothing outside those filters was included. You did not specify level; group was used. You did not specify plan_year; 2027 was used.",
 "evidence": {
  "sources": [
   {
    "dataset": "MA plan networks, 2026 and 2027 (Data Tracker): plan year x CMS plan x NPI x listed location",
    "publisher": "vlada",
    "catalog_updated_at": "2026-11-02"
   }
  ],
  "response_hash": "865b1be73ac8247753af5fdf3842c60072ad001422d6e773075a1231685a75b5"
 },
 "defaults_applied": [
  {
   "param": "level",
   "used": "group",
   "reason": "'group' (default"
  },
  {
   "param": "plan_year",
   "used": 2027,
   "reason": "2026 or 2027 (default 2027)."
  }
 ],
 "freshness": {
  "state": "unknown",
  "why": "This tool does not report an edition for its answer, and the door could not derive one from what the answer reads. Treat the result as current to no stated date."
 }
}

What comes back

{
 "$defs": {
  "Quality": {
   "description": "Row-level quality signal. All flags precomputed at build time\n(stored on the gold mart) and passed through here.",
   "properties": {
    "is_outlier": {
     "default": false,
     "title": "Is Outlier",
     "type": "boolean"
    },
    "is_ghost_candidate": {
     "default": false,
     "title": "Is Ghost Candidate",
     "type": "boolean"
    },
    "n_similar_rates": {
     "default": 0,
     "title": "N Similar Rates",
     "type": "integer"
    },
    "confidence": {
     "default": 1,
     "title": "Confidence",
     "type": "number"
    }
   },
   "title": "Quality",
   "type": "object"
  },
  "Source": {
   "description": "Cell-level provenance. Every served value traces back here.\n\n`snapshot_id` is the Iceberg snapshot the tool read from. Two calls\nat the same snapshot MUST produce byte-identical responses —\nthat's the content-addressed caching guarantee.",
   "properties": {
    "table": {
     "title": "Table",
     "type": "string"
    },
    "rate_id": {
     "anyOf": [
      {
       "type": "string"
      },
      {
       "type": "null"
      }
     ],
     "default": null,
     "title": "Rate Id"
    },
    "source_files": {
     "items": {
      "type": "string"
     },
     "title": "Source Files",
     "type": "array"
    },
    "snapshot_id": {
     "anyOf": [
      {
       "type": "integer"
      },
      {
       "type": "null"
      }
     ],
     "default": null,
     "title": "Snapshot Id"
    }
   },
   "required": [
    "table"
   ],
   "title": "Source",
   "type": "object"
  }
 },
 "properties": {
  "value": {
   "default": null,
   "title": "Value"
  },
  "unit": {
   "anyOf": [
    {
     "type": "string"
    },
    {
     "type": "null"
    }
   ],
   "default": null,
   "title": "Unit"
  },
  "vintage": {
   "anyOf": [
    {
     "type": "string"
    },
    {
     "type": "null"
    }
   ],
   "default": null,
   "title": "Vintage"
  },
  "source": {
   "$ref": "#/$defs/Source"
  },
  "methodology": {
   "anyOf": [
    {
     "type": "string"
    },
    {
     "type": "null"
    }
   ],
   "default": null,
   "title": "Methodology"
  },
  "quality": {
   "$ref": "#/$defs/Quality"
  },
  "invariants_applied": {
   "items": {
    "type": "string"
   },
   "title": "Invariants Applied",
   "type": "array"
  },
  "caveats": {
   "items": {
    "type": "string"
   },
   "title": "Caveats",
   "type": "array"
  },
  "response_hash": {
   "default": "",
   "title": "Response Hash",
   "type": "string"
  },
  "semantic_version": {
   "default": 1,
   "title": "Semantic Version",
   "type": "integer"
  },
  "tool_version": {
   "default": "unknown",
   "title": "Tool Version",
   "type": "string"
  },
  "explanation": {
   "anyOf": [
    {
     "type": "string"
    },
    {
     "type": "null"
    }
   ],
   "default": null,
   "title": "Explanation"
  },
  "status": {
   "default": "complete",
   "title": "Status",
   "type": "string"
  },
  "refusal": {
   "anyOf": [
    {
     "additionalProperties": true,
     "type": "object"
    },
    {
     "type": "null"
    }
   ],
   "default": null,
   "title": "Refusal"
  },
  "failure": {
   "anyOf": [
    {
     "additionalProperties": true,
     "type": "object"
    },
    {
     "type": "null"
    }
   ],
   "default": null,
   "title": "Failure"
  },
  "as_of": {
   "anyOf": [
    {
     "type": "string"
    },
    {
     "type": "null"
    }
   ],
   "default": null,
   "title": "As Of"
  },
  "freshness_state": {
   "default": "unknown",
   "title": "Freshness State",
   "type": "string"
  }
 },
 "title": "NetworkGroupsResponse",
 "type": "object"
}

Sources

Known limits (3)

1. 1Groups come from Medicare reassignment: a group's clinicians who do not bill Medicare are not counted.
2. 2Contract level: a contract with several networks (HMO and PPO plans) is read as one.
3. 3Coverage follows the directory build (stage 25); an uncovered contract answers no_coverage.