dependency_tree

Graph · From docs/MCP_TOOLS.md on GitHub

Category graph · sensitivity confidential · capabilities read_state · readOnly true, destructive false, idempotent true, openWorld false · outputSchema no · timeout: layer default (300 s)

The nested upstream and downstream tree of one asset, the view cloudg deps prints. direction picks depends_on, dependents or both. Each node has id, name, type, account_id, via, relationship and children. include_hierarchy adds organization and account containment edges. The tree is cut to max_nodes nodes depth-first in list order; truncated is true only when nodes were actually left out.

Argument	Type	Default	Constraints	Description
ref	string	required	min length 1	Asset reference: internal id, ARN / cloud resource id, unique name, or unique ARN tail (e.g. 'function:api' or 'i-0abc').
direction	string	"both"	one of up, down, both	up = what it depends on, down = what depends on it.
max_depth	integer	3	1..6	Depth of the tree in each direction.
include_hierarchy	boolean	false		Include org / account containment edges.
max_nodes	integer	200	1..1000	Node budget across both trees; pruning is depth-first in list order.
dataset	string	""		Dataset name (see list_datasets). Empty = the active dataset.

Called with the arguments below, dependency_tree returned this structuredContent.

{"ref": "api-handler", "direction": "both", "max_depth": 2}

{
  "dataset": "sample",
  "asset": {
    "id": "api-handler",
    "name": "api-handler",
    "arn": "arn:aws:lambda:us-east-1:111111111111:function:api-handler",
    "type": "LAMBDA_FUNCTION",
    "account_id": "111111111111",
    "region": "us-east-1"
  },
  "depends_on": [
    {
      "id": "api-gw",
      "name": "public-api",
      "arn": "arn:aws:apigateway:us-east-1::/restapis/a1b2c3",
      "type": "API_GATEWAY",
      "account_id": "111111111111",
      "region": "us-east-1",
      "via": "INVOKES",
      "relationship": null,
      "children": []
    },
    {
      "id": "data-bucket",
      "name": "prod-data",
      "arn": "arn:aws:s3:::prod-data",
      "type": "S3_BUCKET",
      "account_id": "111111111111",
      "region": "us-east-1",
      "via": "INVOKES",
      "relationship": "TRIGGERED_BY",
      "children": []
    },
    "... 4 more"
  ],
  "dependents": [],
  "truncated": false
}

Called with the arguments below, dependency_tree returned this structuredContent.

{"ref": "kms-main", "direction": "down", "max_nodes": 2}

{
  "dataset": "sample",
  "asset": {
    "id": "kms-main",
    "name": "prod-main-key",
    "arn": "arn:aws:kms:us-east-1:111111111111:key/1111-2222",
    "type": "KMS_KEY",
    "account_id": "111111111111",
    "region": "us-east-1"
  },
  "dependents": [
    {
      "id": "api-handler",
      "name": "api-handler",
      "arn": "arn:aws:lambda:us-east-1:111111111111:function:api-handler",
      "type": "LAMBDA_FUNCTION",
      "account_id": "111111111111",
      "region": "us-east-1",
      "via": "REFERENCES",
      "relationship": "ENCRYPTED_BY_KMS",
      "children": []
    },
    {
      "id": "data-bucket",
      "name": "prod-data",
      "arn": "arn:aws:s3:::prod-data",
      "type": "S3_BUCKET",
      "account_id": "111111111111",
      "region": "us-east-1",
      "via": "REFERENCES",
      "relationship": "ENCRYPTED_BY_KMS",
      "children": []
    }
  ],
  "truncated": true
}