MCP Tools Reference: securitycenter.googleapis.com

Tool: get_source

Retrieves display name, description, and metadata for a specific finding source in Security Command Center by its resource name (e.g. "organizations/123/sources/456").

The following code sample shows how to use curl to call the get_source MCP tool.

Curl Request 
curl --location 'https://securitycenter.googleapis.com/mcp/investigate' \
--header 'content-type: application/json' \
--header 'accept: application/json, text/event-stream' \
--data '{
  "method": "tools/call",
  "params": {
    "name": "get_source",
    "arguments": {
      // provide these details according to the tool's MCP specification
    }
  },
  "jsonrpc": "2.0",
  "id": 1
}'

Input Schema

Request message for getting a source.

GetSourceRequest

JSON representation 
{
  "name": string
}
Fields
name

string

Required. Relative resource name of the source. Its format is organizations/[organization_id]/source/[source_id].

Output Schema

Security Command Center finding source. A finding source is an entity or a mechanism that can produce a finding. A source is like a container of findings that come from the same scanner, logger, monitor, and other tools.

Source

JSON representation 
{
  "name": string,
  "displayName": string,
  "description": string,
  "canonicalName": string
}
Fields
name

string

The relative resource name of this source. See: https://cloud.google.com/apis/design/resource_names#relative_resource_name Example: "organizations/{organization_id}/sources/{source_id}"
displayName

string

The source's display name. A source's display name must be unique amongst its siblings, for example, two sources with the same parent can't share the same display name. The display name must have a length between 1 and 64 characters (inclusive).
description

string

The description of the source (max of 1024 characters). Example: "Web Security Scanner is a web security scanner for common vulnerabilities in App Engine applications. It can automatically scan and detect four common vulnerabilities, including cross-site-scripting (XSS), Flash injection, mixed content (HTTP in HTTPS), and outdated or insecure libraries."
canonicalName

string

The canonical name of the finding source. It's either "organizations/{organization_id}/sources/{source_id}", "folders/{folder_id}/sources/{source_id}", or "projects/{project_number}/sources/{source_id}", depending on the closest CRM ancestor of the resource associated with the finding.

Tool Annotations

Tool annotations are sent to MCP clients to describe the basic risk of a given tool. Most clients treat these hints as untrusted, but they can be used to decide when a confirmation prompt might be sent to a user.

Along with the title string, the following boolean hints are defined as follows:

  • readOnlyHint: If true, the tool doesn't modify its environment. Default: false.
  • destructiveHint: If true, then the tool can perform destructive actions. If false, then the tool can only perform additive actions. Default: true.
  • idempotentHint: If true, then calling the tool repeatedly with the same arguments will have no additional effect on its environment. Default: false.
  • openWorldHint: If true, then the tool can interact with an 'open world' of external entities. If false, then the tool can only interact with internal entities. For example, a web search tool would be open world, while a memory tool would not be open world.

Destructive Hint: ❌ | Idempotent Hint: ✅ | Read Only Hint: ✅ | Open World Hint: ❌