query_collection
Run a query against a Firestore database. Executes a structured query and returns the matching documents. Required Parameters: - parent: The parent resource name in projects/{project_id}/databases/{database_id}/documents format (e.g., projects/my-project/databases/(default)/documents). - structur...
This record as markdown: /tools/com-googleapis-firestore-mcp/query-collection.md
What query_collection does on Mcp
AI agents call query_collection to retrieve information from Mcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
parent | string | Yes | Required. The parent resource name. In the format: `projects/{project_id}/databases/{database_id}/documents` or `projects/{project_id}/databases/{database_id}/d |
readTime | string | — | Reads documents as they were at the given time. This must be a microsecond precision timestamp within the past one hour, or if Point-in-Time Recovery is enabled |
transaction | string | — | Run the query within an already active transaction. The value here is the opaque transaction ID to execute the query in. |
explainOptions | object | — | Optional. Explain options for the query. If set, additional query statistics will be returned. If not, only query results will be returned. |
newTransaction | object | — | Starts a new transaction and reads the documents. Defaults to a read-only transaction. The new transaction ID will be returned as the first response in the stre |
requestOptions | object | — | Optional. The request options for this request. |
structuredQuery | object | — | A structured query. |
Parameters from the server's own tool schema.
Why query_collection is rated Low
Even though query_collection only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs query_collection safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For query_collection, this is the rule to start with:
query_collection is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Mcp, apply this rule, and every query_collection call is checked against it from then on.
Questions about query_collection
Run a query against a Firestore database. Executes a structured query and returns the matching documents. Required Parameters: - parent: The parent resource name in projects/{project_id}/databases/{database_id}/documents format (e.g., projects/my-project/databases/(default)/documents). - structured_query: A StructuredQuery object defining the query to execute. Example usage: json { "parent": "projects/my-project/databases/(default)/documents", "structured_query": { "from": [{"collection_id": "users"}], "where": { "field_filter": { "field": {"field_path": "age"}, "op": "GREATER_THAN_OR_EQUAL", "value": {"integer_value": 21} } }, "order_by": [ {"field": {"field_path": "age"}, "direction": "DESCENDING"} ], "limit": 10 } }. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
query_collection accepts 7 parameters: parent, readTime, transaction, explainOptions, newTransaction, requestOptions, structuredQuery. Required: parent. The full parameter table on this page comes from the server's own tool schema.
Register the MCP server in PolicyLayer and add a rule for query_collection: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp. Nothing to install.
query_collection is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the query_collection rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for query_collection. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
query_collection is provided by the MCP server (https://firestore.googleapis.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on , and thousands of servers like it.
This server
Across the catalogue