MCP Tools Reference: firestore.googleapis.com

Tool: create_index

Create a composite index.

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

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

Input Schema

The request for [FirestoreAdmin.CreateIndex][].

CreateIndexRequest

JSON representation 
{
  "parent": string,
  "index": {
    object (Index)
  }
}
Fields
parent

string

Required. A parent name of the form projects/{project_id}/databases/{database_id}/collectionGroups/{collection_id}
index

object (Index)

Required. The composite index to create.

Index

JSON representation 
{
  "name": string,
  "queryScope": enum (QueryScope),
  "apiScope": enum (ApiScope),
  "fields": [
    {
      object (IndexField)
    }
  ],
  "state": enum (State),
  "density": enum (Density),
  "multikey": boolean,
  "shardCount": integer,
  "unique": boolean
}
Fields
name

string

Output only. A server defined name for this index. The form of this name for composite indexes will be: projects/{project_id}/databases/{database_id}/collectionGroups/{collection_id}/indexes/{composite_index_id} For single field indexes, this field will be empty.
queryScope

enum (QueryScope)

Indexes with a collection query scope specified allow queries against a collection that is the child of a specific document, specified at query time, and that has the same collection ID.

Indexes with a collection group query scope specified allow queries against all collections descended from a specific document, specified at query time, and that have the same collection ID as this index.
apiScope

enum (ApiScope)

The API scope supported by this index.
fields[]

object (IndexField)

A field in an index. The field_path describes which field is indexed, the value_mode describes how the field value is indexed.
state

enum (State)

Output only. The serving state of the index.
density

enum (Density)

Immutable. The density configuration of the index.
multikey

boolean

Optional. Whether the index is multikey. By default, the index is not multikey. For non-multikey indexes, none of the paths in the index definition reach or traverse an array, except via an explicit array index. For multikey indexes, at most one of the paths in the index definition reach or traverse an array, except via an explicit array index. Violations will result in errors.

Note this field only applies to index with MONGODB_COMPATIBLE_API ApiScope.
shardCount

integer

Optional. The number of shards for the index.
unique

boolean

Optional. Whether it is an unique index. Unique index ensures all values for the indexed field(s) are unique across documents.

IndexField

JSON representation 
{
  "fieldPath": string,

  // Union field value_mode can be only one of the following:
  "order": enum (Order),
  "arrayConfig": enum (ArrayConfig),
  "vectorConfig": {
    object (VectorConfig)
  }
  // End of list of possible types for union field value_mode.
}
Fields
fieldPath

string

Can be name. For single field indexes, this must match the name of the field or may be omitted.
Union field value_mode. How the field value is indexed. value_mode can be only one of the following:
order

enum (Order)

Indicates that this field supports ordering by the specified order or comparing using =, !=, <, <=, >, >=.
arrayConfig

enum (ArrayConfig)

Indicates that this field supports operations on array_values.
vectorConfig

object (VectorConfig)

Indicates that this field supports nearest neighbor and distance operations on vector.

VectorConfig

JSON representation 
{
  "dimension": integer
}
Fields
dimension

integer

The vector dimension this configuration applies to.

The resulting index will only include vectors of this dimension, and can be used for vector search with the same dimension.

QueryScope

Query Scope defines the scope at which a query is run. This is specified on a StructuredQuery's from field.

Enums
QUERY_SCOPE_UNSPECIFIED The query scope is unspecified. Not a valid option.
COLLECTION Indexes with a collection query scope specified allow queries against a collection that is the child of a specific document, specified at query time, and that has the collection ID specified by the index.
COLLECTION_GROUP Indexes with a collection group query scope specified allow queries against all collections that has the collection ID specified by the index.
COLLECTION_RECURSIVE Include all the collections's ancestor in the index. Only available for Datastore Mode databases.

ApiScope

API Scope defines the APIs (Firestore Native, or Firestore in Datastore Mode) that are supported for queries.

Enums
ANY_API The index can only be used by the Firestore Native query API. This is the default.
DATASTORE_MODE_API The index can only be used by the Firestore in Datastore Mode query API.
MONGODB_COMPATIBLE_API The index can only be used by the MONGODB_COMPATIBLE_API.

Order

The supported orderings.

Enums
ORDER_UNSPECIFIED The ordering is unspecified. Not a valid option.
ASCENDING The field is ordered by ascending field value.
DESCENDING The field is ordered by descending field value.

ArrayConfig

The supported array value configurations.

Enums
ARRAY_CONFIG_UNSPECIFIED The index does not support additional array queries.
CONTAINS The index supports array containment queries.

State

The state of an index. During index creation, an index will be in the CREATING state. If the index is created successfully, it will transition to the READY state. If the index creation encounters a problem, the index will transition to the NEEDS_REPAIR state.

Enums
STATE_UNSPECIFIED The state is unspecified.
CREATING The index is being created. There is an active long-running operation for the index. The index is updated when writing a document. Some index data may exist.
READY The index is ready to be used. The index is updated when writing a document. The index is fully populated from all stored documents it applies to.
NEEDS_REPAIR The index was being created, but something went wrong. There is no active long-running operation for the index, and the most recently finished long-running operation failed. The index is not updated when writing a document. Some index data may exist. Use the google.longrunning.Operations API to determine why the operation that last attempted to create this index failed, then re-create the index.

Density

The density configuration for the index.

Enums
DENSITY_UNSPECIFIED Unspecified. It will use database default setting. This value is input only.
SPARSE_ALL

An index entry will only exist if ALL fields are present in the document.

This is both the default and only allowed value for Standard edition databases (for both Cloud Firestore ANY_API and Cloud Datastore DATASTORE_MODE_API).

Take for example the following document:

{
  "__name__": "...",
  "a": 1,
  "b": 2,
  "c": 3
}

an index on (a ASC, b ASC, c ASC, __name__ ASC) will generate an index entry for this document since a, 'b', c, and __name__ are all present but an index of (a ASC, d ASC, __name__ ASC) will not generate an index entry for this document since d is missing.

This means that such indexes can only be used to serve a query when the query has either implicit or explicit requirements that all fields from the index are present.
SPARSE_ANY

An index entry will exist if ANY field are present in the document.

This is used as the definition of a sparse index for Enterprise edition databases.

Take for example the following document:

{
  "__name__": "...",
  "a": 1,
  "b": 2,
  "c": 3
}

an index on (a ASC, d ASC) will generate an index entry for this document since a is present, and will fill in an unset value for d. An index on (d ASC, e ASC) will not generate any index entry as neither d nor e are present.

An index that contains __name__ will generate an index entry for all documents since Firestore guarantees that all documents have a __name__ field.
DENSE

An index entry will exist regardless of if the fields are present or not.

This is the default density for an Enterprise edition database.

The index will store unset values for fields that are not present in the document.

Output Schema

This resource represents a long-running operation that is the result of a network API call.

Operation

JSON representation 
{
  "name": string,
  "metadata": {
    "@type": string,
    field1: ...,
    ...
  },
  "done": boolean,

  // Union field result can be only one of the following:
  "error": {
    object (Status)
  },
  "response": {
    "@type": string,
    field1: ...,
    ...
  }
  // End of list of possible types for union field result.
}
Fields
name

string

The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the name should be a resource name ending with operations/{unique_id}.
metadata

object

Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.

An object containing fields of an arbitrary type. An additional field "@type" contains a URI identifying the type. Example: { "id": 1234, "@type": "types.example.com/standard/id" }.
done

boolean

If the value is false, it means the operation is still in progress. If true, the operation is completed, and either error or response is available.
Union field result. The operation result, which can be either an error or a valid response. If done == false, neither error nor response is set. If done == true, exactly one of error or response can be set. Some services might not provide the result. result can be only one of the following:
error

object (Status)

The error result of the operation in case of failure or cancellation.
response

object

The normal, successful response of the operation. If the original method returns no data on success, such as Delete, the response is google.protobuf.Empty. If the original method is standard Get/Create/Update, the response should be the resource. For other methods, the response should have the type XxxResponse, where Xxx is the original method name. For example, if the original method name is TakeSnapshot(), the inferred response type is TakeSnapshotResponse.

An object containing fields of an arbitrary type. An additional field "@type" contains a URI identifying the type. Example: { "id": 1234, "@type": "types.example.com/standard/id" }.

Any

JSON representation 
{
  "typeUrl": string,
  "value": string
}
Fields
typeUrl

string

Identifies the type of the serialized Protobuf message with a URI reference consisting of a prefix ending in a slash and the fully-qualified type name.

Example: type.googleapis.com/google.protobuf.StringValue

This string must contain at least one / character, and the content after the last / must be the fully-qualified name of the type in canonical form, without a leading dot. Do not write a scheme on these URI references so that clients do not attempt to contact them.

The prefix is arbitrary and Protobuf implementations are expected to simply strip off everything up to and including the last / to identify the type. type.googleapis.com/ is a common default prefix that some legacy implementations require. This prefix does not indicate the origin of the type, and URIs containing it are not expected to respond to any requests.

All type URL strings must be legal URI references with the additional restriction (for the text format) that the content of the reference must consist only of alphanumeric characters, percent-encoded escapes, and characters in the following set (not including the outer backticks): /-.~_!$&()*+,;=. Despite our allowing percent encodings, implementations should not unescape them to prevent confusion with existing parsers. For example, type.googleapis.com%2FFoo should be rejected.

In the original design of Any, the possibility of launching a type resolution service at these type URLs was considered but Protobuf never implemented one and considers contacting these URLs to be problematic and a potential security issue. Do not attempt to contact type URLs.
value

string (bytes format)

Holds a Protobuf serialization of the type described by type_url.

A base64-encoded string.

Status

JSON representation 
{
  "code": integer,
  "message": string,
  "details": [
    {
      "@type": string,
      field1: ...,
      ...
    }
  ]
}
Fields
code

integer

The status code, which should be an enum value of google.rpc.Code.
message

string

A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
details[]

object

A list of messages that carry the error details. There is a common set of message types for APIs to use.

An object containing fields of an arbitrary type. An additional field "@type" contains a URI identifying the type. Example: { "id": 1234, "@type": "types.example.com/standard/id" }.

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: ❌