AWS S3 Connector MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AWS_REGION | No | AWS region (default: us-west-2) | us-west-2 |
| AWS_ACCESS_KEY_ID | Yes | AWS access key ID for authentication | |
| AWS_SECRET_ACCESS_KEY | Yes | AWS secret access key for authentication |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| connect_awsA | Connect to AWS S3. Supports two modes:
|
| create_table_bucketC | Creates an S3 table bucket. Permissions: You must have the s3tables:CreateTableBucket permission. |
| list_table_bucketsA | List all S3 table buckets for your AWS account. Permissions: You must have the s3tables:ListTableBuckets permission. |
| create_namespaceA | Creates a namespace. A namespace is a logical grouping of tables within your S3 table bucket. Permissions: You must have the s3tables:CreateNamespace permission. |
| list_namespacesA | List all namespaces across all S3 table buckets. Permissions: You must have the s3tables:ListNamespaces permission. |
| create_tableB | Creates a new S3 table associated with the given S3 namespace in an S3 table bucket. The S3 table can be configured with specific format and metadata settings. Permissions: You must have the s3tables:CreateTable permission. |
| list_tablesA | List all S3 tables across all table buckets and namespaces. Permissions: You must have the s3tables:ListTables permission. |
| rename_tableA | Renames an S3 table or moves it to a different S3 namespace within the same S3 table bucket. Permissions: You must have the s3tables:RenameTable permission. |
| get_table_metadata_locationB | Gets the S3 URI location of the table metadata, which contains the schema and other table configuration information. Permissions: You must have the s3tables:GetTableMetadataLocation permission. |
| update_table_metadata_locationB | Updates the metadata location for an S3 table. Permissions: You must have the s3tables:UpdateTableMetadataLocation permission. |
| get_bucket_metadata_configC | Retrieves the metadata table configuration for a regular general purpose bucket in S3. Permissions: You must have the s3:GetBucketMetadataConfiguration permission. |
| get_table_maintenance_configA | Gets details about the maintenance configuration of a table. Permissions: You must have the s3tables:GetTableMaintenanceConfiguration permission. |
| get_maintenance_job_statusB | Gets the status of a maintenance job for a table. Permissions: You must have the s3tables:GetTableMaintenanceJobStatus permission. |
| query_databaseA | Execute SQL queries against S3 Tables using PyIceberg/Daft engine. This tool provides a secure interface to run read-only SQL queries. |
| append_rows_to_tableB | Append rows to an Iceberg table using PyIceberg engine. The rows parameter must be a list of dictionaries, each representing a row. |
| import_csv_to_tableB | Reads data from a CSV file stored in S3 and imports it into an S3 table. If the table doesn't exist, it will be created with a schema inferred from the CSV. |
| import_parquet_to_tableA | Reads data from a Parquet file stored in S3 and imports it into an existing S3 table. The table must already exist. The Parquet file schema must be compatible with the table's schema. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 17 tools
Each tool targets a distinct operation on S3 Tables or related resources (e.g., bucket creation, namespace management, table CRUD, metadata, maintenance, data import/query, and connection setup). There is no overlap between tool purposes.
All tools follow a clear verb_noun (or verb_noun_noun) pattern, e.g., create_table_bucket, list_namespaces, get_table_metadata_location. No mixing of conventions like camelCase or inconsistent verb forms.
17 tools cover a broad domain of S3 Tables management, data operations, and connectivity. While slightly above the typical 3-15 range, they are well-scoped for the server's stated purpose.
Missing essential CRUD operations like delete (table, namespace, table bucket) and update (except metadata location). No tool to retrieve table schema or detailed table info beyond metadata location. Significant lifecycle gaps exist.