Gcore MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GCORE_TOOLS | No | Tool selection configuration. Can include predefined toolset names and/or wildcard patterns. Default depends on transport mode: HTTP uses 'management,instances', stdio uses 'management' | |
| GCORE_API_KEY | Yes | Your Gcore API key. Obtain from https://gcore.com/docs/account-settings/create-use-or-delete-a-permanent-api-token | |
| GCORE_BASE_URL | No | Base URL for Gcore API | https://api.gcore.com |
| GCORE_CLIENT_ID | No | Client ID | |
| GCORE_CLOUD_REGION_ID | No | Cloud region ID | |
| GCORE_CLOUD_PROJECT_ID | No | Cloud project ID |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| cloud_insts_actB | Proxy for Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_add_placegrpA | Add an instance to a server group. The instance must not already be in a server group. Bare metal servers do not support server groups. Args: servergroup_id: Anti-affinity or affinity or soft-anti-affinity server group ID. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_assign_secgrpA | Assign the security group to the server. To assign multiple security groups to
all ports, use the NULL value for the Args: name: Security group name, applies to all ports ports_security_group_names: Port security groups mapping extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_newA | Create an instance with specified configuration. How to get access: For Linux,
For Windows,
Args: project_id: Project ID region_id: Region ID flavor: The flavor of the instance. interfaces: A list of network interfaces for the instance. You can create one or more interfaces - private, public, or both. volumes: List of volumes that will be attached to the instance. allow_app_ports: Set to configuration: Parameters for the application template if creating the instance from an
name: Instance name. name_template: If you want the instance name to be automatically generated based on IP
addresses, you can provide a name template instead of specifying the name
manually. The template should include a placeholder that will be replaced during
provisioning. Supported placeholders are: password: For Linux instances, 'username' and 'password' are used to create a new user.
When only 'password' is provided, it is set as the password for the default user
of the image. For Windows instances, 'username' cannot be specified. Use the
'password' field to set the password for the 'Admin' user on Windows. Use the
' security_groups: Specifies security group UUIDs to be applied to all instance network interfaces. servergroup_id: Placement group ID for instance placement policy. ssh_key_name: Specifies the name of the SSH keypair, created via the
/v1/ tags: Key-value tags to associate with the resource. A tag is a key-value pair that can be associated with a resource, enabling efficient filtering and grouping for better organization and management. Some tags are read-only and cannot be modified by the user. Tags are also integrated with cost reports, allowing cost data to be filtered based on tag keys or values. user_data: String in base64 format. For Linux instances, ' username: For Linux instances, 'username' and 'password' are used to create a new user. For Windows instances, 'username' cannot be specified. Use 'password' field to set the password for the 'Admin' user on Windows. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_delA | Delete instance Args: project_id: Project ID region_id: Region ID instance_id: Instance ID delete_floatings: True if it is required to delete floating IPs assigned to the instance. Can't be
used with floatings: Comma separated list of floating ids that should be deleted. Can't be used with
reserved_fixed_ips: Comma separated list of port IDs to be deleted with the instance volumes: Comma separated list of volume IDs to be deleted with the instance extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_dis_portsecB | Disable port security for instance interface Args: extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_en_portsecB | Enable port security for instance interface Args: extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_getA | Retrieve detailed information about a specific instance. The response content
language for Cookie Parameters:
Args: project_id: Project ID region_id: Region ID instance_id: Instance ID extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_get_conC | Get instance console URL Args: console_type: Console type extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_lsA | List all instances in the specified project and region. Results can be filtered by various parameters like name, status, and IP address. Args: project_id: Project ID region_id: Region ID available_floating: Only show instances which are able to handle floating address changes_before: Filters the instances by a date and time stamp when the instances last changed. changes_since: Filters the instances by a date and time stamp when the instances last changed status. exclude_flavor_prefix: Exclude instances with specified flavor prefix exclude_secgroup: Exclude instances with specified security group name flavor_id: Filter out instances by flavor_prefix: Filter out instances by include_ai: Include GPU clusters' servers include_baremetal: Include bare metal servers. Please, use include_k8s: Include managed k8s worker nodes ip: An IPv4 address to filter results by. Note: partial matches are allowed. For example, searching for 192.168.0.1 will return 192.168.0.1, 192.168.0.10, 192.168.0.110, and so on. limit: Optional. Limit the number of returned items name: Filter instances by name. You can provide a full or partial name, instances with matching names will be returned. For example, entering 'test' will return all instances that contain 'test' in their name. offset: Optional. Offset value is used to exclude the first set of records from the result only_isolated: Include only isolated instances only_with_fixed_external_ip: Return bare metals only with external fixed IP addresses. order_by: Order by field and direction. profile_name: Filter result by ddos protection profile name. Effective only with protection_status: Filter result by DDoS status: Filters instances by status. tag_key_value: Optional. Filter by tag key-value pairs. tag_value: Optional. Filter by tag values. ? type_ddos_profile: Return bare metals either only with advanced or only basic DDoS protection.
Effective only with uuid: Filter the server list result by the UUID of the server. Allowed UUID part with_ddos: Include DDoS profile information in the response when set to with_interfaces_name: Include extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_rm_placegrpA | Remove an instance from its current server group. The instance must be in a server group to be removed. Bare metal servers do not support server groups. Args: extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_reszB | Change flavor of the instance Args: flavor_id: Flavor ID extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_unassign_secgrpB | Un-assign the security group to the server. To un-assign multiple security
groups to all ports, use the NULL value for the Args: name: Security group name, applies to all ports ports_security_group_names: Port security groups mapping extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_updC | Rename instance Args: project_id: Project ID region_id: Region ID instance_id: Instance ID name: Name. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_flavs_lsB | Retrieve a list of available instance flavors in the project and region. When
Args: disabled: Flag for filtering disabled flavors in the region. Defaults to true exclude_linux: Set to true to exclude flavors dedicated to linux images. Default False exclude_windows: Set to true to exclude flavors dedicated to windows images. Default False include_prices: Set to true if the response should include flavor prices extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_imgs_new_volA | Create a new image from a bootable volume. The volume must be bootable to create an image from it. Args: name: Image name volume_id: Required if source is volume. Volume id architecture: Image CPU architecture type: hw_firmware_type: Specifies the type of firmware with which to boot the guest. hw_machine_type: A virtual chipset type. is_baremetal: Set to true if the image will be used by bare metal servers. Defaults to false. os_type: The operating system installed on the image. source: Image source ssh_key: Whether the image supports SSH key or not tags: Key-value tags to associate with the resource. A tag is a key-value pair that can be associated with a resource, enabling efficient filtering and grouping for better organization and management. Some tags are read-only and cannot be modified by the user. Tags are also integrated with cost reports, allowing cost data to be filtered based on tag keys or values. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_imgs_delA | Delete a specific image. The image cannot be deleted if it is used by protected snapshots. Args: extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_imgs_getA | Retrieve detailed information about a specific image. Args: include_prices: Show price extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_imgs_lsA | Retrieve a list of available images in the project and region. The list can be filtered by visibility, tags, and other parameters. Returned entities are owned by the project or are public/shared with the client. Args: include_prices: Show price private: Any value to show private images tag_key: Filter by tag keys. tag_key_value: Filter by tag key-value pairs. Must be a valid JSON string. visibility: Image visibility. Globally visible images are public extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_imgs_updB | Update image properties and tags. Args: hw_firmware_type: Specifies the type of firmware with which to boot the guest. hw_machine_type: A virtual chipset type. is_baremetal: Set to true if the image will be used by bare metal servers. name: Image display name os_type: The operating system installed on the image. ssh_key: Whether the image supports SSH key or not tags: Key-value tags to associate with the resource. A tag is a key-value pair that can be associated with a resource, enabling efficient filtering and grouping for better organization and management. Some tags are read-only and cannot be modified by the user. Tags are also integrated with cost reports, allowing cost data to be filtered based on tag keys or values. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_imgs_uplA | Upload an image from a URL. The image can be configured with various properties like OS type, architecture, and tags. Args: name: Image name url: URL architecture: Image CPU architecture type: cow_format: When True, image cannot be deleted unless all volumes, created from it, are deleted. hw_firmware_type: Specifies the type of firmware with which to boot the guest. hw_machine_type: A virtual chipset type. is_baremetal: Set to true if the image will be used by bare metal servers. Defaults to false. os_distro: OS Distribution, i.e. Debian, CentOS, Ubuntu, CoreOS etc. os_type: The operating system installed on the image. os_version: OS version, i.e. 22.04 (for Ubuntu) or 9.4 for Debian ssh_key: Whether the image supports SSH key or not tags: Key-value tags to associate with the resource. A tag is a key-value pair that can be associated with a resource, enabling efficient filtering and grouping for better organization and management. Some tags are read-only and cannot be modified by the user. Tags are also integrated with cost reports, allowing cost data to be filtered based on tag keys or values. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_ifaces_attB | Proxy for Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_ifaces_detB | Detach interface from instance Args: ip_address: IP address port_id: ID of the port extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_ifaces_lsA | List all network interfaces attached to the specified instance. Args: extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_insts_metr_lsA | Get instance metrics, including cpu, memory, network and disk metrics Args: project_id: Project ID region_id: Region ID instance_id: Instance ID time_interval: Time interval. time_unit: Time interval unit. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_placegrps_newA | Create an affinity or anti-affinity or soft-anti-affinity placement group Args: name: The name of the server group. policy: The server group policy. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_placegrps_delB | Delete placement group Args: extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_placegrps_getB | Get placement group Args: extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_placegrps_lsB | List placement groups Args: extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_projs_newB | Create a new project for a client. Project management must be enabled to perform this operation. Args: name: Unique project name for a client. Each client always has one "default" project. client_id: ID associated with the client. description: Description of the project. state: State of the project. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds |
| cloud_projs_delA | Delete a project and all its associated cloud resources across all regions. This operation is irreversible and cannot be undone. Default projects cannot be deleted. Args: extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_projs_getA | Retrieve detailed information about a specific project. Args: extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_projs_lsB | Retrieve a list of projects for a client. Results can be filtered by name and ordered by various fields. Args: client_id: Client ID filter for administrators. include_deleted: Whether to include deleted projects in the response. limit: Limit value is used to limit the number of records in the result name: Name to filter the results by. offset: Offset value is used to exclude the first set of records from the result order_by: Order by field and direction. extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds |
| cloud_qotas_get_allC | Get combined client quotas, including both regional and global quotas. |
| cloud_qotas_get_by_regionA | Get quotas for a specific region and client. Args: client_id: Client ID region_id: Region ID extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric region_id. Resolve region names with |
| cloud_qotas_get_globalC | Get global quotas for a specific client. Args: client_id: Client ID extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds |
| cloud_rgns_getA | Get region Args: region_id: Region ID show_volume_types: If true, null extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric region_id. Resolve region names with |
| cloud_rgns_lsA | List regions Args: limit: Limit the number of returned regions. Falls back to default of 100 if not specified. Limited by max limit value of 1000 offset: Offset value is used to exclude the first set of records from the result order_by: Order by field and direction. product: If defined then return only regions that support given product. show_volume_types: If true, null extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds |
| cloud_tsks_ack_allC | Acknowledge all tasks Args: project_id: Project ID region_id: Region ID extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
| cloud_tsks_ack_oneC | Acknowledge one task Args: task_id: Task ID extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds |
| cloud_tsks_getC | Get task Args: task_id: Task ID extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds |
| cloud_tsks_lsB | List tasks Args: from_timestamp: ISO formatted datetime string. Filter the tasks by creation date greater than or
equal to is_acknowledged: Filter the tasks by their acknowledgement status limit: Limit the number of returned tasks. Falls back to default of 10 if not specified. Limited by max limit value of 1000 offset: Offset value is used to exclude the first set of records from the result order_by: Sorting by creation date. Oldest first, or most recent first project_id: The project ID to filter the tasks by project. Supports multiple values of kind key=value1&key=value2 region_id: The region ID to filter the tasks by region. Supports multiple values of kind key=value1&key=value2 sorting: (DEPRECATED Use ' state: Filter the tasks by state. Supports multiple values of kind key=value1&key=value2 task_type: Filter the tasks by their type one of [' to_timestamp: ISO formatted datetime string. Filter the tasks by creation date less than or
equal to extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Note: Pass the numeric project_id. When a project name is provided, resolve it via |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/G-Core/gcore-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server