ellipsis-drive

Endpoint

Hosted endpoint · transport http

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

Tools

• create_compute_task — Creates a compute task environment with the given specification. It usually takes up to a few minutes for the requested environment to be prepared.
• execute_compute_task — Executes a python function on the created compute environment. Depending on the complexity of the code and the input/output data sizes this can either resolve in minutes to hours. This tool will move the compute task to processing,
• get_compute_task — Returns detailed information on the given compute task
• download_partial_result_compute_task — Downloads a file with part of the compute task result when largeResult is true. The file ids can be found in the result section of the get_compute_task tool.
• terminate_compute_task — Terminates the given compute task
• get_path_info — Returns information about the given path
• path_get_info — Returns detailed information on the given path
• path_get_thumbnail — Returns the preview thumbnail of a given path
• create_raster_path — Creates a new raster path
• create_raster_timestamp — Creates a new raster timestamp
• location_vector — Get features at a location of a vector timestamp
• path_raster_get_uploads — Gets the uploads of a raster timestamp
• get_compute_tasks — Retrieves the compute tasks of a given user
• path_list_folder — Returns all layers in the given folder that you have access to.
• analyse_raster — Analyses the data of raster timestamps
• path_search — Search paths on Ellipsis Drive according to the given criteria
• features_by_extent — Get features of a vector timestamp by extent
• user_list_root — Lists paths in the given root directory of the authenticated user

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.

Work with this as data

Every MCP server here is available over the APIs.io API and to AI agents over MCP.

curl "https://apis.io/api/v1/mcp/ellipsis-drive"

curl "https://apis.io/api/v1/mcp?limit=25"