GS Robot MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GS_CLIENT_ID | Yes | Your Gausium Application Client ID | |
| GS_CLIENT_SECRET | Yes | Your Gausium Application Client Secret | |
| GS_OPEN_ACCESS_KEY | Yes | Your Gausium OpenAPI Access Key |
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_robotsB | Fetches the list of robots from the Gausium OpenAPI. |
| list_robot_mapsA | Fetches the list of maps associated with a specific robot. |
| create_robot_commandB | Creates a robot command. |
| get_site_infoA | Gets site information for a specific robot. |
| get_map_subareasC | Gets map subareas information for precise area control. |
| submit_temp_site_taskC | Submits a temporary task with site information for S-line robots. |
| submit_temp_no_site_taskB | Submits a temporary task without site information for S-line robots. |
| get_robot_commandB | Gets the result of a specific robot command. |
| list_robot_commandsB | Lists historical commands sent to a robot. |
| upload_robot_map_v1C | Uploads a robot map using V1 API. |
| get_upload_record_v1C | Checks the status of a V1 map upload. |
| download_robot_map_v1C | Downloads a robot map using V1 API. |
| download_robot_map_v2C | Downloads a robot map using V2 API. |
| generate_task_report_pngC | Generates a PNG map for M-line task report. |
| execute_m_line_task_workflowC | Executes complete M-line robot task workflow. |
| execute_s_line_site_task_workflowA | Executes complete S-line robot task workflow with site information. |
| execute_s_line_no_site_task_workflowB | Executes complete S-line robot task workflow without site information. |
| get_robot_status_smartA | 智能获取机器人状态。 |
| get_task_reports_smartC | 智能获取任务报告。 |
| batch_get_robot_statuses_smartA | 智能批量获取机器人状态。 |
| get_robot_capabilitiesC | 获取机器人支持的API能力。 |
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 21 tools
Most tools have clear purposes, but there is notable overlap between download_robot_map_v1 and download_robot_map_v2, which differ only by API version and are easy for an agent to confuse. There is also potential ambiguity between the three workflow-execution tools and the lower-level task submission/command tools, since they cover overlapping workflows at different abstraction levels.
The tools mostly follow a consistent snake_case verb_noun pattern, such as list_robots, get_site_info, create_robot_command, and upload_robot_map_v1. The main deviations are the 'smart' suffix tools and nested workflow names like execute_s_line_site_task_workflow, but the pattern remains predictable overall.
With 21 tools, the surface is somewhat heavy for an MCP server, especially because several tools are version-specific or workflow-level wrappers around lower-level operations. The count is defensible for a broad robot management domain, but it feels closer to the upper limit of what a typical agent can navigate efficiently.
The toolset covers the core robot lifecycle well: robot listing, status, capabilities, map retrieval/upload, commands, task submission, reporting, and workflow execution. Minor gaps include lack of map update/delete operations and no v2 upload counterpart, but the available surface supports realistic automation workflows.