A Model Context Protocol (MCP) server acts as a proxy between an external service that provides context, data, or capabilities to a Large Language Model (LLM) or AI application. MCP servers connect AI applications to external systems such as databases and web services, translating their responses into a format that the AI application can understand.
Server Setup
You must enable MCP servers and set up authentication before use. For more information about using Google and Google Cloud remote MCP servers, see Google Cloud MCP servers overview.
MCP server for Gemini Enterprise for Customer Experience API
Server Endpoints
An MCP service endpoint is the network address and communication interface (usually a URL) of the MCP server that an AI application (the Host for the MCP client) uses to establish a secure, standardized connection. It is the point of contact for the LLM to request context, call a tool, or access a resource. Google MCP endpoints can be global or regional.
The ces.googleapis.com MCP server has the following MCP endpoint:
- https://ces.[REGION].rep.googleapis.com/mcp
MCP Tools
An MCP tool is a function or executable capability that an MCP server exposes to a LLM or AI application to perform an action in the real world.
The ces.googleapis.com MCP server has the following tools:
| MCP Tools | |
|---|---|
| list_apps | Lists apps in the given project and location. |
| get_app | Gets details of the specified app. |
| create_app | Creates a new app in the given project and location. |
| update_app | Updates the specified app. Make sure to always pass an update mask in the input. |
| delete_app | Deletes the specified app. |
| list_agents | Lists agents in the given app. |
| get_agent | Gets details of the specified agent. |
| create_agent | Creates a new agent in the given app. |
| update_agent | Updates the specified agent. Make sure to always pass an update mask in the input. |
| delete_agent | Deletes the specified agent. |
| list_tools | Lists tools in the given app. |
| get_tool | Gets details of the specified tool. |
| create_tool | Creates a new tool in the given app. |
| update_tool | Updates the specified tool. Make sure to always pass an update mask in the input. |
| delete_tool | Deletes the specified tool. |
| list_guardrails | Lists guardrails in the given app. |
| get_guardrail | Gets details of the specified guardrail. |
| create_guardrail | Creates a new guardrail in the given app. |
| update_guardrail | Updates the specified guardrail. Make sure to always pass an update mask in the input. |
| delete_guardrail | Deletes the specified guardrail. |
| list_deployments | Lists deployments in the given app. |
| get_deployment | Gets details of the specified deployment. |
| create_deployment | Creates a new deployment in the given app. |
| update_deployment | Updates the specified deployment. Make sure to always pass an update mask in the input. |
| delete_deployment | Deletes the specified deployment. |
| list_toolsets | Lists toolsets in the given app. |
| get_toolset | Gets details of the specified toolset. |
| create_toolset | Creates a new toolset in the given app. |
| update_toolset | Updates the specified toolset. Make sure to always pass an update mask in the input. |
| delete_toolset | Deletes the specified toolset. |
| list_app_versions | Lists all app versions in the given app. |
| get_app_version | Gets details of the specified app version. |
| create_app_version | Creates a new app version in the given app. |
| delete_app_version | Deletes the specified app version. |
| restore_app_version | Restores the specified app version. |
| list_changelogs | Lists changelogs in the given app. |
| get_changelog | Gets details of the specified changelog. |
| start_export_app | Starts to export a CES app |
| start_import_app | Starts to import a CES app |
| run_evaluation | Runs an evaluation for a CES app |
| create_evaluation | Creates a new evaluation. |
| create_evaluation_dataset | Creates a new evaluation dataset. |
| delete_evaluation | Deletes the specified evaluation. |
| delete_evaluation_dataset | Deletes the specified evaluation dataset. |
| generate_evaluation_from_conversation | Generates an evaluation from a conversation. |
| get_evaluation | Gets details of the specified evaluation. |
| get_evaluation_dataset | Gets details of the specified evaluation dataset. |
| get_evaluation_result | Gets details of the specified evaluation result. |
| get_evaluation_run | Gets details of the specified evaluation run. |
| list_evaluation_datasets | Lists evaluation datasets. |
| list_evaluation_results | Lists evaluation results. |
| list_evaluation_runs | Lists evaluation runs. |
| list_evaluations | Lists evaluations. |
| update_evaluation | Updates the specified evaluation. Make sure to always pass an update mask in the input. |
| update_evaluation_dataset | Updates the specified evaluation dataset Make sure to always pass an update mask in the input. |
| delete_evaluation_result | Deletes the specified evaluation result. |
| delete_evaluation_run | Deletes the specified evaluation run. |
| get_conversation | Gets details of the specified conversation. |
| list_conversations | Lists conversations. |
| get_operation |
Gets the status of a long-running operation. Usage Some tools (for example, Parameters * |
Get MCP tool specifications
To get the MCP tool specifications for all tools in an MCP server, use the tools/list method. The following example demonstrates how to use curl to list all tools and their specifications currently available within the MCP server.
| Curl Request |
|---|
curl --location 'https://ces.[REGION].rep.googleapis.com/mcp' \ --header 'content-type: application/json' \ --header 'accept: application/json, text/event-stream' \ --data '{ "method": "tools/list", "jsonrpc": "2.0", "id": 1 }' |