Copy as Markdown[Open in ChatGPT](https://chatgpt.com/?q=Read%20https%3A%2F%2Fcoralogix.com%2Fdocs%2Fuser-guides%2Fmcp-server%2Ftools%2Fai-center.md%20and%20help%20me%20with%20my%20question%20about%20this%20Coralogix%20documentation%20page.)[Open in Claude](https://claude.ai/new?q=Read%20https%3A%2F%2Fcoralogix.com%2Fdocs%2Fuser-guides%2Fmcp-server%2Ftools%2Fai-center.md%20and%20help%20me%20with%20my%20question%20about%20this%20Coralogix%20documentation%20page.) # AI Center Use the Coralogix MCP server to work with [AI Center](https://coralogix.com/docs/docs/user-guides/ai/.md) directly from your AI agent: take inventory of your AI applications, read and configure [evaluations](https://coralogix.com/docs/docs/user-guides/ai/evaluations/.md) and custom evaluation policies, link policies to applications, and manage per-model pricing. These tools are available on MCP server v2 and inherit the permissions of your authenticated user (see [AI Center permissions](https://coralogix.com/docs/docs/user-guides/ai/permissions/.md)). The read tools need any one of `AI-OVERVIEW:READ`, `AI-APP-CATALOG:READ`, or `AI-APP-EVALUATORS:READ`. The evaluation write tools need `AI-APP-EVALUATORS:MANAGE`; the custom-evaluation and model-pricing tools require AI Center management access. Reading interaction content also requires `SPANS.DATA-API#HIGH:READDATA`. Note The write tools change live AI Center configuration. MCP clients prompt for per-call approval on the destructive ones (create, update, delete, link, unlink, set pricing) before they run. ## Read tools[​](#read-tools "Direct link to Read tools") | Tool | Description | | --------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------- | | `ai_center_list_applications` | List the team's AI applications, including each app's guarded (`guardrailsIntegrated`) status. | | `ai_center_get_application` | Get one AI application by its UUID. | | `ai_center_list_evaluations` | List configured evaluations (enabled state, target, config), optionally scoped to one app by `application` + `subsystem`. | | `ai_center_get_evaluation` | Get one configured evaluation by its UUID. | | `ai_center_get_coverage` | Get evaluation coverage across applications—a mapping of each evaluation type to the number of apps using it. | | `ai_center_list_custom_evaluations` | List all custom evaluation policies for the team. | | `ai_center_list_custom_evaluations_for_application` | List custom evaluations linked to a specific application, by app UUID. | | `ai_center_get_model_pricing` | Get the team's custom per-model pricing overrides. | ## Write tools[​](#write-tools "Direct link to Write tools") | Tool | Description | | ------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------- | | `ai_center_create_evaluation` | Create (enable) an evaluation on an AI application. | | `ai_center_update_evaluation` | Update a configured evaluation by UUID (enable/disable, change config or threshold). Partial patch. | | `ai_center_delete_evaluation` | Delete a configured evaluation by UUID, removing it from its application. Not reversible. | | `ai_center_create_custom_evaluation` | Create a custom evaluation policy. | | `ai_center_update_custom_evaluation` | Update a custom evaluation policy by UUID. Partial patch. | | `ai_center_add_policy_to_application` | Attach a custom evaluation (policy) to an AI application. | | `ai_center_remove_policy_from_application` | Detach a custom evaluation (policy) from an application. Removes only the link; the policy itself is untouched and can be re-added. | | `ai_center_set_model_pricing` | Set the team's custom per-model pricing overrides. Team-wide; applies to new data only. | Note Some deletions are intentionally not available through the MCP server: deleting a custom evaluation policy, deleting an AI application, and deleting model-pricing overrides. Use the Coralogix UI for those. To stop applying a policy to an app, unlink it with `ai_center_remove_policy_from_application`—the policy object survives. ### Create and update parameters[​](#create-and-update-parameters "Direct link to Create and update parameters") `ai_center_create_evaluation`: | Parameter | Required | Type | Description | | ------------- | -------- | ------- | ------------------------------------------------------------------ | | `application` | Yes | string | The application to attach the evaluation to. | | `subsystem` | Yes | string | The application's subsystem. | | `config` | Yes | object | The `EvaluationConfig` object—the `$case` variant plus its fields. | | `target` | No | enum | The evaluated turn: `prompt` or `response`. | | `is_enabled` | No | boolean | Whether the evaluation is enabled. Defaults to `true`. | | `threshold` | No | number | Score threshold for the evaluation. | `ai_center_create_custom_evaluation` takes a `body` object with `name`, `instructions`, `policyType`, and optional `description`, `violates`, `safe`, `examples`, and `applicationIds`. `ai_center_update_evaluation` and `ai_center_update_custom_evaluation` take the object's UUID plus an `updates` object—a partial patch, so include only the fields you want to change; omitted fields are left unchanged. `ai_center_set_model_pricing` takes a `prices` object mapping each model name to `{ inputPricePerMillionTokens, outputPricePerMillionTokens, cacheReadPricePerMillionTokens, cacheWritePricePerMillionTokens }`. ## Example prompts[​](#example-prompts "Direct link to Example prompts") ### Take inventory[​](#take-inventory "Direct link to Take inventory") ``` List my AI applications and tell me which ones aren't guarded. ``` ### Check evaluation coverage[​](#check-evaluation-coverage "Direct link to Check evaluation coverage") ``` Which evaluation types have the least coverage across my AI apps? ``` ### Configure an evaluation[​](#configure-an-evaluation "Direct link to Configure an evaluation") ``` Enable the hallucination evaluation on the "support-bot" app's production subsystem, evaluating the response. ``` ### Link a custom policy[​](#link-a-custom-policy "Direct link to Link a custom policy") ``` Attach my "no-legal-advice" custom policy to the support-bot application. ``` ## Next steps[​](#next-steps "Direct link to Next steps") * Learn about [AI Center](https://coralogix.com/docs/docs/user-guides/ai/.md), [evaluations](https://coralogix.com/docs/docs/user-guides/ai/evaluations/.md), and [guardrails](https://coralogix.com/docs/docs/user-guides/ai/guardrails/.md). * Review the required [AI Center permissions](https://coralogix.com/docs/docs/user-guides/ai/permissions/.md).