> ## Documentation Index > Fetch the complete documentation index at: https://conductorone-docs-cxp-788.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Get > Get the tenant's AI governance settings — the controls behind the admin /admin/settings/ai-governance page. Returns the full AIGovernanceSettings: allowed MCP client types, default client lifecycle, require_tool_approval, default tool classification, audit verbosity, auto-discovery toggle + interval, prefer_code_mode_over_direct_tools, and surface_requestable_tools. ## OpenAPI ````yaml https://spec.speakeasy.com/conductor-one/conductorone/my-source-with-code-samples get /api/v1/settings/ai-governance openapi: 3.1.0 info: description: The C1 API is a HTTP API for managing C1 resources. title: C1 API version: 0.1.0-alpha servers: - description: The C1 API server for the current tenant. url: https://{tenantDomain}.conductor.one variables: tenantDomain: default: example description: The domain of the tenant to use for this request. security: - bearerAuth: [] oauth: [] paths: /api/v1/settings/ai-governance: get: tags: - AI Governance Settings summary: Get description: |- Get the tenant's AI governance settings — the controls behind the admin /admin/settings/ai-governance page. Returns the full AIGovernanceSettings: allowed MCP client types, default client lifecycle, require_tool_approval, default tool classification, audit verbosity, auto-discovery toggle + interval, prefer_code_mode_over_direct_tools, and surface_requestable_tools. operationId: c1.api.ai_governance.v1.AIGovernanceSettingsService.Get responses: '200': content: application/json: schema: $ref: >- #/components/schemas/c1.api.ai_governance.v1.GetAIGovernanceSettingsResponse description: >- GetAIGovernanceSettingsResponse contains the tenant's AI governance settings. x-codeSamples: - lang: go label: Get source: "package main\n\nimport(\n\t\"context\"\n\t\"github.com/conductorone/conductorone-sdk-go/pkg/models/shared\"\n\tconductoronesdkgo \"github.com/conductorone/conductorone-sdk-go\"\n\t\"log\"\n)\n\nfunc main() {\n ctx := context.Background()\n\n s := conductoronesdkgo.New(\n conductoronesdkgo.WithSecurity(shared.Security{\n BearerAuth: \"\",\n Oauth: \"\",\n }),\n )\n\n res, err := s.AIGovernanceSettings.Get(ctx)\n if err != nil {\n log.Fatal(err)\n }\n if res.GetAIGovernanceSettingsResponse != nil {\n // handle response\n }\n}" - lang: typescript label: Typescript (SDK) source: >- import { ConductoroneSDKTypescript } from "conductorone-sdk-typescript"; const conductoroneSDKTypescript = new ConductoroneSDKTypescript({ security: { bearerAuth: "", oauth: "", }, }); async function run() { const result = await conductoroneSDKTypescript.aiGovernanceSettings.get(); console.log(result); } run(); components: schemas: c1.api.ai_governance.v1.GetAIGovernanceSettingsResponse: description: >- GetAIGovernanceSettingsResponse contains the tenant's AI governance settings. properties: aiGovernanceSettings: oneOf: - $ref: >- #/components/schemas/c1.api.ai_governance.v1.AIGovernanceSettings - type: 'null' title: Get Ai Governance Settings Response type: object x-speakeasy-name-override: GetAIGovernanceSettingsResponse c1.api.ai_governance.v1.AIGovernanceSettings: description: >- AIGovernanceSettings holds the tenant-wide AI governance policy that controls MCP client access, tool approval, classification defaults, audit detail, and automatic tool discovery. There is one settings object per tenant. properties: allowedClientTypes: description: >- MCP client types permitted to connect. An empty list allows all types. items: enum: - MCP_CLIENT_TYPE_UNSPECIFIED - MCP_CLIENT_TYPE_PERSONAL - MCP_CLIENT_TYPE_SHARED - MCP_CLIENT_TYPE_SERVICE - MCP_CLIENT_TYPE_EPHEMERAL type: string x-speakeasy-unknown-values: allow type: - array - 'null' auditVerbosity: description: How much detail is captured in the audit log for MCP tool calls. enum: - AUDIT_VERBOSITY_UNSPECIFIED - AUDIT_VERBOSITY_MINIMAL - AUDIT_VERBOSITY_STANDARD - AUDIT_VERBOSITY_FULL type: string x-speakeasy-unknown-values: allow autoDiscoveryEnabled: description: >- When true, C1 periodically re-discovers tools from registered MCP servers on the discovery_interval schedule. type: boolean c1awAutospillDisabled: deprecated: true description: |- Deprecated. Set QUOTA_REF_TENANT_C1AW_AUTOSPILL_THRESHOLD_KB to 0 to disable C1AW autospill. type: boolean c1awAutospillThresholdBytes: deprecated: true description: |- Deprecated. C1AW autospill is configured with QUOTA_REF_TENANT_C1AW_AUTOSPILL_THRESHOLD_KB. format: uint32 type: integer codeModeConcurrency: description: |- Number of pre-warmed Lambda instances for the per-tenant code-mode function. 0 (default) leaves the Lambda cold-started on first call; > 0 keeps that many execution environments warm via AWS Lambda provisioned concurrency, redeploying the function on change. format: int32 type: integer createdAt: format: date-time type: - string - 'null' defaultClientLifecycle: oneOf: - $ref: >- #/components/schemas/c1.api.ai_governance.v1.MCPClientLifecycleConfig - type: 'null' defaultToolClassification: description: >- Classification assigned to newly discovered tools that do not declare their own classification (for example, read, write, or destructive). enum: - TOOL_CLASSIFICATION_UNSPECIFIED - TOOL_CLASSIFICATION_READ - TOOL_CLASSIFICATION_WRITE - TOOL_CLASSIFICATION_DESTRUCTIVE - TOOL_CLASSIFICATION_SENSITIVE - TOOL_CLASSIFICATION_DANGEROUS type: string x-speakeasy-unknown-values: allow discoveryInterval: format: duration type: - string - 'null' enabled: deprecated: true description: Legacy master switch. type: boolean preferCodeModeOverDirectTools: description: >- When true, the MCP server hides direct tool listings from capable clients whenever the code-mode entrypoints (describe + execute) are registered, so agents discover and invoke MCP tools through TypeScript code mode instead of direct tool calls. A small allowlist of high-traffic direct tools remains exposed. Incapable clients (e.g. SERVICE, EPHEMERAL) see the normal tool set regardless. Defaults to false. type: boolean requireToolApproval: description: >- When true, newly discovered tools start in a pending state and must be approved by an admin before they can be granted or invoked. type: boolean surfaceRequestableTools: description: |- When true, MCP discovery surfaces tools the caller could request (no active grant, but reachable through a request catalog) alongside granted tools — both on the classic tools/list path and inside the code-mode describe entrypoint. Invoking such a tool opens (or reuses) an access-request ticket and returns a request_created envelope instead of executing. Defaults to true. type: boolean updatedAt: format: date-time type: - string - 'null' title: Ai Governance Settings type: object x-speakeasy-name-override: AIGovernanceSettings c1.api.ai_governance.v1.MCPClientLifecycleConfig: description: |- MCPClientLifecycleConfig controls how long inactive MCP clients remain visible, when their access is closed, and when their records are removed. Durations are measured from the client's last activity. Any duration left at zero disables that transition. properties: inactivityCloseAfter: format: duration type: - string - 'null' inactivityHideAfter: format: duration type: - string - 'null' retentionDeleteAfter: format: duration type: - string - 'null' title: Mcp Client Lifecycle Config type: object x-speakeasy-name-override: MCPClientLifecycleConfig securitySchemes: bearerAuth: scheme: bearer type: http oauth: description: >- This API uses OAuth2 with the Client Credential flow. Client Credentials must be sent in the BODY, not the headers. For an example of how to implement this, refer to the [c1TokenSource.Token()](https://github.com/ConductorOne/conductorone-sdk-go/blob/3375fe7c0126d17e7ec4e711693dee7b791023aa/token_source.go#L101-L187) function. flows: clientCredentials: scopes: {} tokenUrl: /auth/v1/token type: oauth2 ````