> ## Documentation Index > Fetch the complete documentation index at: https://docs.threetone.in/llms.txt > Use this file to discover all available pages before exploring further. # Delete Mcp Server Tool Approval > Remove approval for a specific MCP tool when using per-tool approval mode. ## OpenAPI ````yaml /api-reference/openapi.json delete /v1/convai/mcp-servers/{mcp_server_id}/tool-approvals/{tool_name} openapi: 3.1.0 info: title: Threetone API Documentation description: >- This is the documentation for the Threetone API. You can use this API to use our service programmatically with API keys sent in the x-api-key header. You can create and manage API keys in the dashboard at https://threetone.in/app/developers/api-keys. version: '1.0' servers: - url: https://api.threetone.in description: Production security: [] paths: /v1/convai/mcp-servers/{mcp_server_id}/tool-approvals/{tool_name}: delete: tags: - Agents Platform summary: Delete Mcp Server Tool Approval description: >- Remove approval for a specific MCP tool when using per-tool approval mode. operationId: remove_mcp_server_tool_approval_route parameters: - name: mcp_server_id in: path required: true schema: type: string description: ID of the MCP Server. title: Mcp Server Id description: ID of the MCP Server. - name: tool_name in: path required: true schema: type: string description: Name of the MCP tool to remove approval for. title: Tool Name description: Name of the MCP tool to remove approval for. - name: x-api-key in: header required: false schema: anyOf: - type: string - type: 'null' description: >- Your API key for programmatic access. Send it in the x-api-key header; you can create and manage keys from the Developers page. title: X-Api-Key description: >- Your API key for programmatic access. Send it in the x-api-key header; you can create and manage keys from the Developers page. responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/MCPServerResponseModel' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: MCPServerResponseModel: properties: id: type: string title: Id config: $ref: '#/components/schemas/MCPServerConfig' access_info: anyOf: - $ref: '#/components/schemas/ResourceAccessInfo' - type: 'null' description: The access information of the MCP Server dependent_agents: items: oneOf: - $ref: '#/components/schemas/DependentAvailableAgentIdentifier' - $ref: '#/components/schemas/DependentUnknownAgentIdentifier' discriminator: propertyName: type mapping: available: $ref: '#/components/schemas/DependentAvailableAgentIdentifier' unknown: $ref: '#/components/schemas/DependentUnknownAgentIdentifier' type: array title: Dependent Agents description: List of agents that depend on this MCP Server. metadata: $ref: '#/components/schemas/MCPServerMetadataResponseModel' description: The metadata of the MCP Server type: object required: - id - config - metadata title: MCPServerResponseModel description: Response model representing an MCP Server configuration. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError MCPServerConfig: properties: approval_policy: $ref: '#/components/schemas/MCPApprovalPolicy' default: require_approval_all tool_approval_hashes: items: $ref: '#/components/schemas/MCPToolApprovalHash' type: array title: Tool Approval Hashes description: >- List of tool approval hashes for per-tool approval when approval_policy is REQUIRE_APPROVAL_PER_TOOL transport: $ref: '#/components/schemas/MCPServerTransport' description: The transport type used to connect to the MCP server default: SSE url: anyOf: - type: string - $ref: '#/components/schemas/ConvAISecretLocator' title: Url description: >- The URL of the MCP server, if this contains a secret please store as a workspace secret, otherwise store as a plain string. Must use https secret_token: anyOf: - $ref: '#/components/schemas/ConvAISecretLocator' - $ref: '#/components/schemas/ConvAIUserSecretDBModel' - type: 'null' title: Secret Token description: >- The secret token (Authorization header) stored as a workspace secret or in-place secret request_headers: additionalProperties: anyOf: - type: string - $ref: '#/components/schemas/ConvAISecretLocator' - $ref: '#/components/schemas/ConvAIDynamicVariable' - $ref: '#/components/schemas/ConvAIEnvVarLocator' type: object title: Request Headers description: The headers included in the request request_meta: additionalProperties: anyOf: - type: string - type: integer - type: number - type: boolean - $ref: '#/components/schemas/ConvAISecretLocator' - $ref: '#/components/schemas/ConvAIDynamicVariable' - $ref: '#/components/schemas/ConvAIEnvVarLocator' type: object title: Request Meta description: >- Entries sent in the MCP `_meta` field of tools/call requests. Values may be JSON scalars, or references to a workspace secret, dynamic variable, or environment variable resolved per call. auth_connection: anyOf: - $ref: '#/components/schemas/AuthConnectionLocator' - $ref: '#/components/schemas/EnvironmentAuthConnectionLocator' - type: 'null' title: Auth Connection description: >- Optional auth connection to use for authentication with this MCP server name: type: string title: Name description: type: string title: Description default: '' pre_tool_speech: $ref: '#/components/schemas/PreToolSpeechMode' description: >- Controls whether the agent speaks before this tool is called. 'auto' (default) decides based on recent tool latency, 'force' always asks the agent to speak, 'off' fully opts out regardless of latency. Applies to every tool from this MCP server unless overridden per tool. default: auto interruption_mode: $ref: '#/components/schemas/ToolInterruptionMode' description: >- Controls whether the user can interrupt the agent around this tool call. 'allow' (default) lets the user interrupt at any time, 'disable_during_tool' suppresses interruptions only while the tool is running, 'disable_during_tool_and_turn' suppresses interruptions while the tool runs and for the agent response that follows it. Applies to every tool from this MCP server unless overridden per tool. default: allow tool_call_sound: anyOf: - $ref: '#/components/schemas/ToolCallSoundType' - type: 'null' description: >- Predefined tool call sound type to play during tool execution for all tools from this MCP server tool_call_sound_behavior: $ref: '#/components/schemas/ToolCallSoundBehavior' description: >- Determines when the tool call sound should play for all tools from this MCP server default: auto execution_mode: $ref: '#/components/schemas/ToolExecutionMode' description: >- Determines when and how all tools from this MCP server execute: 'immediate' executes the tool right away when requested by the LLM, 'post_tool_speech' waits for the agent to finish speaking before executing, 'async' runs the tool in the background without blocking - best for long-running operations. default: immediate response_timeout_secs: type: integer maximum: 300 minimum: 5 title: Response Timeout Secs description: >- The maximum time in seconds to wait for each MCP tool call to complete. Must be between 5 and 300 seconds (inclusive). default: 30 tool_config_overrides: items: $ref: '#/components/schemas/MCPToolConfigOverride' type: array title: Tool Config Overrides description: >- List of per-tool configuration overrides that override the server-level defaults for specific tools disable_compression: type: boolean title: Disable Compression description: >- Whether to disable HTTP compression for this MCP server. Enable this if the server does not support compressed responses. default: false type: object required: - url - name title: MCPServerConfig ResourceAccessInfo: properties: is_creator: type: boolean title: Is Creator description: Whether the user making the request is the creator of the agent creator_name: type: string title: Creator Name description: Name of the agent's creator creator_email: type: string title: Creator Email description: Email of the agent's creator role: type: string enum: - admin - editor - commenter - viewer title: Role description: The role of the user making the request anonymous_access_level_override: anyOf: - type: string enum: - admin - editor - commenter - viewer - type: 'null' title: Anonymous Access Level Override description: >- The access level for anonymous users. If None, the resource is not shared publicly. access_source: anyOf: - type: string enum: - creator - explicit - workspace_admin - workspace_default - type: 'null' title: Access Source description: >- Why the requesting user has access to this resource. 'creator' = caller is the owner. 'explicit' = caller (or one of their workspace groups) is listed in role_to_group_ids beyond the workspace-wide everyone group. 'workspace_default' = the workspace-wide everyone group is listed in role_to_group_ids (every non-anon workspace member, including admins, sees this resource). 'workspace_admin' = caller is a workspace admin and the admin seat is the *only* path to access; reserved for docs nobody else can see. Lets the UI disclose why an admin-bypass viewer sees a doc that wasn't explicitly shared with them. type: object required: - is_creator - creator_name - creator_email - role title: ResourceAccessInfo example: access_source: creator creator_email: john.doe@example.com creator_name: John Doe is_creator: true role: admin DependentAvailableAgentIdentifier: properties: referenced_resource_ids: items: type: string type: array title: Referenced Resource Ids description: >- If the agent is a transitive dependent, contains IDs of the resources that the agent depends on directly. id: type: string title: Id name: type: string title: Name type: type: string const: available title: Type default: available created_at_unix_secs: type: integer title: Created At Unix Secs access_level: type: string enum: - admin - editor - commenter - viewer title: Access Level type: object required: - id - name - created_at_unix_secs - access_level title: DependentAvailableAgentIdentifier DependentUnknownAgentIdentifier: properties: referenced_resource_ids: items: type: string type: array title: Referenced Resource Ids description: >- If the agent is a transitive dependent, contains IDs of the resources that the agent depends on directly. id: type: string title: Id type: type: string const: unknown title: Type default: unknown type: object required: - id title: DependentUnknownAgentIdentifier description: |- A model that represents an agent dependent on a knowledge base/tools to which the user has no direct access. MCPServerMetadataResponseModel: properties: created_at: type: integer title: Created At owner_user_id: anyOf: - type: string - type: 'null' title: Owner User Id type: object required: - created_at title: MCPServerMetadataResponseModel ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError MCPApprovalPolicy: type: string enum: - auto_approve_all - require_approval_all - require_approval_per_tool title: MCPApprovalPolicy description: Defines the MCP server-level approval policy for tool execution. default: require_approval_all MCPToolApprovalHash: properties: tool_name: type: string title: Tool Name description: The name of the MCP tool tool_hash: type: string title: Tool Hash description: SHA256 hash of the tool's parameters and description approval_policy: $ref: '#/components/schemas/MCPToolApprovalPolicy' description: The approval policy for this tool default: requires_approval type: object required: - tool_name - tool_hash title: MCPToolApprovalHash description: Model for storing tool approval hashes for per-tool approval. MCPServerTransport: type: string enum: - SSE - STREAMABLE_HTTP title: MCPServerTransport description: Supported MCP server transport types. default: SSE ConvAISecretLocator: properties: secret_id: type: string title: Secret Id type: object required: - secret_id title: ConvAISecretLocator description: Used to reference a secret from the agent's secret store. ConvAIUserSecretDBModel: properties: id: type: string title: Id name: type: string title: Name encrypted_value: type: string title: Encrypted Value nonce: type: string title: Nonce type: object required: - id - name - encrypted_value - nonce title: ConvAIUserSecretDBModel description: >- User-specific secret model that are not shared with other users in a workspace. ConvAIDynamicVariable: properties: variable_name: type: string title: Variable Name type: object required: - variable_name title: ConvAIDynamicVariable description: Used to reference a dynamic variable. ConvAIEnvVarLocator: properties: env_var_label: type: string title: Env Var Label type: object required: - env_var_label title: ConvAIEnvVarLocator description: Used to reference an environment variable by label. AuthConnectionLocator: properties: auth_connection_id: type: string title: Auth Connection Id type: object required: - auth_connection_id title: AuthConnectionLocator description: >- Used to reference an auth connection from the workspace's auth connection store. EnvironmentAuthConnectionLocator: properties: env_var_label: type: string title: Env Var Label type: object required: - env_var_label title: EnvironmentAuthConnectionLocator description: |- References an environment variable of type 'auth_connection' by label. At runtime, resolves to the auth connection for the current environment, falling back to the default environment. PreToolSpeechMode: type: string enum: - auto - force - 'off' title: PreToolSpeechMode ToolInterruptionMode: type: string enum: - allow - disable_during_tool - disable_during_tool_and_turn title: ToolInterruptionMode default: allow ToolCallSoundType: type: string enum: - typing - elevator1 - elevator2 - elevator3 - elevator4 title: ToolCallSoundType description: Predefined tool call sound types. ToolCallSoundBehavior: type: string enum: - auto - always title: ToolCallSoundBehavior description: Determines how the tool call sound should be played. ToolExecutionMode: type: string enum: - immediate - post_tool_speech - async title: ToolExecutionMode MCPToolConfigOverride: properties: tool_name: type: string title: Tool Name description: The name of the MCP tool pre_tool_speech: anyOf: - $ref: '#/components/schemas/PreToolSpeechMode' - type: 'null' description: >- If set, overrides the server's pre_tool_speech setting for this tool. interruption_mode: anyOf: - $ref: '#/components/schemas/ToolInterruptionMode' - type: 'null' description: >- If set, overrides the server's interruption_mode setting for this tool. tool_call_sound: anyOf: - $ref: '#/components/schemas/ToolCallSoundType' - type: string const: 'off' - type: 'null' title: Tool Call Sound description: >- Overrides the server's tool_call_sound setting for this tool. A sound name plays that sound; 'off' overrides to no sound (silence); null means do not override (inherit the server default). tool_call_sound_behavior: anyOf: - $ref: '#/components/schemas/ToolCallSoundBehavior' - type: 'null' description: >- If set, overrides the server's tool_call_sound_behavior setting for this tool execution_mode: anyOf: - $ref: '#/components/schemas/ToolExecutionMode' - type: 'null' description: If set, overrides the server's execution_mode setting for this tool response_timeout_secs: anyOf: - type: integer maximum: 300 minimum: 5 - type: 'null' title: Response Timeout Secs description: >- If set, overrides the server's response timeout for this MCP tool (seconds). assignments: items: $ref: '#/components/schemas/DynamicVariableAssignment' type: array title: Assignments description: Dynamic variable assignments for this MCP tool input_overrides: anyOf: - additionalProperties: oneOf: - $ref: '#/components/schemas/ConstantSchemaOverride' - $ref: '#/components/schemas/DynamicVariableSchemaOverride' - $ref: '#/components/schemas/LLMSchemaOverride' - $ref: '#/components/schemas/OmitSchemaOverride' discriminator: propertyName: source mapping: constant: $ref: '#/components/schemas/ConstantSchemaOverride' dynamic_variable: $ref: '#/components/schemas/DynamicVariableSchemaOverride' llm: $ref: '#/components/schemas/LLMSchemaOverride' omit: $ref: '#/components/schemas/OmitSchemaOverride' type: object - type: 'null' title: Input Overrides description: Mapping of json path to input override configuration response_mocks: anyOf: - items: $ref: '#/components/schemas/ToolResponseMockConfig' type: array - type: 'null' title: Response Mocks description: >- Mock responses with optional parameter conditions. Evaluated top-to-bottom; first match wins. type: object required: - tool_name title: MCPToolConfigOverride MCPToolApprovalPolicy: type: string enum: - auto_approved - requires_approval title: MCPToolApprovalPolicy description: Defines the tool-level approval policy. default: requires_approval DynamicVariableAssignment: properties: source: type: string const: response title: Source description: >- The source to extract the value from. Currently only 'response' is supported. default: response dynamic_variable: type: string title: Dynamic Variable description: The name of the dynamic variable to assign the extracted value to value_path: type: string title: Value Path description: >- Dot notation path to extract the value from the source (e.g., 'user.name' or 'data.0.id') sanitize: type: boolean title: Sanitize description: >- If true, this assignment's value will be removed from the tool response before sending to the LLM and transcript, but still processed for variable assignment. default: false preserve_native_type: type: boolean title: Preserve Native Type description: >- If true, non-scalar values (lists, objects) extracted from the tool response are stored as their native type instead of being stringified to JSON. Enable this to use extracted arrays directly as list dynamic variables. default: false additionalProperties: false type: object required: - dynamic_variable - value_path title: DynamicVariableAssignment description: >- Configuration for extracting values from tool responses and assigning them to dynamic variables. example: dynamic_variable: user_name preserve_native_type: false sanitize: false source: response value_path: user.name ConstantSchemaOverride: properties: source: type: string const: constant title: Source default: constant constant_value: anyOf: - type: string - type: integer - type: number - type: boolean - items: {} type: array - additionalProperties: true type: object - type: 'null' title: Constant Value description: The constant value to use type: object required: - constant_value title: ConstantSchemaOverride DynamicVariableSchemaOverride: properties: source: type: string const: dynamic_variable title: Source default: dynamic_variable dynamic_variable: type: string minLength: 1 title: Dynamic Variable description: The name of the dynamic variable to use type: object required: - dynamic_variable title: DynamicVariableSchemaOverride LLMSchemaOverride: properties: source: type: string const: llm title: Source default: llm prompt: anyOf: - type: string - type: 'null' title: Prompt description: >- Prompt override for the LLM. If not provided, the original schema description is used. type: object title: LLMSchemaOverride OmitSchemaOverride: properties: source: type: string const: omit title: Source default: omit type: object title: OmitSchemaOverride ToolResponseMockConfig: properties: parameter_conditions: items: $ref: '#/components/schemas/UnitTestToolCallParameter' type: array title: Parameter Conditions description: If the list is empty, the mock will always activate. mock_result: type: string title: Mock Result description: The return value the LLM sees when this mock is active. is_error: type: boolean title: Is Error description: >- If true, the mock result is surfaced to the LLM as a tool error rather than a successful result. default: false type: object required: - mock_result title: ToolResponseMockConfig UnitTestToolCallParameter: properties: eval: oneOf: - $ref: '#/components/schemas/LLMParameterEvaluationStrategy' - $ref: '#/components/schemas/RegexParameterEvaluationStrategy' - $ref: '#/components/schemas/ExactParameterEvaluationStrategy' - $ref: '#/components/schemas/MatchAnythingParameterEvaluationStrategy' title: Eval discriminator: propertyName: type mapping: anything: $ref: '#/components/schemas/MatchAnythingParameterEvaluationStrategy' exact: $ref: '#/components/schemas/ExactParameterEvaluationStrategy' llm: $ref: '#/components/schemas/LLMParameterEvaluationStrategy' regex: $ref: '#/components/schemas/RegexParameterEvaluationStrategy' path: type: string title: Path type: object required: - eval - path title: UnitTestToolCallParameter LLMParameterEvaluationStrategy: properties: type: type: string const: llm title: Type description: type: string title: Description description: A description of the evaluation strategy to use for the test. type: object required: - type - description title: LLMParameterEvaluationStrategy RegexParameterEvaluationStrategy: properties: type: type: string const: regex title: Type pattern: type: string title: Pattern description: A regex pattern to match the agent's response against. type: object required: - type - pattern title: RegexParameterEvaluationStrategy ExactParameterEvaluationStrategy: properties: type: type: string const: exact title: Type expected_value: type: string title: Expected Value description: The exact string value that the parameter must match. type: object required: - type - expected_value title: ExactParameterEvaluationStrategy MatchAnythingParameterEvaluationStrategy: properties: type: type: string const: anything title: Type type: object required: - type title: MatchAnythingParameterEvaluationStrategy ````