Skip to main content
Glama

update_integration

Update an integration's name, API key, or provider-specific configuration. Key and config changes take effect immediately and may affect dependent providers.

Instructions

Update an integration's name, key, or provider-specific config. Key and config changes take effect immediately and can disrupt dependent providers or live requests.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
slugYesThe slug of the integration to update
nameNoNew human-readable name for the integration
keyNoNew API key for the provider
descriptionNoNew description for the integration
api_versionNoNew API version (for Azure OpenAI)
resource_nameNoNew resource name (for Azure OpenAI)
deployment_nameNoNew deployment name (for Azure OpenAI)
aws_regionNoNew AWS region (for AWS Bedrock)
aws_access_key_idNoNew AWS access key ID (for AWS Bedrock)
aws_secret_access_keyNoNew AWS secret access key (for AWS Bedrock)
vertex_project_idNoNew GCP project ID (for Vertex AI)
vertex_regionNoNew GCP region (for Vertex AI)
custom_hostNoNew custom base URL for the provider

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYesWhether the tool call succeeded and returned structured data
dataNoStructured success payload when ok is true
errorNoStructured error payload when ok is false

Implementation Reference

  • Registration of the 'update_integration' MCP tool via server.tool() call, with handler logic that collects provider-specific configs and calls the service layer.
    // Update integration tool
    server.tool(
    	"update_integration",
    	"Update an integration's name, key, or provider-specific config. Key and config changes take effect immediately and can disrupt dependent providers or live requests.",
    	INTEGRATIONS_TOOL_SCHEMAS.updateIntegration,
    	async (params) => {
    		const configurations: Record<string, unknown> = {};
    
    		// Azure OpenAI configurations
    		if (params.api_version !== undefined)
    			configurations.api_version = params.api_version;
    		if (params.resource_name !== undefined)
    			configurations.resource_name = params.resource_name;
    		if (params.deployment_name !== undefined)
    			configurations.deployment_name = params.deployment_name;
    
    		// AWS Bedrock configurations
    		if (params.aws_region !== undefined)
    			configurations.aws_region = params.aws_region;
    		if (params.aws_access_key_id !== undefined)
    			configurations.aws_access_key_id = params.aws_access_key_id;
    		if (params.aws_secret_access_key !== undefined)
    			configurations.aws_secret_access_key = params.aws_secret_access_key;
    
    		// Vertex AI configurations
    		if (params.vertex_project_id !== undefined)
    			configurations.vertex_project_id = params.vertex_project_id;
    		if (params.vertex_region !== undefined)
    			configurations.vertex_region = params.vertex_region;
    
    		// Custom host
    		if (params.custom_host !== undefined)
    			configurations.custom_host = params.custom_host;
    
    		const result = await service.integrations.updateIntegration(params.slug, {
    			name: params.name,
    			key: params.key,
    			description: params.description,
    			configurations:
    				Object.keys(configurations).length > 0 ? configurations : undefined,
    		});
    
    		return {
    			content: [
    				{
    					type: "text",
    					text: JSON.stringify(
    						{
    							message: `Successfully updated integration "${params.slug}"`,
    							success: result.success,
    						},
    						null,
    						2,
    					),
    				},
    			],
    		};
    	},
    );
  • Zod schema for the update_integration tool input, defining all optional fields: slug (required), name, key, description, and provider-specific config fields (Azure, AWS, Vertex, custom_host).
    updateIntegration: {
    	slug: z.string().describe("The slug of the integration to update"),
    	name: z
    		.string()
    		.optional()
    		.describe("New human-readable name for the integration"),
    	key: z.string().optional().describe("New API key for the provider"),
    	description: z
    		.string()
    		.optional()
    		.describe("New description for the integration"),
    	api_version: z
    		.string()
    		.optional()
    		.describe("New API version (for Azure OpenAI)"),
    	resource_name: z
    		.string()
    		.optional()
    		.describe("New resource name (for Azure OpenAI)"),
    	deployment_name: z
    		.string()
    		.optional()
    		.describe("New deployment name (for Azure OpenAI)"),
    	aws_region: z
    		.string()
    		.optional()
    		.describe("New AWS region (for AWS Bedrock)"),
    	aws_access_key_id: z
    		.string()
    		.optional()
    		.describe("New AWS access key ID (for AWS Bedrock)"),
    	aws_secret_access_key: z
    		.string()
    		.optional()
    		.describe("New AWS secret access key (for AWS Bedrock)"),
    	vertex_project_id: z
    		.string()
    		.optional()
    		.describe("New GCP project ID (for Vertex AI)"),
    	vertex_region: z
    		.string()
    		.optional()
    		.describe("New GCP region (for Vertex AI)"),
    	custom_host: z
    		.string()
    		.optional()
    		.describe("New custom base URL for the provider"),
    },
  • Service-layer handler for update_integration - makes a PUT request to /integrations/{slug} with the provided data and returns success status.
    async updateIntegration(
    	slug: string,
    	data: UpdateIntegrationRequest,
    ): Promise<{ success: boolean }> {
    	await this.put(`/integrations/${this.encodePathSegment(slug)}`, data);
    	return { success: true };
    }
  • TypeScript interface defining the shape of the update request payload sent to the API.
    export interface UpdateIntegrationRequest {
    	name?: string;
    	key?: string;
    	description?: string;
    	configurations?: IntegrationConfigurations;
    }
  • TypeScript interface for provider-specific configurations used in the update request.
    export interface IntegrationConfigurations {
    	// OpenAI / Azure OpenAI specific
    	api_version?: string;
    	resource_name?: string;
    	deployment_name?: string;
    	// AWS Bedrock specific
    	aws_region?: string;
    	aws_access_key_id?: string;
    	aws_secret_access_key?: string;
    	aws_session_token?: string;
    	// Vertex AI specific
    	vertex_project_id?: string;
    	vertex_region?: string;
    	vertex_service_account_json?: string;
    	// Custom base URL
    	custom_host?: string;
    	// Generic key-value for provider-specific configs
    	[key: string]: unknown;
    }
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description warns that 'key and config changes take effect immediately and can disrupt dependent providers or live requests.' Annotations indicate destructiveHint=false, which is not directly contradicted (disruption is not necessarily destructive). No mention of authentication or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences; efficient and front-loaded. However, it could be structured with bullet points for the warning to improve scanability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 13 provider-specific parameters, the description does not explain parameter applicability or required permissions. The output schema exists, so return values are covered. The disruption warning adds useful context, but overall completeness is mediocre.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters. The description adds no new meaning beyond grouping fields. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Update'), resource ('integration'), and specific fields ('name, key, or provider-specific config'). This distinguishes it from sibling tools like create_integration and delete_integration.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives (e.g., update_integration_models, update_integration_workspaces). The warning about disruption is useful but does not address selection criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/s-b-e-n-s-o-n/portkey-admin-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server