> ## Documentation Index > Fetch the complete documentation index at: https://docs.orq.ai/llms.txt > Use this file to discover all available pages before exploring further. # Update an MCP gateway > Updates mutable fields of an existing MCP gateway. Omitted optional fields keep their current values. **Related guide**: MCP gateways guide. See the [MCP gateways guide](/ai-gateway/mcp-portal/mcp-gateways) for a walkthrough with examples. ## OpenAPI ````yaml patch /v2/mcp-gateways/{id} openapi: 3.1.0 info: title: orq.ai API version: '2.0' description: orq.ai API documentation servers: - url: https://my.orq.ai security: - ApiKey: [] tags: - name: Chunking description: Split text into smaller chunks for retrieval and generation workflows. - name: File Systems description: >- Create and manage persistent file systems that agents and MCP clients read from and write to. - name: Knowledge Bases description: Create and manage knowledge bases used by agents and retrieval workflows. - name: Memory Stores description: Create and manage memory stores, memories, and memory documents. - name: Evals description: Run an evaluator against a conversation and its result - name: Logs description: >- OpenTelemetry log query API. Search, filter, aggregate, and facet log records ingested via OTLP. - name: Reporting description: >- GenAI reporting API over canonical analytics rollups. Accepts a metric name, time range, grain, group-by, and filters; returns a typed time series and optional totals. - name: Traces description: >- Query and inspect ingested trace data: search trace summaries, aggregate metrics, and read individual traces and their spans. - description: List models available through the AI Router. name: Models - name: Policies - name: Alerts description: >- Alerts evaluate a Reporting API metric on a fixed interval and fire notifications through notifiers when the value breaches a threshold. Each breach opens a trigger that tracks the incident until the value recovers. - name: Annotation Queues description: Annotation queues collect spans for human review. - name: API keys description: >- API keys authenticate programmatic access to the workspace. They expose opaque tokens, per-domain access grants, and budget and rate-limit constraints. - name: Audit Logs description: Audit logs record workspace entity changes and access-relevant events. - name: Budgets description: >- Budgets govern spend, token usage, and request rate across six scopes: workspace, project, identity, API key, provider, and model. Every applicable budget is enforced, and the most restrictive limit applies per dimension. - name: Files description: File upload and retrieval operations. - name: Guardrail Rules description: >- Guardrail Rules conditionally enforce evaluators and plugins for AI Gateway traffic. Rules may be scoped to a project or the whole workspace. - name: Hub description: Hub items are reusable templates available to a workspace. - name: Identities description: >- Identities represent end users from your system for usage and engagement tracking. - name: Management keys description: >- Management keys are workspace-scoped credentials that authenticate programmatic access to workspace administration surfaces (API keys, budgets). Unlike project-scoped API keys, a management key always operates at the workspace level. - name: MCP Gateway description: >- Register upstream MCP servers, discover and sync their tools, and assemble gateways that expose a curated tool surface to MCP clients. - name: Model Catalog description: >- Browse the orq.ai model catalog: every model orq offers, across every provider, with pricing, capabilities and benchmark data. List endpoints only return models that are not deprecated. This API is public, requires no authentication, and is rate limited to 120 requests per minute per IP. Responses carry a 5-minute cache-control max-age. - name: Notifiers description: Notifier destinations used to send delivery and workflow notifications. - name: Projects description: Projects organize resources within a workspace - name: Routing Rules description: >- Routing Rules conditionally select models and enforce request plugins for AI Gateway traffic. Rules are evaluated by ascending priority and may be scoped to a project or the whole workspace. - name: Threads description: Threads group related trace invocations and their aggregate usage - name: Skills description: >- Skills are modular instructions you can use to codify processes and conventions - name: Smart Routers description: >- Create and manage workspace Smart Routers. A Smart Router selects a model from an eligible pool for each request according to a quality, balanced, or cost profile. - name: Webhooks description: >- Create and manage webhooks that deliver workspace events to external HTTPS endpoints. - name: Workspaces description: >- A workspace is the tenant. Create is called from a user session during onboarding; Get, List, and Update are the public management surface. - name: Workspace Security description: >- Workspace-level domain verification and IP allowlist controls. These operations are restricted to workspace administrators. - name: Workspace Settings description: >- Workspace-level settings managed with a workspace credential. A workspace is the tenant, so these settings are a singleton — there is nothing to create or delete, only read and update. - name: Responses - description: Run agents on a cron cadence. Minimum firing interval is 1 hour. name: Agent Schedules - name: Embeddings - name: Telemetry description: >- Unified query envelope for traces, metrics, and logs. One request shape, one filter dialect, and one response shape per source, validated by a per-source registry. - description: Beta. Run typed classification questions against a classify model. name: Classify - description: Search Gateway with managed credits or BYOK. name: Web Search externalDocs: url: https://docs.orq.ai description: orq.ai Documentation paths: /v2/mcp-gateways/{id}: patch: tags: - MCP Gateway summary: Update an MCP gateway description: >- Updates mutable fields of an existing MCP gateway. Omitted optional fields keep their current values. operationId: McpGatewayUpdate parameters: - name: id in: path description: Unique identifier of the MCP gateway. required: true schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/UpdateMcpGatewayRequest' required: true responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/UpdateMcpGatewayResponse' x-code-samples: - lang: curl label: Core - Narrow the tools a gateway exposes source: | curl --request PATCH \ --url 'https://my.orq.ai/v2/mcp-gateways/01JQ0M8W4T5YB2Q7N1F6K3PZRC' \ --header "Authorization: Bearer $ORQ_API_KEY" \ --header 'Content-Type: application/json' \ --data '{ "server_links": [ { "mcp_server_id": "01JQ0K5R8N2ZC7X4M9T3V6HWBD", "alias": "github", "enabled": true, "tool_exposure": { "mode": "MCP_TOOL_EXPOSURE_MODE_SELECTED", "tool_ids": [ "01JQ0KA2M7VD9E4R6T8Y1U3XSB", "01JQ0KB5P9WF2G7H4J6K8L1NQD" ] } } ] }' - lang: curl label: Core - Disable a gateway source: | curl --request PATCH \ --url 'https://my.orq.ai/v2/mcp-gateways/01JQ0M8W4T5YB2Q7N1F6K3PZRC' \ --header "Authorization: Bearer $ORQ_API_KEY" \ --header 'Content-Type: application/json' \ --data '{ "status": "MCP_GATEWAY_STATUS_DISABLED" }' - lang: python label: Python - Narrow the tools a gateway exposes source: > import os from orq_ai_sdk import Orq client = Orq(api_key=os.environ["ORQ_API_KEY"]) # tool_ids come from McpTool.id. A tool renamed upstream gets a new id # on the next sync, which drops it from this allowlist. result = client.mcp_gateways.update( id="01JQ0M8W4T5YB2Q7N1F6K3PZRC", server_links=[ { "mcp_server_id": "01JQ0K5R8N2ZC7X4M9T3V6HWBD", "alias": "github", "enabled": True, "tool_exposure": { "mode": "MCP_TOOL_EXPOSURE_MODE_SELECTED", "tool_ids": [ "01JQ0KA2M7VD9E4R6T8Y1U3XSB", "01JQ0KB5P9WF2G7H4J6K8L1NQD", ], }, }, ], ) print(result.mcp_gateway.exposed_tools_count) - lang: typescript label: Node.js - Narrow the tools a gateway exposes source: > import { Orq } from '@orq-ai/node'; const client = new Orq({ apiKey: process.env.ORQ_API_KEY, }); // toolIds come from McpTool.id. A tool renamed upstream gets a new id // on the next sync, which drops it from this allowlist. const result = await client.mcpGateways.update({ id: '01JQ0M8W4T5YB2Q7N1F6K3PZRC', serverLinks: [ { mcpServerId: '01JQ0K5R8N2ZC7X4M9T3V6HWBD', alias: 'github', enabled: true, toolExposure: { mode: 'MCP_TOOL_EXPOSURE_MODE_SELECTED', toolIds: [ '01JQ0KA2M7VD9E4R6T8Y1U3XSB', '01JQ0KB5P9WF2G7H4J6K8L1NQD', ], }, }, ], }); console.log(result.mcpGateway.exposedToolsCount); components: schemas: UpdateMcpGatewayRequest: required: [] type: object properties: key: type: string description: >- Rejected with INVALID_ARGUMENT: the key backs the gateway's public MCP URL and is immutable after creation. Retained so callers get an error rather than a silently ignored field. display_name: type: string description: Human readable name shown in the workspace. description: type: string description: Free-form note about what this gateway is for. server_links: type: array items: $ref: '#/components/schemas/McpGatewayServerLink' description: >- Replaces the current links. An empty array is treated as no change; use `clear_server_links` to remove them all. tool_naming: $ref: '#/components/schemas/McpToolNaming' description: How upstream tool names are namespaced before they are exposed. status: $ref: '#/components/schemas/McpGatewayStatus' description: >- ACTIVE serves MCP traffic; DISABLED rejects it while keeping the configuration. mode: $ref: '#/components/schemas/McpGatewayMode' description: 'Shape of the tool surface presented to MCP clients: CODE or DIRECT.' sharing: allOf: - $ref: '#/components/schemas/Sharing' description: >- Which projects in the workspace may use this gateway. Defaults to every project. clear_server_links: type: boolean description: >- Set true to remove every link; cannot be combined with `server_links`. plugins: type: array items: $ref: '#/components/schemas/McpGatewayPlugin' description: Plugins run on every tool call this gateway serves. UpdateMcpGatewayResponse: type: object properties: mcp_gateway: $ref: '#/components/schemas/McpGateway' McpGatewayServerLink: required: - mcp_server_id - alias - tool_exposure type: object properties: mcp_server_id: type: string description: Upstream MCP server this gateway aggregates. alias: type: string description: >- Prefix used instead of the server key when namespacing this server's tool names. Must be unique within the gateway. enabled: type: boolean description: Whether this link contributes tools to the gateway. tool_exposure: allOf: - $ref: '#/components/schemas/McpToolExposure' description: Narrows which of the server's tools this gateway exposes. McpToolNaming: type: string enum: - MCP_TOOL_NAMING_UNSPECIFIED - MCP_TOOL_NAMING_PREFIX_WITH_SERVER_KEY - MCP_TOOL_NAMING_PREFIX_ON_COLLISION McpGatewayStatus: type: string enum: - MCP_GATEWAY_STATUS_UNSPECIFIED - MCP_GATEWAY_STATUS_ACTIVE - MCP_GATEWAY_STATUS_DISABLED McpGatewayMode: type: string enum: - MCP_GATEWAY_MODE_UNSPECIFIED - MCP_GATEWAY_MODE_CODE - MCP_GATEWAY_MODE_DIRECT Sharing: type: object properties: all_projects: allOf: - $ref: '#/components/schemas/SharingAllProjects' description: Visible to every project in the workspace. selected: allOf: - $ref: '#/components/schemas/SharingSelectedProjects' description: Visible to the listed projects only. allow_version_pin: type: boolean description: |- Consuming projects may pin a specific version instead of tracking the latest version. allow_fork: type: boolean description: |- Projects may duplicate this entity into a detached project-owned copy. auto_grant_new_projects: type: boolean description: |- New projects created after this sharing config is applied should receive access automatically. description: |- Sharing controls which projects in the workspace may use this entity and what they may do with it. McpGatewayPlugin: type: object properties: id: type: string description: Plugin discriminator. language: type: string entities: type: array items: type: string on_failure: type: string threshold: type: number format: double mask: type: array items: type: string McpGateway: type: object properties: id: type: string description: Unique identifier of the MCP gateway. key: type: string description: >- Lowercase slug of letters, digits, hyphens and underscores, max 64 characters, unique per workspace; backs the gateway's public MCP URL. display_name: type: string description: Human readable name shown in the workspace. description: type: string description: Free-form note about what this gateway is for. server_links: type: array items: $ref: '#/components/schemas/McpGatewayServerLink' description: Upstream servers this gateway aggregates. tool_naming: $ref: '#/components/schemas/McpToolNaming' description: How upstream tool names are namespaced before they are exposed. status: $ref: '#/components/schemas/McpGatewayStatus' description: >- ACTIVE serves MCP traffic; DISABLED rejects it while keeping the configuration. public_url: type: string description: >- Endpoint MCP clients connect to; relative when the deployment has no public base URL configured. created: type: string description: ISO 8601 timestamp of when the gateway was created. updated: type: string description: ISO 8601 timestamp of the most recent change to the gateway. exposed_tools_count: type: integer description: Number of tools currently exposed across all enabled links. format: int32 mode: $ref: '#/components/schemas/McpGatewayMode' description: 'Shape of the tool surface presented to MCP clients: CODE or DIRECT.' sharing: allOf: - $ref: '#/components/schemas/Sharing' description: Which projects in the workspace may use this gateway. plugins: type: array items: $ref: '#/components/schemas/McpGatewayPlugin' description: Plugins run on every tool call this gateway serves. McpToolExposure: required: - mode type: object properties: mode: $ref: '#/components/schemas/McpToolExposureMode' description: 'Selection strategy: ALL, SELECTED or NONE.' read_only: type: boolean description: Keeps only the tools the upstream annotates as read-only. tool_ids: type: array items: type: string description: >- `McpTool.id` values to expose when mode is SELECTED; a tool renamed upstream gets a new id on the next sync. SharingAllProjects: type: object properties: {} SharingSelectedProjects: type: object properties: project_ids: type: array items: type: string description: >- Projects allowed to use the entity. An empty list shares it with no project. McpToolExposureMode: type: string enum: - MCP_TOOL_EXPOSURE_MODE_UNSPECIFIED - MCP_TOOL_EXPOSURE_MODE_ALL - MCP_TOOL_EXPOSURE_MODE_SELECTED - MCP_TOOL_EXPOSURE_MODE_NONE securitySchemes: ApiKey: type: http scheme: bearer bearerFormat: JWT ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.