> ## 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. # Release 4.18 > Release 4.18 upgrades the MCP Gateway, makes Activity the new home for workspace usage, and connects external A2A agents. **MCP Gateway upgrade** v4.18.0 Decide which tools reach agents before they can call them. The **MCP Gateway** now holds back newly discovered tools until they are approved, supports per-user OAuth, creates servers from OpenAPI specifications, and runs **Guardrails** on tool traffic. ![MCP Gateway Toolset tab for a Fireflies server with three tools marked New and hidden, an Expose tooltip on the first one, and the selected tool's JSON schema on the right](https://mintcdn.com/orqai/I3iX4Fs1Wcqb_Q9y/images/mcp_gateway_4_18.webp?fit=max\&auto=format\&n=I3iX4Fs1Wcqb_Q9y\&q=85\&s=b07d1fb16a02c21829f6aef7b0919357) * **New tools need approval**: Syncing an MCP server marks newly discovered tools as New and keeps them off every gateway until they are exposed. A sync summary lists new and removed tools, with one-click expose per gateway. * **[Per-user OAuth](https://docs.orq.ai/ai-gateway/mcp-portal/mcp-servers.md#per-user-oauth)**: Each user connects their own account to an MCP server, and tool calls from **Agents** and **MCP Gateways** use the token of the user who made the call. A user without a connection is asked to connect on first use. * **OpenAPI as an MCP server**: Point the [MCP Portal](https://docs.orq.ai/ai-gateway/mcp-portal/mcp-servers.md) at an OpenAPI specification and each operation becomes a tool, with its schema constraints kept. * **[Guardrails on tool calls](https://docs.orq.ai/ai-gateway/mcp-portal/mcp-gateways.md#guardrails)**: Run a gateway's **Guardrails** on tool arguments before the upstream call, on tool results before they reach the agent, or on both. > [!NOTE] > > Set up a gateway from the [MCP Gateway](https://docs.orq.ai/ai-gateway/mcp-portal/mcp-gateways.md) guide. **Activity** v4.18.0 See how the workspace uses LLMs the moment it opens. **Activity** replaces the old Home dashboard and shows spend, requests, tokens, and caching across models, users, and coding harnesses. ![Activity Overview tab with total spend, requests, token volume, and error rate tiles above hourly charts of usage by model, request volume by model, and token breakdown](https://mintcdn.com/orqai/I3iX4Fs1Wcqb_Q9y/images/activity_4_18.webp?fit=max\&auto=format\&n=I3iX4Fs1Wcqb_Q9y\&q=85\&s=64f9738c46a4171868ec3c22ab401bb6) * **Overview and Explore**: Follow spend and request trends, then break them down by model, user, or harness. * **My activity**: Each member sees their own usage, including requests sent with their own API keys. * **MCP usage**: Track calls across **MCP Gateways** in the same place. > [!NOTE] > > Learn what each view shows in [Activity](https://docs.orq.ai/ai-studio/observability/activity.md). **External agents** v4.18.0 Bring agents built anywhere into **Orq.ai**. Connect an external agent that speaks the A2A protocol, and call it like any other **Agent**. ![Agent Card of a research\_assistant A2A agent at version 1.0.2, listing its JSON-RPC and HTTP+JSON interfaces, streaming support, and three skills starting with Web Scraper](https://mintcdn.com/orqai/I3iX4Fs1Wcqb_Q9y/images/external_agents_4_18.webp?fit=max\&auto=format\&n=I3iX4Fs1Wcqb_Q9y\&q=85\&s=ab0e80503239eb41899513ab036d6454) * **Connect external agents**: Register an A2A agent by its URL and invoke it through the Responses API with `model: "agent/"`, or add it to an **Agent**'s team. * **Built-in safety**: Calls to external agents are checked for unsafe network targets and protected against an agent calling itself without limit. > [!NOTE] > > Connect a first agent with the [external agents](https://docs.orq.ai/ai-gateway/features/agents-gateway.md) guide. **Enterprise: SSO and access control** v4.18.0 * **Custom roles**: Define workspace roles with exactly the permissions a team needs, beyond the preset roles. * **[SCIM provisioning](https://docs.orq.ai/ai-studio/organization/sso.md#scim-provisioning)**: Let the identity provider create members and teams and remove people automatically, instead of inviting them by hand. * **[Enterprise-managed MCP authorization](https://docs.orq.ai/ai-studio/organization/sso.md#cross-app-access)**: **MCP Gateways** call enterprise-managed MCP servers on behalf of each SSO user, with the identity provider deciding who can access which app (ID-JAG). Trusted enterprise identity providers can also sign clients in to a gateway. **New features** v4.18.0 * **[Files](https://docs.orq.ai/ai-studio/ai-engineering/files.md)**: Upload files once and reuse them in model requests, **Knowledge Bases**, batches, and code interpreter tools. Batch files show a ready-to-use Batch API example. * **[Evaluator timeout](https://docs.orq.ai/ai-studio/optimize/evaluators.md)**: Set a timeout from 1 to 120 seconds on an **Evaluator** used as a **Guardrail**. A request can shorten it but not extend it. * **Machine-to-machine access to MCP Gateways**: Services can sign in to a gateway with OAuth client credentials or `private_key_jwt`, and clients such as VS Code connect through client metadata documents. **Improvements** v4.18.0 * **Total cost for filtered [Traces](https://docs.orq.ai/ai-studio/observability/traces.md)**: One total shows the cost of every trace that matches the current time range, filters, and search, not just the loaded page. * **Traces on Playgrounds**: Each **Playground** has its own **Traces** tab. * **Studio navigation**: Pin and reorder tabs, follow breadcrumbs on every page, and collapse the sidebar with a smooth animation. * **Small Budget spend**: Spend below one cent shows in [**Budgets**](https://docs.orq.ai/ai-gateway/budgets.md), with the exact amount on hover. * **[Sonnet 5.5 thinking between tools](https://docs.orq.ai/ai-gateway/features/reasoning.md)**: `thinking: {"type": "between_tools"}` works on Chat Completions and can be saved on an **Agent**. **Deprecations** v4.18.0 * **Prompts**: **Prompts** reach end of life in the coming months. Creating and importing **Prompts** is no longer possible, and existing users are pointed to **Agents**. * **Deployments in new workspaces**: New workspaces no longer show **Deployments** in the sidebar, command bar, or search. **New models** v4.18.0 New additions to the **Model Garden**. Browse details on the [Supported Models](https://docs.orq.ai/ai-gateway/supported-models.md) page. | Provider | Models | | - | - | | **OpenAI** | `gpt-6.1-terra`, and `gpt-image-2.6-flare` and `gpt-image-2.6-sunburst` for image generation | | **Moonshot AI** | `kimi-k3.1-pro`, on Moonshot AI and TensorX | | **Google** | `gemma-4-12b` via Munito | | **Aleph Alpha** | `kolibri-1` via Munito | | **Particle** | `particle-1` | | **OCR** | `lightonocr-2-1b` (LightOn), `ocr-auto` and `ocr-fast` (Munito) | **Bug fixes** v4.18.0 * **Deployments**: Gemini **Deployments** keep `extra_params` tools and `tool_choice`. * **Traces**: Pydantic AI agent spans show their input and usage, the Thread view opens when an input guardrail fires, and **Agent** trace costs include guardrail **Evaluator** costs. * **Settings**: API keys record when they were last used, editing a fired budget alert keeps it firing, and Notifier webhooks with secret headers can be updated. * **Agents and Datasets**: Tool errors show a readable message, moving a **Dataset** to another **Project** persists, and Mustache list variables work in **Experiments**. Released on November 9, 2026. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.