> ## 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. # List MCP servers > Returns a paginated list of MCP servers in the workspace. ## OpenAPI ````yaml get /v2/mcp-servers openapi: 3.1.0 info: title: orq.ai API version: '2.0' description: orq.ai API documentation servers: - url: https://api.orq.ai security: - ApiKey: [] tags: - name: Chunking description: Split text into smaller chunks for retrieval and generation workflows. - 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 - 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: API keys description: >- API keys authenticate programmatic access to the workspace. The unified key model exposes opaque tokens, per-domain access grants, and budget / rate-limit constraints (see ADR 0001 and ADR 0002). - name: Budgets description: >- Budgets govern spend, token usage, and request rate across six scopes: workspace, project, identity, api-key, provider, and model. A budget is hierarchical and defense-in-depth — every applicable budget is a hard gate, and the most restrictive one wins per dimension (see ADR 0007). - name: Documentation description: >- Search the orq.ai documentation. Proxies the workspace's query to the hosted docs search index. - name: Files description: File upload and retrieval operations. - name: Finder description: >- Finder entities back the studio navigation tree, project switcher, and cross-project resource references. - 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: 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: Model Sharing description: >- Model sharing controls which projects a workspace model is available to. Workspace admins configure a model's Sharing (all projects / selected projects); the config ships inline on the models list response, so there is no separate read endpoint. - 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: 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: 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: 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. externalDocs: url: https://docs.orq.ai description: orq.ai Documentation paths: /v2/mcp-servers: get: tags: - MCP Gateway summary: List MCP servers description: Returns a paginated list of MCP servers in the workspace. operationId: McpServerList parameters: - name: limit in: query description: Page size between 1 and 200. Defaults to 25. schema: type: integer format: int32 - name: starting_after in: query description: >- Cursor for the page after the given item id. Mutually exclusive with `ending_before`. schema: type: string - name: ending_before in: query description: >- Cursor for the page before the given item id. Mutually exclusive with `starting_after`. schema: type: string - name: search in: query description: Case-insensitive match against the server key and display name. schema: type: string responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/ListMcpServersResponse' x-code-samples: - lang: curl label: Core - List MCP servers source: | curl --get 'https://api.orq.ai/v2/mcp-servers' \ --header 'Authorization: Bearer $ORQ_API_KEY' \ --data-urlencode 'limit=25' \ --data-urlencode 'search=github' - lang: python label: Python - List MCP servers source: | import os from orq_ai_sdk import Orq client = Orq(api_key=os.environ["ORQ_API_KEY"]) page = client.mcp_servers.list( limit=25, search="github", ) for server in page.data: print(server.key, server.sync_state.tools_total) - lang: typescript label: Node.js - List MCP servers source: | import { Orq } from '@orq-ai/node'; const client = new Orq({ apiKey: process.env.ORQ_API_KEY, }); const page = await client.mcpServers.list({ limit: 25, search: 'github', }); for (const server of page.data) { console.log(server.key, server.syncState.toolsTotal); } components: schemas: ListMcpServersResponse: type: object properties: object: type: string description: Always "list". data: type: array items: $ref: '#/components/schemas/McpServer' description: MCP servers on the current page. has_more: type: boolean description: Whether further items exist beyond this page. McpServer: type: object properties: id: type: string description: Unique identifier of the MCP server. key: type: string description: >- Lowercase slug of letters, digits, hyphens and underscores, max 64 characters, unique per workspace; prefixes this server's tool names in gateways. display_name: type: string description: Human readable name shown in the workspace. description: type: string description: Free-form note about what this server is for. connection: allOf: - $ref: '#/components/schemas/McpConnection' description: How the gateway dials the upstream server. auth: allOf: - $ref: '#/components/schemas/McpAuthConfig' description: >- Credentials the gateway sends upstream; send `type: NONE` explicitly for public servers. default_tool_exposure: allOf: - $ref: '#/components/schemas/McpToolExposure' description: >- Fallback exposure used by any gateway link that does not set its own. sync_state: allOf: - $ref: '#/components/schemas/McpSyncState' description: Result of the last `:sync`; a new server has no tools until synced. tools: type: array items: $ref: '#/components/schemas/McpTool' description: Tool catalog discovered by the last successful `:sync`. created: type: string description: ISO 8601 timestamp of when the server was created. updated: type: string description: ISO 8601 timestamp of the most recent change to the server. sharing: allOf: - $ref: '#/components/schemas/Sharing' description: Which projects in the workspace may use this server. template_variables: readOnly: true type: array items: type: string description: >- Names of `{{variable}}` placeholders found in the connection or auth config; supply values as `discovery_variables` on test, sync and tool calls. x-speakeasy-ignore: true created_by_id: readOnly: true type: string description: Account that created the server. McpConnection: required: - type - url type: object properties: type: $ref: '#/components/schemas/McpConnectionType' description: Transport the gateway uses to dial the upstream server. url: type: string description: Upstream endpoint; must use the http or https scheme. McpAuthConfig: required: - type type: object properties: type: $ref: '#/components/schemas/McpAuthType' description: >- Credential scheme; only NONE and STATIC_HEADERS are accepted by create, update and test. static_headers: type: array items: $ref: '#/components/schemas/McpHeaderSecret' description: >- Headers sent upstream on every request; at least one entry when type is STATIC_HEADERS. oauth: allOf: - $ref: '#/components/schemas/McpOAuthConfig' description: Not settable through these endpoints. 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. McpSyncState: type: object properties: status: $ref: '#/components/schemas/SyncStatus' description: >- Outcome of the last sync; a sync that discovers zero tools still reports SYNCED. tools_total: type: integer description: Tools in the catalog after the last sync. format: int32 tools_added: type: integer description: Tools the last sync discovered for the first time. format: int32 tools_removed: type: integer description: Tools the last sync no longer found upstream and marked MISSING. format: int32 last_synced_at: type: string description: ISO 8601 timestamp of the last sync attempt. errors: type: array items: type: string description: Failures reported by the last sync. McpTool: type: object properties: name: type: string description: Bare tool name as advertised by the upstream server. description: type: string description: Tool description advertised upstream, passed through to MCP clients. input_schema: type: object description: JSON Schema for the tool arguments, as advertised upstream. status: type: string description: >- `ACTIVE`, or `MISSING` when the last sync no longer found the tool upstream. id: readOnly: true type: string description: Assigned once on first discovery and preserved across sync. title: type: string description: Human-readable label advertised upstream, when the server sends one. annotations: allOf: - $ref: '#/components/schemas/McpToolAnnotations' description: Behaviour hints claimed by the upstream server. 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 latest. Enforcement lives with the consuming reference. 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. Enforcement lives with project creation and entity-specific adoption code. description: |- Sharing controls which projects in the workspace may use this entity and what they may do with it. McpConnectionType: type: string enum: - MCP_CONNECTION_TYPE_UNSPECIFIED - MCP_CONNECTION_TYPE_HTTP - MCP_CONNECTION_TYPE_SSE - MCP_CONNECTION_TYPE_STDIO McpAuthType: type: string enum: - MCP_AUTH_TYPE_UNSPECIFIED - MCP_AUTH_TYPE_NONE - MCP_AUTH_TYPE_STATIC_HEADERS - MCP_AUTH_TYPE_OAUTH_CLIENT_CREDENTIALS - MCP_AUTH_TYPE_PER_USER_OAUTH McpHeaderSecret: type: object properties: key: type: string description: Header name sent to the upstream server. value: writeOnly: true type: string description: Header value; accepted on write and never returned. masked_value: type: string description: Redacted preview of `value`, returned in its place. McpOAuthConfig: type: object properties: client_id: type: string description: >- OAuth client identifier presented to the upstream authorization server. client_secret: writeOnly: true type: string description: OAuth client secret; accepted on write and never returned. token_url: type: string description: Token endpoint the gateway calls to mint upstream access tokens. scopes: type: array items: type: string description: Scopes requested when minting upstream access tokens. masked_value: type: string description: Redacted preview of `client_secret`, returned in its place. McpToolExposureMode: type: string enum: - MCP_TOOL_EXPOSURE_MODE_UNSPECIFIED - MCP_TOOL_EXPOSURE_MODE_ALL - MCP_TOOL_EXPOSURE_MODE_SELECTED - MCP_TOOL_EXPOSURE_MODE_NONE SyncStatus: type: string enum: - SYNC_STATUS_UNSPECIFIED - SYNC_STATUS_SYNCED - SYNC_STATUS_FAILED - SYNC_STATUS_PENDING McpToolAnnotations: type: object properties: read_only: type: boolean description: Upstream claims the tool does not modify state. destructive: type: boolean description: Upstream claims the tool can perform destructive updates. idempotent: type: boolean description: >- Upstream claims repeated calls with the same arguments have no extra effect. open_world: type: boolean description: Upstream claims the tool reaches systems outside its own domain. description: Hints claimed by the upstream server; the gateway does not enforce them. 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. securitySchemes: ApiKey: type: http scheme: bearer bearerFormat: JWT ````