> ## Documentation Index > Fetch the complete documentation index at: https://developers.telnyx.com/llms.txt > Use this file to discover all available pages before exploring further. # Retrieve a policy > Returns one policy, in its current version. ## OpenAPI ````yaml /openapi/source/external/agent-gateway/agent-gateway.json get /agent_gateways/{instance_id}/policies/{name} openapi: 3.1.0 info: version: 1.0.0 title: Telnyx API x-latency-category: interactive x-endpoint-cost: light description: >- Agent Gateway authenticates, authorizes, and audits the requests agents send to models, tools, and other agents. Each gateway runs as a dedicated instance on the account's [*Network*](https://developers.telnyx.com/docs/network/overview). This API creates, lists, and deletes instances, and manages the keys, teams, spend logs, MCP servers, APIs, tool permissions, and guardrails on them. Each instance serves an OpenAI-compatible API at its `gateway_url`. servers: - url: https://api.telnyx.com/v2 description: Telnyx API v2 security: - bearerAuth: [] tags: - name: Agent Gateways description: Create, list, retrieve, and delete Agent Gateway instances. - name: Agent Gateway Keys description: Keys on an instance. - name: Agent Gateway Teams description: 'Teams on an instance: shared model lists, budgets, and rate limits.' - name: Agent Gateway Spend Logs description: The requests an instance served, with their cost. - name: Agent Gateway MCP Servers description: MCP servers on an instance, served to agents at one MCP endpoint. - name: Agent Gateway APIs description: REST APIs on an instance, served to agents as tools. - name: Agent Gateway Tool Permissions description: The MCP servers and tools a key or team may use. - name: Agent Gateway Guardrails description: Checks an instance runs on model and tool requests. - name: Agent Gateway Policies description: Named sets of guardrails an instance applies to requests. - name: Agent Gateway Policy Attachments description: Where an instance applies each policy. paths: /agent_gateways/{instance_id}/policies/{name}: get: tags: - Agent Gateway Policies summary: Retrieve a policy description: Returns one policy, in its current version. operationId: RetrieveAgentGatewayPolicy parameters: - name: instance_id in: path required: true description: The Agent Gateway's `id`. schema: type: string format: uuid example: 32ce035d-3165-4031-b1a7-a7c0c259590a - name: name in: path required: true description: The policy's `name`. schema: type: string example: strict responses: '200': description: The policy content: application/json: schema: $ref: '#/components/schemas/AgentGatewayPolicyResponse' example: data: name: strict description: null base: baseline guardrails: add: - no-forbidden remove: [] model: GLM-5.3.* pipeline: null created_at: '2026-11-02T12:58:54.285000Z' updated_at: '2026-11-02T12:58:54.285000Z' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/TelnyxErrors' example: errors: - code: '10009' title: Authentication failed detail: >- The required authentication headers were either invalid or not included in the request. meta: url: https://developers.telnyx.com/docs/overview/errors/10009 '404': description: Not found content: application/json: schema: $ref: '#/components/schemas/TelnyxErrors' example: errors: - code: '10005' title: Resource not found detail: The requested resource or URL could not be found. meta: url: https://developers.telnyx.com/docs/overview/errors/10005 components: schemas: AgentGatewayPolicyResponse: type: object required: - data properties: data: $ref: '#/components/schemas/AgentGatewayPolicy' TelnyxErrors: type: object properties: errors: type: array items: $ref: '#/components/schemas/TelnyxError' AgentGatewayPolicy: type: object description: A named set of guardrails. required: - name - description - base - guardrails - model - pipeline - created_at - updated_at properties: name: type: string pattern: ^[A-Za-z0-9_.-]{1,100}$ description: >- A name, unique on the instance. A request names the policy in its `policies` field. description: anyOf: - type: string - type: 'null' description: What the policy is for. base: anyOf: - type: string - type: 'null' description: >- A policy this one builds on, by name. The policy starts with the base's guardrails. guardrails: $ref: '#/components/schemas/AgentGatewayPolicyGuardrails' model: anyOf: - type: string - type: 'null' description: >- A condition on the model, by name or regular expression. The policy's guardrails run only on requests for a matching model. `null` matches every model. pipeline: anyOf: - $ref: '#/components/schemas/AgentGatewayPolicyPipeline' - type: 'null' description: Ordered steps, in place of the guardrails running independently. created_at: anyOf: - type: string format: date-time - type: 'null' description: >- When the policy's current version was created. An update creates a new version. updated_at: anyOf: - type: string format: date-time - type: 'null' description: When the policy last changed. TelnyxError: type: object properties: code: type: string title: type: string detail: type: string source: type: object properties: pointer: type: string parameter: type: string meta: type: object properties: url: type: string AgentGatewayPolicyGuardrails: type: object description: >- The guardrails a policy adds to its base's, and the ones it removes from them, by name. properties: add: type: array items: type: string default: [] description: Guardrails the policy runs in addition to its base's. remove: type: array items: type: string default: [] description: Guardrails from its base that the policy does not run. AgentGatewayPolicyPipeline: type: object description: >- Ordered steps that run in place of the policy's guardrails running independently. required: - hook - steps properties: hook: type: string enum: - before_request - after_request description: >- `before_request` runs the steps on the request, and `after_request` on the model's response. steps: type: array items: $ref: '#/components/schemas/AgentGatewayPolicyStep' AgentGatewayPolicyStep: type: object description: >- One pipeline step: a guardrail, and what happens when it passes, fails, or errors. required: - guardrail properties: guardrail: type: string pattern: ^[A-Za-z0-9_.-]{1,100}$ description: A guardrail on the instance, by name. on_pass: type: string enum: - next - allow - block - respond default: allow description: >- What happens when the guardrail passes. `next` goes on to the next step, `allow` allows the request, `block` blocks it, and `respond` answers with `message`. on_fail: type: string enum: - next - allow - block - respond default: block description: What happens when the guardrail fails. on_error: anyOf: - type: string enum: - next - allow - block - respond - type: 'null' description: >- What happens when the guardrail errors. Left out, the same as `on_fail`. message: anyOf: - type: string - type: 'null' description: >- The response that replaces the model's when an outcome is `respond`. Required with `respond`. pass_data: type: boolean default: false description: >- `true` hands the step's modified request, such as masked text, to the next step. securitySchemes: bearerAuth: type: http scheme: bearer description: Telnyx API key ````