> ## Documentation Index > Fetch the complete documentation index at: https://bifrost-dev.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Edit MCP client > Updates an existing MCP client's configuration. All fields are optional (PATCH semantics); connection_type, auth_type, connection_string, stdio_config, and oauth_config_id are immutable after creation. Unlike client creation, tool_pricing can be included to set per-tool execution costs since tools are already fetched. For OAuth-based clients, providing oauth_config rotates the stored OAuth configuration in place and flips every bound token to needs_reauth when a field actually changes (see MCPClientUpdateRequest.oauth_config). Optionally provide vk_configs to manage which virtual keys have access to this MCP server and with which tools. When provided, this fully replaces all existing VK assignments in a single atomic transaction. Set disabled: true to shut down the client's connection and workers without removing it. Set disabled: false to reconnect a previously disabled client. ## OpenAPI ````yaml /openapi/openapi.json put /api/mcp/client/{id} openapi: 3.1.0 info: title: Bifrost API description: > Bifrost HTTP Transport API for AI model inference and gateway management. This API provides a unified interface for interacting with multiple AI providers including OpenAI, Anthropic, Bedrock, Gemini, and more through a single API, along with comprehensive management APIs for configuring and monitoring the gateway. ## API Structure ### Unified Inference API (`/v1/*`) The primary API using Bifrost's unified format. Model parameters use the format `provider/model` (e.g., `openai/gpt-4`, `anthropic/claude-3-opus`). ### Async Inference API (`/v1/async/*`) Submit inference requests for asynchronous execution. Returns a job ID immediately and allows polling for results. Supports all inference types except batches, files, and containers. ### Provider Integration APIs Native provider-format APIs for drop-in compatibility: - `/openai/*` - OpenAI-compatible API - `/anthropic/*` - Anthropic-compatible API - `/genai/*` - Google GenAI (Gemini) compatible API - `/bedrock/*` - AWS Bedrock compatible API - `/cohere/*` - Cohere compatible API ### Framework Integration APIs Multi-provider proxy endpoints for AI frameworks: - `/litellm/*` - LiteLLM proxy with all provider formats - `/langchain/*` - LangChain compatible endpoints - `/pydanticai/*` - PydanticAI compatible endpoints ### Management APIs (`/api/*`) APIs for managing and monitoring the Bifrost gateway: - `/api/config` - Configuration management - `/api/providers` - Provider and API key management - `/api/plugins` - Plugin management - `/api/governance/*` - Virtual keys, teams, customers, budgets, rate limits, routing rules, and pricing overrides - `/api/logs` - Log search and analytics - `/api/mcp/*` - MCP (Model Context Protocol) client management - `/api/session/*` - Authentication and session management - `/api/cache/*` - Cache management - `/health` - Health check endpoint ## Fallbacks Requests can include fallback models that will be tried if the primary model fails. version: 1.0.0 contact: name: Contact Us url: https://getmaxim.ai/bifrost license: name: Apache 2.0 url: https://opensource.org/licenses/Apache-2.0 servers: - url: '{baseUrl}' description: Your Bifrost instance variables: baseUrl: default: http://localhost:8080 description: Base URL of your Bifrost instance (e.g. https://bifrost.mycompany.com) security: - BearerAuth: [] - BasicAuth: [] - ApiKeyAuth: [] tags: - name: Models description: Model listing and information - name: Chat Completions description: Chat-based text generation - name: Text Completions description: Text completion generation - name: Responses description: OpenAI Responses API compatible endpoints - name: OCR description: Optical character recognition for documents and images - name: Rerank description: Document reranking by relevance to a query - name: Embeddings description: Text embedding generation - name: Images description: Image generations, editing, and variations - name: Videos description: Video generation and management - name: Audio description: Speech synthesis and transcription - name: Count Tokens description: Token counting utilities - name: Batch description: Batch processing operations - name: Files description: File management operations - name: Containers description: Container management operations - name: Async Jobs description: Asynchronous job submission and retrieval endpoints - name: Realtime description: Realtime WebSocket and WebRTC endpoints - name: OpenAI Integration description: OpenAI-compatible API endpoints (/openai/*) - name: Azure Integration description: Azure OpenAI integration endpoints - name: Anthropic Integration description: Anthropic-compatible API endpoints (/anthropic/*) - name: GenAI Integration description: Google GenAI (Gemini) compatible API endpoints (/genai/*) - name: Bedrock Integration description: AWS Bedrock compatible API endpoints (/bedrock/*) - name: Cohere Integration description: Cohere compatible API endpoints (/cohere/*) - name: LiteLLM Integration description: LiteLLM proxy endpoints with multi-provider support (/litellm/*) - name: LangChain Integration description: LangChain compatible endpoints with multi-provider support (/langchain/*) - name: PydanticAI Integration description: >- PydanticAI compatible endpoints with multi-provider support (/pydanticai/*) - name: Health description: Health check endpoints - name: Configuration description: Configuration management endpoints - name: Session description: Session and authentication endpoints - name: Providers description: Provider management endpoints - name: Plugins description: Plugin management endpoints - name: MCP description: Model Context Protocol endpoints - name: Governance description: Virtual keys, teams, and customers management - name: Routing description: Routing rules and complexity analyzer configuration - name: Logging description: Log search and management endpoints - name: Cache description: Cache management endpoints - name: Vault description: Vault secret management endpoints - name: Skills description: Skills Repository management, marketplace, and download endpoints - name: Audit Logs description: >- CADF-compliant audit log search, export, and signature verification endpoints - name: Webhooks description: Webhook endpoint management and signed async-job delivery history - name: Notifications description: >- Role-targeted dashboard notifications, delivered over the dashboard WebSocket paths: /api/mcp/client/{id}: put: tags: - MCP summary: Edit MCP client description: > Updates an existing MCP client's configuration. All fields are optional (PATCH semantics); connection_type, auth_type, connection_string, stdio_config, and oauth_config_id are immutable after creation. Unlike client creation, tool_pricing can be included to set per-tool execution costs since tools are already fetched. For OAuth-based clients, providing oauth_config rotates the stored OAuth configuration in place and flips every bound token to needs_reauth when a field actually changes (see MCPClientUpdateRequest.oauth_config). Optionally provide vk_configs to manage which virtual keys have access to this MCP server and with which tools. When provided, this fully replaces all existing VK assignments in a single atomic transaction. Set disabled: true to shut down the client's connection and workers without removing it. Set disabled: false to reconnect a previously disabled client. operationId: editMCPClient parameters: - name: id in: path required: true description: MCP client ID schema: type: string requestBody: required: true content: application/json: schema: type: object description: > MCP client configuration for updating an existing client (includes tool_pricing). All fields are optional; omitting a field retains its existing value (PATCH semantics). Immutable fields (connection_type, auth_type, connection_string, stdio_config, oauth_config_id) are not accepted here; they cannot be changed after creation. properties: name: type: string description: Display name for the MCP client is_code_mode_client: type: boolean description: Whether this client is available in code mode is_ping_available: type: boolean description: | Whether the MCP server supports ping for health checks. If true, uses lightweight ping method for health checks. If false, uses listTools method for health checks instead. needs_session_stickiness: type: boolean description: > HTTP-only. Only meaningful for auth_type "oauth", "headers", or "none" — per-user auth types are always per-call regardless of this field. When true, Bifrost holds one persistent upstream connection, reused for every tool call. When false, a fresh connection is dialed per tool call. Cannot be set to false for connection_type "sse" or "stdio" — both are always sticky. tool_sync_interval: type: integer minimum: 0 description: > Per-client tool-list sync interval in minutes. 0 falls back to the global mcp_tool_sync_interval client config. tool_execution_timeout: type: integer minimum: 0 description: > Per-client tool execution timeout in seconds. 0 falls back to the global mcp_tool_execution_timeout client config. headers: type: object additionalProperties: type: string description: > Custom headers to include in requests. Only used when auth_type is "headers". Supports env./vault. references. Values echoed back redacted from a GET response are recognized and preserve the stored value, so a fetch-modify-put round trip is safe. allowed_extra_headers: type: array items: type: string description: > Allowlist of request-level headers callers may forward to this MCP server at execution time. ["*"] => any header may be forwarded [] => no extra headers are forwarded ["header1", "header2"] => only the specified headers oauth_config: $ref: '#/components/schemas/OAuthConfigRequest' description: > Rotates the stored OAuth configuration in place. Only accepted for auth_type "oauth" or "per_user_oauth" (400 otherwise). Any provided field replaces the stored value; no new config row is created and no re-discovery or re-registration runs. Unset fields preserve stored values: client_id/client_secret follow the SecretVar masked-placeholder convention (send back the redacted placeholder from a GET response to keep the stored secret), while empty strings / empty arrays on the remaining fields mean "not provided". When any field actually changes, every token bound to the OAuth config is flipped to needs_reauth regardless of auth mode, shared and per-user sessions alike must re-authenticate. A round trip that resolves to the stored values is a no-op and does not cascade. Rotation cannot run while the client is (or is being) disabled (400); send those as two separate requests. tools_to_execute: type: array items: type: string description: | Include-only list for tools. ["*"] => all tools are included [] => no tools are included ["tool1", "tool2"] => include only the specified tools tools_to_auto_execute: type: array items: type: string description: > List of tools that can be auto-executed without user approval. Must be a subset of tools_to_execute. ["*"] => all executable tools can be auto-executed [] => no tools are auto-executed ["tool1", "tool2"] => only specified tools can be auto-executed tool_pricing: type: object additionalProperties: type: number format: double description: > Per-tool cost in USD for execution. Key is the tool name, value is the cost per execution. Example: {"read_file": 0.001, "write_file": 0.002} Note: Only available when updating an existing client after tools have been fetched. allow_on_all_virtual_keys: type: boolean default: false description: > When true, this MCP client's tools are accessible to all virtual keys without requiring explicit per-key assignment. All tools are allowed by default. If a virtual key has an explicit MCP config for this client, that config takes precedence and overrides this behaviour. per_user_header_keys: type: array items: type: string description: > For `per_user_headers` clients only. Cannot be set to an empty list. Updating this list flips every existing active per-user credential row to `needs_update`; callers will be sent back to the submission form on their next tool call to satisfy the new schema. The retained admin discovery credential is flipped the same way; repair it by calling POST /api/mcp/client/{id}/verify-headers with fresh sample values. token_exchange: type: object required: - audience properties: audience: type: string minLength: 1 description: >- Resource identifier this server is scoped to at the identity provider (e.g. "api://jira-mcp") use_idp_credentials: type: boolean description: > When true, performs the exchange as the SSO login application itself instead of client_id/client_secret below, which are then ignored. Some providers require this: Microsoft Entra ID's on-behalf-of grant only accepts an assertion audienced to the exchanging application, and the SSO login flow always requests a token self-audienced to the SSO application, so a separate exchange application can never receive a usable one. client_id: type: string minLength: 1 description: > The identity-provider application authorized to perform exchanges for this audience — typically a dedicated registration carrying the token-exchange (or on-behalf-of) grant, separate from the SSO login application. Required unless use_idp_credentials is true. Supports env.VAR_NAME and vault.path references. Redacted in API responses. client_secret: type: string description: > Secret for the exchange application; omit for public clients. Ignored when use_idp_credentials is true. Supports env.VAR_NAME and vault.path references. Redacted in API responses. scopes: type: array items: type: string description: > Optional scopes to request on the exchanged token. Include "offline_access" (where the identity provider supports it) so the retained admin discovery credential gets a refresh token and stays self-renewing. authorization_server_url: type: string description: > Overrides the Authorization Server the exchange request is sent to. Only needed when the audience is registered on a different Authorization Server than the one used for SSO login (e.g. Okta's per-resource Custom Authorization Servers). Leave unset to use the deployment's SSO login issuer, which is correct for providers with a single tenant-wide token endpoint (Entra, Auth0). allOf: - if: not: properties: use_idp_credentials: const: true required: - use_idp_credentials then: required: - client_id description: > client_id is required unless use_idp_credentials is true, in which case the exchange uses the SSO login application's own credentials instead. additionalProperties: false description: > For `token_exchange` clients only. Omitted preserves the stored configuration. A redacted `client_id` / `client_secret` round-tripped from a prior GET is resolved back to the stored value rather than overwriting it; any other change re-scopes future exchanges and invalidates cached exchanged tokens for this client. disabled: type: boolean default: false description: > When true, the client's connection, health monitor, and tool syncer are shut down. The client entry is preserved so it can be re-enabled later by sending disabled: false. Disabled clients do not expose tools to inference requests. tls_config: type: object description: | TLS configuration for HTTP and SSE connections. Not applicable to stdio or inprocess connection types. properties: insecure_skip_verify: type: boolean description: > Disable TLS certificate verification. Takes priority over ca_cert_pem when both are set. Use only in development or trusted isolated environments. Not recommended for production. ca_cert_pem: type: string description: > PEM-encoded CA certificate to trust for MCP server connections. Use when the MCP server uses a self-signed or private CA certificate. Supports env.VAR_NAME syntax to read the certificate from an environment variable. vk_configs: type: array items: type: object description: >- Per-virtual-key tool access configuration for an MCP client required: - virtual_key_id - tools_to_execute properties: virtual_key_id: type: string description: ID of the virtual key tools_to_execute: type: array items: type: string description: > Tools this virtual key is allowed to call on this MCP server. ["*"] => all tools allowed ["tool1", "tool2"] => only the specified tools description: > When provided, replaces all virtual key assignments for this MCP client. Each entry specifies a virtual key and the tools it is allowed to call. To remove all VK access, provide an empty array []. Omit this field to leave existing VK assignments unchanged. responses: '200': description: MCP client updated successfully content: application/json: schema: $ref: '#/components/schemas/SuccessResponse' '400': description: Bad request content: application/json: schema: $ref: '#/components/schemas/BifrostError' '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/BifrostError' security: - ManagementBearerAuth: [] components: schemas: OAuthConfigRequest: type: object description: | OAuth configuration for an MCP client. Used both when creating a client (initiates the OAuth flow) and when updating one (rotates the stored OAuth config in place; see MCPClientUpdateRequest.oauth_config). properties: client_id: allOf: - type: object description: > A secret-capable value. Serialized as an object with the resolved `value` plus reference metadata; on input, a bare string is also accepted — plain text, `env.VAR_NAME`, or `vault.path/to/secret` (references resolve at runtime and only the reference is persisted). properties: value: type: string description: Resolved value (redacted in GET responses for secret fields) ref: type: string description: >- Source reference (`env.VAR_NAME` or `vault.path`); empty for plain-text values type: type: string enum: - plain_text - env - vault description: Source type of the value description: > OAuth client ID. Optional if client supports dynamic client registration (RFC 7591). If not provided, the server_url must be set for OAuth discovery and dynamic registration. Supports env./vault. references. client_secret: allOf: - type: object description: > A secret-capable value. Serialized as an object with the resolved `value` plus reference metadata; on input, a bare string is also accepted — plain text, `env.VAR_NAME`, or `vault.path/to/secret` (references resolve at runtime and only the reference is persisted). properties: value: type: string description: Resolved value (redacted in GET responses for secret fields) ref: type: string description: >- Source reference (`env.VAR_NAME` or `vault.path`); empty for plain-text values type: type: string enum: - plain_text - env - vault description: Source type of the value description: > OAuth client secret. Optional for public clients using PKCE or clients obtained via dynamic registration. Supports env./vault. references. authorize_url: type: string description: > OAuth authorization endpoint URL. Optional - will be discovered from server_url if not provided. token_url: type: string description: > OAuth token endpoint URL. Optional - will be discovered from server_url if not provided. registration_url: type: string description: > Dynamic client registration endpoint URL (RFC 7591). Optional - will be discovered from server_url if not provided. scopes: type: array items: type: string description: > OAuth scopes requested. Optional - can be discovered from server_url if not provided. Example: ["read", "write"] resource: type: string description: > Resource indicator (RFC 8707) sent on authorization and token requests. Optional - identifies the protected MCP resource the token is intended for, when the upstream provider supports resource indicators. SuccessResponse: type: object description: Generic success response properties: status: type: string example: success message: type: string example: Operation completed successfully BifrostError: type: object description: Error response from Bifrost properties: event_id: type: string type: type: string is_bifrost_error: type: boolean status_code: type: integer error: $ref: '#/components/schemas/ErrorField' extra_fields: $ref: '#/components/schemas/BifrostErrorExtraFields' ErrorField: type: object properties: type: type: string code: type: string message: type: string param: type: string event_id: type: string BifrostErrorExtraFields: type: object properties: provider: $ref: '#/components/schemas/ModelProvider' model_requested: type: string request_type: type: string ModelProvider: type: string description: AI model provider identifier enum: - openai - azure - anthropic - bedrock - cohere - vertex - vllm - mistral - ollama - groq - sgl - parasail - perplexity - replicate - cerebras - deepseek - gemini - openrouter - elevenlabs - huggingface - nebius - xai - runway - fireworks securitySchemes: BearerAuth: type: http scheme: bearer description: > Bearer token authentication. Use your provider API key or Bifrost authentication token. Virtual keys (prefixed with `sk-bf-`) can also be passed here. BasicAuth: type: http scheme: basic description: | Basic authentication using username and password. ApiKeyAuth: type: apiKey in: header name: x-api-key description: | API key authentication via the `x-api-key` header. Virtual keys (prefixed with `sk-bf-`) can also be passed here. ManagementBearerAuth: type: http scheme: bearer description: > Management API authentication for `/api/*` endpoints. Use the `Authorization` header with `Bearer `. Virtual keys, dashboard/user/session tokens, and `x-api-key` headers are not supported on management APIs. ````