> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getbifrost.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Create team (deprecated path)
> Creates a new team.
This path is deprecated and will be removed in the following major release.
Use `/api/governance/teams` instead.
## OpenAPI
````yaml /openapi/openapi.json post /api/teams
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: 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
paths:
/api/teams:
post:
tags:
- Governance
summary: Create team (deprecated path)
description: Creates a new team.
operationId: createTeamLegacy
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/CreateTeamRequest'
responses:
'200':
description: Team created successfully
content:
application/json:
schema:
$ref: '#/components/schemas/TeamResponse'
'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'
deprecated: true
security:
- ManagementBearerAuth: []
components:
schemas:
CreateTeamRequest:
type: object
description: Create team request
required:
- name
properties:
name:
type: string
customer_id:
type: string
budgets:
type: array
description: Budgets to create for this team; reset durations must be unique
items:
$ref: '#/components/schemas/CreateBudgetRequest'
TeamResponse:
type: object
description: Team operation response
properties:
message:
type: string
team:
$ref: '#/components/schemas/Team'
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'
CreateBudgetRequest:
type: object
description: Create budget request
required:
- max_limit
- reset_duration
properties:
max_limit:
type: number
reset_duration:
type: string
reset_config:
type: object
description: >
Window settings the reset duration cannot express. Only valid when
reset_duration is quarterly (`1Q`); the API rejects it on any other
window.
properties:
quarter_start_month:
type: integer
minimum: 1
maximum: 12
description: >
First month of Q1 as 1-12, so a fiscal year opening in April (4)
gives Apr-Jun / Jul-Sep / Oct-Dec / Jan-Mar. Omitted means
January. Quarter boundaries repeat every three months, so only
the value modulo 3 changes the reset dates: January, April, July
and October all reset on calendar quarters and differ only in
which quarter is labelled Q1.
additionalProperties: false
calendar_aligned:
type: boolean
default: false
description: >
When true, usage resets at the start of each calendar period in UTC
instead of on a rolling window from last reset. Only valid with
reset durations that use day, week, month, quarter, or year suffixes
(`d`, `w`, `M`, `Q`, `Y`). For example `1d` resets at midnight UTC;
`1w` at Monday 00:00 UTC; `1M` on the first day of each month; `1Q`
on the first day of the fiscal quarter; `1Y` on January 1. Sub-day
durations (e.g. `1h`) cannot use calendar alignment.
Team:
type: object
description: Team configuration
properties:
id:
type: string
name:
type: string
customer_id:
type: string
customer:
$ref: '#/components/schemas/Customer'
budgets:
type: array
description: Budgets owned by this team
items:
$ref: '#/components/schemas/Budget'
virtual_keys:
type:
- array
- 'null'
description: >
Virtual keys assigned to this team. This field may be omitted or
returned as null in some responses (for example, when a team is
embedded inside a virtual-key response) to avoid nested
`virtual_keys` recursion.
items:
$ref: '#/components/schemas/VirtualKey'
profile:
type: object
additionalProperties: true
config:
type: object
additionalProperties: true
claims:
type: object
additionalProperties: true
config_hash:
type:
- string
- 'null'
created_at:
type: string
format: date-time
updated_at:
type: string
format: date-time
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
Customer:
type: object
description: Customer configuration
properties:
id:
type: string
name:
type: string
budget_id:
type: string
budget:
$ref: '#/components/schemas/Budget'
teams:
type: array
items:
$ref: '#/components/schemas/Team'
virtual_keys:
type:
- array
- 'null'
description: >
Virtual keys owned by this customer. Omitted or returned as null by
the paginated list endpoint (`GET /api/governance/customers` with
`limit`/`offset`/`search`), which reports `virtual_key_count`
instead; use the single-customer endpoint to retrieve the keys
themselves.
items:
$ref: '#/components/schemas/VirtualKey'
virtual_key_count:
type: integer
description: Number of virtual keys owned by this customer. Always populated.
config_hash:
type: string
created_at:
type: string
format: date-time
updated_at:
type: string
format: date-time
Budget:
type: object
description: Budget configuration
required:
- id
- max_limit
- reset_duration
- last_reset
- current_usage
- config_hash
- created_at
- updated_at
properties:
id:
type: string
max_limit:
type: number
description: Maximum budget in dollars
reset_duration:
type: string
description: Reset duration (e.g., "30s", "5m", "1h", "1d", "1w", "1M", "1Q")
reset_config:
type: object
description: >
Window settings the reset duration cannot express. Only valid when
reset_duration is quarterly (`1Q`); the API rejects it on any other
window.
properties:
quarter_start_month:
type: integer
minimum: 1
maximum: 12
description: >
First month of Q1 as 1-12, so a fiscal year opening in April (4)
gives Apr-Jun / Jul-Sep / Oct-Dec / Jan-Mar. Omitted means
January. Quarter boundaries repeat every three months, so only
the value modulo 3 changes the reset dates: January, April, July
and October all reset on calendar quarters and differ only in
which quarter is labelled Q1.
additionalProperties: false
calendar_aligned:
type: boolean
description: >-
When true, resets align to calendar period boundaries in UTC (not
rolling from last reset)
default: false
last_reset:
type: string
format: date-time
current_usage:
type: number
override_amount:
type: number
description: >-
Additional spend added on top of `max_limit` while the override is
active. Omitted when no override is set.
override_mode:
type: string
description: >
How long the override stays active. `cycles` keeps it active for a
finite number of
reset windows; `forever` keeps it active until it is removed.
Omitted when no override is set.
enum:
- cycles
- forever
override_cycles_remaining:
type: integer
description: >
Reset windows the override is still valid for, including the current
one. Positive only
for `cycles` mode; recomputed from the original grant on every
reset, never decremented in place.
override_cycles_total:
type: integer
description: >-
Number of reset windows the current `cycles` override was granted
for. Immutable for the life of the grant.
override_anchor_reset:
type: string
format: date-time
description: >-
Reset-window boundary at which the current `cycles` override was
granted. Immutable for the life of the grant.
team_id:
type: string
description: Team that owns this budget, when the budget is team-scoped
virtual_key_id:
type: string
description: >-
Virtual key that owns this budget, when the budget is
virtual-key-scoped
provider_config_id:
type: integer
description: >-
Provider config that owns this budget, when the budget is
provider-config-scoped
config_hash:
type:
- string
- 'null'
created_at:
type: string
format: date-time
updated_at:
type: string
format: date-time
VirtualKey:
type: object
description: Virtual key configuration
required:
- id
- name
- value
- is_active
- provider_configs
- mcp_configs
- calendar_aligned
- config_hash
- created_at
- updated_at
properties:
id:
type: string
name:
type: string
value:
type: string
description:
type: string
is_active:
type: boolean
expires_at:
type:
- string
- 'null'
format: date-time
description: >-
Expiry timestamp. Requests using this virtual key are rejected once
it passes. Null or absent means the key never expires.
provider_configs:
type: array
items:
$ref: '#/components/schemas/VirtualKeyProviderConfig'
mcp_configs:
type: array
items:
$ref: '#/components/schemas/VirtualKeyMCPConfig'
team_id:
type: string
customer_id:
type: string
rate_limit_id:
type: string
calendar_aligned:
type: boolean
team:
$ref: '#/components/schemas/Team'
customer:
$ref: '#/components/schemas/Customer'
budgets:
type: array
description: Budget quotas assigned directly to this virtual key
items:
$ref: '#/components/schemas/Budget'
rate_limit:
$ref: '#/components/schemas/RateLimit'
config_hash:
type: string
created_by_user_id:
type: string
description: User that created this virtual key, when available
created_at:
type: string
format: date-time
updated_at:
type: string
format: date-time
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
VirtualKeyProviderConfig:
type: object
description: Provider configuration for a virtual key
required:
- id
- virtual_key_id
- provider
- weight
- allowed_models
- blacklisted_models
- allow_all_keys
- keys
properties:
id:
type: integer
virtual_key_id:
type: string
provider:
type: string
weight:
type:
- number
- 'null'
description: >-
Weight for provider load balancing. Null means excluded from
weighted routing.
allowed_models:
type: array
items:
type: string
blacklisted_models:
type: array
items:
type: string
allow_all_keys:
type: boolean
rate_limit_id:
type: string
budgets:
type: array
description: Budget quotas assigned to this provider config
items:
$ref: '#/components/schemas/Budget'
rate_limit:
$ref: '#/components/schemas/RateLimit'
keys:
type:
- array
- 'null'
description: >
Associated API keys for this provider config. **Always null in the
quota endpoint** — keys are intentionally not loaded here to keep
the response lean and avoid exposing sensitive credentials. Use the
admin virtual-key API to inspect actual key assignments.
items:
$ref: '#/components/schemas/TableKey'
VirtualKeyMCPConfig:
type: object
description: MCP configuration for a virtual key
required:
- id
- virtual_key_id
- mcp_client_id
- mcp_client
- tools_to_execute
properties:
id:
type: integer
virtual_key_id:
type: string
mcp_client_id:
type: integer
mcp_client:
$ref: '#/components/schemas/MCPClientConfig'
tools_to_execute:
type: array
items:
type: string
RateLimit:
type: object
description: Rate limit configuration
required:
- id
- token_current_usage
- token_last_reset
- request_current_usage
- request_last_reset
- config_hash
- created_at
- updated_at
properties:
id:
type: string
token_max_limit:
type: integer
format: int64
token_reset_duration:
type: string
token_current_usage:
type: integer
format: int64
token_last_reset:
type: string
format: date-time
request_max_limit:
type:
- integer
- 'null'
format: int64
request_reset_duration:
type:
- string
- 'null'
request_current_usage:
type: integer
format: int64
request_last_reset:
type: string
format: date-time
config_hash:
type:
- string
- 'null'
created_at:
type: string
format: date-time
updated_at:
type: string
format: date-time
TableKey:
type: object
description: Table key configuration
properties:
id:
type: integer
name:
type: string
provider_id:
type: integer
provider:
type: string
key_id:
type: string
value:
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
models:
type: array
items:
type: string
weight:
type:
- number
- 'null'
enabled:
type:
- boolean
- 'null'
default: true
use_for_batch_api:
type:
- boolean
- 'null'
default: false
created_at:
type: string
format: date-time
updated_at:
type: string
format: date-time
config_hash:
type:
- string
- 'null'
azure_endpoint:
oneOf:
- 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
- type: 'null'
azure_client_id:
oneOf:
- 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
- type: 'null'
azure_client_secret:
oneOf:
- 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
- type: 'null'
azure_tenant_id:
oneOf:
- 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
- type: 'null'
vertex_project_id:
oneOf:
- 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
- type: 'null'
vertex_project_number:
oneOf:
- 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
- type: 'null'
vertex_region:
oneOf:
- 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
- type: 'null'
vertex_auth_credentials:
oneOf:
- 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
- type: 'null'
bedrock_access_key:
oneOf:
- 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
- type: 'null'
bedrock_secret_key:
oneOf:
- 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
- type: 'null'
bedrock_session_token:
oneOf:
- 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
- type: 'null'
bedrock_region:
oneOf:
- 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
- type: 'null'
bedrock_arn:
oneOf:
- 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
- type: 'null'
MCPClientConfig:
type: object
description: Full MCP client configuration (used in responses)
properties:
client_id:
type: string
description: Unique identifier for the MCP client
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
connection_type:
type: string
enum:
- http
- stdio
- sse
- inprocess
description: Connection type for MCP client
connection_string:
type: string
description: HTTP or SSE URL (required for HTTP or SSE connections)
stdio_config:
type: object
description: STDIO configuration for MCP client
properties:
command:
type: string
description: Executable command to run
args:
type: array
items:
type: string
description: Command line arguments
envs:
type: array
items:
type: string
description: Environment variables required
tls_config:
type: object
description: TLS configuration for HTTP and SSE connections.
properties:
insecure_skip_verify:
type: boolean
description: Disable TLS certificate verification. Development/testing only.
ca_cert_pem:
type: string
description: >
PEM-encoded CA certificate. Supports env.VAR_NAME syntax for
input.
Responses return a redacted placeholder rather than the raw PEM
value.
auth_type:
type: string
enum:
- none
- headers
- oauth
- per_user_oauth
- per_user_headers
- token_exchange
description: Authentication type for the MCP connection
oauth_config_id:
type: string
description: |
OAuth config ID for OAuth authentication.
References the oauth_configs table.
Only set when auth_type is "oauth".
headers:
type: object
additionalProperties:
type: string
description: |
Custom headers to include in requests.
Only used when auth_type is "headers".
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}
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. The list of header names each
end-user
must supply via the inline-401 flow. Header values themselves are
stored
per-user in a separate table (surfaced on `/api/mcp/sessions`).
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. `client_id` and `client_secret`
are
redacted in this response.
disabled:
type: boolean
default: false
description: >
Whether the client is intentionally disabled.
When true, the client has no active connection or workers and its
tools are not available for inference.
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.
````