Skip to content
  • Auto
  • Light
  • Dark
DiscordForumGitHubSign up
View as Markdown
Copy Markdown

Open in Claude
Open in ChatGPT

Mcp Servers

Create Mcp Server
client.mcpServers.create(McpServerCreateParams { config, server_name } body, RequestOptionsoptions?): McpServerCreateResponse
post/v1/mcp-servers/
List Mcp Servers
client.mcpServers.list(RequestOptionsoptions?): McpServerListResponse { , , }
get/v1/mcp-servers/
Retrieve Mcp Server
client.mcpServers.retrieve(stringmcpServerID, RequestOptionsoptions?): McpServerRetrieveResponse
get/v1/mcp-servers/{mcp_server_id}
Delete Mcp Server
client.mcpServers.delete(stringmcpServerID, RequestOptionsoptions?): void
delete/v1/mcp-servers/{mcp_server_id}
Update Mcp Server
client.mcpServers.update(stringmcpServerID, McpServerUpdateParams { config, server_name } body, RequestOptionsoptions?): McpServerUpdateResponse
patch/v1/mcp-servers/{mcp_server_id}
Refresh Mcp Server Tools
client.mcpServers.refresh(stringmcpServerID, McpServerRefreshParams { agent_id } params?, RequestOptionsoptions?): McpServerRefreshResponse
patch/v1/mcp-servers/{mcp_server_id}/refresh
ModelsExpand Collapse
CreateSseMcpServer { server_url, auth_header, auth_token, 2 more }

Create a new SSE MCP server

server_url: string

The URL of the server

auth_header?: string | null

The name of the authentication header (e.g., 'Authorization')

auth_token?: string | null

The authentication token or API key value

custom_headers?: Record<string, string> | null

Custom HTTP headers to include with requests

mcp_server_type?: "sse"
Accepts one of the following:
"sse"
CreateStdioMcpServer { args, command, env, mcp_server_type }

Create a new Stdio MCP server

args: Array<string>

The arguments to pass to the command

command: string

The command to run (MCP 'local' client will run this command)

env?: Record<string, string> | null

Environment variables to set

mcp_server_type?: "stdio"
Accepts one of the following:
"stdio"
CreateStreamableHTTPMcpServer { server_url, auth_header, auth_token, 2 more }

Create a new Streamable HTTP MCP server

server_url: string

The URL of the server

auth_header?: string | null

The name of the authentication header (e.g., 'Authorization')

auth_token?: string | null

The authentication token or API key value

custom_headers?: Record<string, string> | null

Custom HTTP headers to include with requests

mcp_server_type?: "streamable_http"
Accepts one of the following:
"streamable_http"
SseMcpServer { server_name, server_url, id, 4 more }

An SSE MCP server

server_name: string

The name of the MCP server

server_url: string

The URL of the server

id?: string

The human-friendly ID of the Mcp_server

auth_header?: string | null

The name of the authentication header (e.g., 'Authorization')

auth_token?: string | null

The authentication token or API key value

custom_headers?: Record<string, string> | null

Custom HTTP headers to include with requests

mcp_server_type?: "sse"
Accepts one of the following:
"sse"
StdioMcpServer { args, command, server_name, 3 more }

A Stdio MCP server

args: Array<string>

The arguments to pass to the command

command: string

The command to run (MCP 'local' client will run this command)

server_name: string

The name of the MCP server

id?: string

The human-friendly ID of the Mcp_server

env?: Record<string, string> | null

Environment variables to set

mcp_server_type?: "stdio"
Accepts one of the following:
"stdio"
StreamableHTTPMcpServer { server_name, server_url, id, 4 more }

A Streamable HTTP MCP server

server_name: string

The name of the MCP server

server_url: string

The URL of the server

id?: string

The human-friendly ID of the Mcp_server

auth_header?: string | null

The name of the authentication header (e.g., 'Authorization')

auth_token?: string | null

The authentication token or API key value

custom_headers?: Record<string, string> | null

Custom HTTP headers to include with requests

mcp_server_type?: "streamable_http"
Accepts one of the following:
"streamable_http"
UpdateSseMcpServer { server_url, auth_header, auth_token, 2 more }

Update schema for SSE MCP server - all fields optional

server_url: string | null

The URL of the server

auth_header?: string | null

The name of the authentication header (e.g., 'Authorization')

auth_token?: string | null

The authentication token or API key value

custom_headers?: Record<string, string> | null

Custom HTTP headers to include with requests

mcp_server_type?: "sse"
Accepts one of the following:
"sse"
UpdateStdioMcpServer { args, command, env, mcp_server_type }

Update schema for Stdio MCP server - all fields optional

args: Array<string> | null

The arguments to pass to the command

command: string | null

The command to run (MCP 'local' client will run this command)

env?: Record<string, string> | null

Environment variables to set

mcp_server_type?: "stdio"
Accepts one of the following:
"stdio"
UpdateStreamableHTTPMcpServer { server_url, auth_header, auth_token, 2 more }

Update schema for Streamable HTTP MCP server - all fields optional

server_url: string | null

The URL of the server

auth_header?: string | null

The name of the authentication header (e.g., 'Authorization')

auth_token?: string | null

The authentication token or API key value

custom_headers?: Record<string, string> | null

Custom HTTP headers to include with requests

mcp_server_type?: "streamable_http"
Accepts one of the following:
"streamable_http"

Mcp ServersTools

List Tools For Mcp Server
client.mcpServers.tools.list(stringmcpServerID, RequestOptionsoptions?): ToolListResponse { id, args_json_schema, created_by_id, 15 more }
get/v1/mcp-servers/{mcp_server_id}/tools
Retrieve Mcp Tool
client.mcpServers.tools.retrieve(stringtoolID, ToolRetrieveParams { mcp_server_id } params, RequestOptionsoptions?): Tool { id, args_json_schema, created_by_id, 15 more }
get/v1/mcp-servers/{mcp_server_id}/tools/{tool_id}
Run Mcp Tool
client.mcpServers.tools.run(stringtoolID, ToolRunParams { mcp_server_id, args } params, RequestOptionsoptions?): ToolExecutionResult { status, agent_state, func_return, 3 more }
post/v1/mcp-servers/{mcp_server_id}/tools/{tool_id}/run