Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
WO_API_KEYYesYour IBM Cloud API key
WO_AGENT_IDNoSingle default agent ID (optional, alternative to WO_AGENT_IDs)
WO_AGENT_IDsNoComma-separated list of default agent IDs (optional)
WO_INSTANCE_URLYesThe URL of your Watson Orchestrate instance

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_api_specA

Get the Watson Orchestrate OpenAPI spec. Describes all REST endpoints the MCP server uses (tools, agents, connections, flows, runs). Use to understand what operations the Watson Orchestrate instance supports.

list_skillsC

List all available tools/skills in the Watson Orchestrate catalog

list_tools_with_connectionsA

List Watson Orchestrate tools grouped by connection status: tools that require an API key/OAuth connection vs standard tools. Matches the extension Tools view. Use for prompts like "list my tools with active connections".

list_standard_toolsA

List only standard tools (tools with no connections). Returns accurate count and list from Watson Orchestrate. Use for 'list standard tools' or 'tools with no connections' – tools with empty/missing security and connection_id. Do not guess; use this tool for accurate data.

execute_toolA

Execute a Watson Orchestrate tool by name or ID. Use for prompts like "execute News Search Tool" or "run the Weather tool". Resolves tool names (e.g. "News Search Tool") to IDs, ensures an agent has the tool, then invokes it. Pass parameters as a JSON object if the tool requires them.

get_skillA

Get a specific skill/tool by ID. Returns tool details including display name, description, and binding.

delete_skillB

Delete a skill by ID

deploy_skillC

Deploy a tool from OpenAPI spec. Set openapi_spec["x-ibm-connection-id"] to bind a connection.

update_skillC

Update a tool (name, display_name, description, permission)

copy_skillA

Copy a tool. Creates a new tool with same spec and connection. Use new_name (e.g. "MVKWeatherV2") for a custom name. Names must use only letters, digits, underscores.

deploy_tool_from_urlA

Create a tool from a URL. Works with: (1) APIs with API key – auto-creates connection, (2) Public APIs (REST Countries, Open-Meteo) – no auth needed. Use this MCP tool, NOT ADK.

create_tool_and_assign_to_agentA

Create a tool from URL and assign to agent – ONE step. Use for 'create REST Countries tool and assign to TimeWeatherAgent'. Works with public APIs (no auth) and APIs with keys. Use this MCP tool, do NOT use ADK.

assign_tool_to_agentA

Assign a tool to an agent (add to toolkit). Use tool_name or tool_id, agent_name or agent_id. For "assign REST Countries to TimeWeatherAgent" – use MCP, not ADK.

test_tool_localA

Test an API endpoint locally (direct HTTP GET). Use for "run locally" or "test locally". Does not go through Watson Orchestrate.

list_agentsC

List all available agents

create_agentC

Create an agent. Pass tools array to assign tool IDs.

get_agentA

Get agent details by ID. Returns config, assigned tools, instructions, and model.

get_agent_chat_starter_settingsA

Get chat starter settings for an agent: welcome message and quick prompts. Use agent_id or agent_name.

update_agent_chat_starter_settingsB

Update chat starter settings: welcome_message, quick_prompts (array of {title, prompt}). Use agent_id or agent_name.

list_agent_toolsA

List tools assigned to an agent, with display names and descriptions when available. Use agent_name (e.g. "TimeWeatherAgent") or agent_id. For "which tools are assigned to TimeWeatherAgent". Returns accurate tool list from Watson Orchestrate.

update_agentA

Update an agent. Use agent_name (e.g. "TimeWeatherAgent") or agent_id. Pass payload with instructions, tools, description, etc. For "update TimeWeatherAgent instructions" use agent_name and payload: { instructions: "..." }.

update_agent_instructions_from_toolsA

Update an agent's instructions based on its assigned tools. Fetches tools, builds helpful instructions, and patches the agent. Use for "update TimeWeatherAgent instructions based on its tools".

invoke_agentA

Chat with an agent. Use agent_name (e.g. "TimeWeatherAgent") or agent_id. For "ask TimeWeatherAgent what the exchange rate is CAD/USD" – use agent_name and message. Runs behind the scenes, no script needed.

delete_agentB

Delete an agent by ID

list_connectorsC

List available connector applications from the catalog

list_connectionsB

List configured connections (scope: draft, live, or all)

list_active_live_connectionsA

List only active and live connections (not tools). Returns deduplicated connection names. Use for 'list all connections which are active and live, just the connections not the tools'.

get_connectionC

Get a connection by app_id

create_connectionB

Create a connection. Then use configure_connection for credentials.

delete_connectionB

Delete a connection by app_id

configure_connectionC

Configure connection credentials (api_key, basic, bearer)

list_flowsC

List all available flows

create_flowC

Create or update a flow

get_flowB

Get a flow by ID

delete_flowB

Delete a flow by ID

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/markusvankempen/wxo-builder-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server