temporal-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TEMPORAL_ADDRESS | No | Temporal server address | localhost:7233 |
| TEMPORAL_API_KEY | No | API key (for Cloud) | |
| TEMPORAL_TLS_KEY | No | Path to TLS key (for Cloud) | |
| TEMPORAL_TLS_CERT | No | Path to TLS certificate (for Cloud) | |
| TEMPORAL_NAMESPACE | No | Temporal namespace | default |
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
| Capability | Details |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
},
"prompts": {
"get": {}
},
"resources": {
"read": {}
}
}
} |
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_workflowsA | List workflow executions from Temporal. Args: query: Optional query filter (Temporal list filter syntax). Example: 'WorkflowType="MyWorkflow" AND ExecutionStatus="Running"' limit: Maximum number of workflows to return (default 10, max 100) |
| describe_workflowA | Get detailed information about a specific workflow execution. Args: workflow_id: The workflow ID to describe run_id: Optional run ID (uses latest run if not specified) |
| get_workflow_historyA | Get the event history for a workflow execution. Args: workflow_id: The workflow ID run_id: Optional run ID (uses latest run if not specified) max_events: Maximum number of events to return (default 100, max 1000) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool targets a distinct aspect of workflow inspection: list_workflows returns filtered overviews, describe_workflow provides detailed state for a specific execution, and get_workflow_history returns the event sequence. There is no meaningful overlap between the tools.
All tool names follow a consistent lowercase verb_noun pattern: list_workflows, describe_workflow, get_workflow_history. The naming style is uniform and predictable.
Three tools form a focused read-only workflow inspection surface for Temporal. Each tool earns its place, and the count is well-scoped for the apparent purpose.
The set covers core inspection operations well, but it lacks common workflow management operations such as start, signal, terminate, or query. For a read-only observability server this would be complete, but for a general temporal-mcp toolset it has notable gaps.