Parallel Works MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PARALLEL_WORKS_TOKEN | No | JWT bearer token for authentication | |
| PARALLEL_WORKS_API_KEY | No | API key for basic authentication | |
| PARALLEL_WORKS_API_URL | No | Custom API base URL (default: https://activate.parallel.works) |
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 |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_auth_sessionA | Get the current authentication session and user information |
| get_organizationsA | List organizations the user can access |
| get_groupsB | Get groups for the authenticated user |
| list_clustersA | List all clusters the user can access |
| get_cluster_nodesA | Get nodes for a specific compute cluster |
| list_workflowsC | List all workflows for the authenticated user |
| get_workflowB | Get details of a specific workflow |
| get_workflow_yamlB | Get the YAML configuration of a workflow |
| run_workflowB | Run a workflow with optional input parameters |
| list_bucketsB | List storage buckets the user can access |
| list_lustreA | List Lustre filesystems the user can access |
| list_nfsB | List NFS filesystems the user can access |
| list_sessionsB | List sessions for the authenticated user |
| list_allocationsB | List budget allocations the user can access |
| list_kubernetes_clustersB | List Kubernetes clusters accessible to the user |
| list_ml_workspacesC | List Machine Learning Workspaces |
| get_notificationsB | Get notifications for the authenticated user |
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 17 tools
Each tool targets a distinct resource: auth, organizations, groups, clusters, nodes, workflows, workflow YAML, storage types, sessions, allocations, Kubernetes, ML workspaces, and notifications. No two tools appear to serve the same purpose, and the resource-action pairs are clearly differentiated.
The naming pattern is generally verb_noun, but there is inconsistency between 'get_' and 'list_' prefixes for essentially the same operation. For example, get_organizations and get_groups return lists, while list_clusters and list_workflows are used elsewhere. This mixed convention adds avoidable ambiguity.
With 17 tools, the server covers a broad but reasonable domain of resources and actions. While slightly on the heavier side, each tool represents a distinct resource or operation, and the count aligns with the platform's diverse feature set without feeling excessive.
The tool surface is strong for read/listing operations and includes run_workflow as the primary action, but lacks create, update, or delete capabilities for most resources (e.g., creating a bucket, deleting a session, or stopping a workflow). This leaves the set incomplete for full lifecycle management, though it may suffice for monitoring and execution scenarios.