Opus MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPUS_SERVICE_KEY | Yes | Your Opus service key for authentication. Get this from Opus platform: My Organization → gear icon → API Keys → Generate API Key |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_workflow_detailsB | Get workflow details including jobPayloadSchema that defines required inputs for a workflow |
| initiate_jobC | Initiate a new job for a workflow. Returns jobExecutionId required for subsequent operations |
| generate_file_upload_urlA | Generate presigned URL for file upload. Returns presignedUrl (for uploading) and fileUrl (to reference in job execution) |
| execute_jobB | Execute a job with populated input values. Use jobPayloadSchema from get_workflow_details to structure inputs correctly |
| get_job_statusC | Get the current status of a job execution (e.g., IN PROGRESS, COMPLETED, FAILED) |
| get_job_resultsA | Get the results of a completed job execution. Only works when job status is COMPLETED |
| get_job_audit_logB | Get detailed audit log of all system actions during job execution |
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 7 tools
Each tool has a clearly distinct purpose with no ambiguity. Tools are organized around specific job lifecycle stages: initiation (initiate_job), execution (execute_job), status checking (get_job_status), result retrieval (get_job_results), audit logging (get_job_audit_log), workflow details (get_workflow_details), and file upload (generate_file_upload_url). There is no overlap in functionality.
All tools follow a consistent verb_noun pattern with snake_case throughout. The naming convention is perfectly predictable: 'get_' for retrieval operations, 'initiate_' and 'execute_' for job control, and 'generate_' for URL creation. No deviations or mixed conventions exist.
With 7 tools, the count is well-scoped for a job/workflow execution server. Each tool earns its place by covering essential aspects of the domain: workflow definition, job initiation, execution, status monitoring, result retrieval, audit logging, and file handling. This is neither too sparse nor bloated.
The tool set provides complete CRUD/lifecycle coverage for job execution. It includes workflow discovery (get_workflow_details), job initiation (initiate_job), execution (execute_job), status tracking (get_job_status), result retrieval (get_job_results), audit logging (get_job_audit_log), and file upload support (generate_file_upload_url). There are no obvious gaps that would cause agent failures.