SRA Simple MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_all_configA | List all available task config names. Returns: List of config names (e.g., ["Default", "MyConfig"]) |
| run_sra_taskA | Run an SRA task asynchronously. Args: config_name: Name of the config to use (e.g., "Default") timeout: Timeout in seconds (default 3600 = 60 minutes) admin: Start SRA with admin or not Returns: Dict with keys: pid, started_at, cmd, thread, timeout Raises: Exception: If a task is already running, or if config/Popen cannot be loaded. |
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 2 tools
The two tools have completely distinct purposes: one lists configuration names, the other runs an SRA task. There is no overlap or ambiguity.
Both tools follow a consistent verb_noun pattern in snake_case: 'list_all_config' and 'run_sra_task'. This is clear and predictable.
With only 2 tools, the server feels minimal but might be appropriate for a very simple use case. However, most MCP servers for task execution have more tools to manage the lifecycle.
The server lacks essential operations for managing SRA tasks, such as stopping a running task, checking task status, or retrieving results. These gaps will cause agent failures.