MCP-SST
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Path to your SST project |
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 |
|---|---|
| sst_discoverC | Discover running SST dev servers and available stages. |
| sst_list_tabsB | List all available log tabs/files from SST dev. |
| sst_read_logsC | Read the last N lines from a specific SST dev log tab. |
| sst_get_statusB | Get current deployment status and resources from SST dev. |
| sst_get_invocationsC | Get recent Lambda function invocations from SST dev. |
| sst_get_eventsC | Get recent events from the SST dev event stream. |
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 6 tools
Each tool has a clearly distinct purpose targeting different aspects of SST dev monitoring: discovery, events, invocations, status, log tabs, and log reading. There is no overlap or ambiguity between tools.
All tools follow a perfect 'sst_verb_noun' pattern with consistent snake_case naming. The verb choices (discover, get, list, read) are appropriate and uniformly applied.
With 6 tools, this is well-scoped for monitoring SST dev servers. Each tool serves a specific monitoring function, and the count is neither too sparse nor excessive for the domain.
The toolset provides comprehensive coverage for monitoring SST dev environments, including discovery, status, events, invocations, and logs. A minor gap is the lack of tools for controlling or interacting with the servers (e.g., restarting or deploying), but the monitoring surface is complete.