mcp-server-suite
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_SQL_DSN | No | PostgreSQL DSN. Default: unset. Must use postgres:// or postgresql://. Enables the read_only_sql tool. | |
| MCP_SAFE_DATA_DIR | No | Absolute, existing directory used as the sandbox root. Default: unset, except the container image sets /safe_data_dir. Enables the sandbox_fs_read tool. | |
| MCP_METRICS_ENABLED | No | Boolean value controlling whether the system_metrics tool is enabled. | true |
| MCP_METRICS_DISK_PATH | No | Absolute path of the filesystem reported by disk_percent_used. | / |
| MCP_SQL_POOL_MAX_SIZE | No | Maximum pooled connections. Constraint: 1-32. Connections are created lazily. | 4 |
| MCP_SQL_QUERY_TIMEOUT | No | Client timeout and server statement_timeout in seconds. Constraint: > 0 and <= 300. | 10 |
| MCP_MAX_ARGUMENT_DEPTH | No | Maximum nesting depth of tool arguments. Constraint: 1-64. | 8 |
| MCP_MAX_ARGUMENT_ITEMS | No | Maximum number of items in any argument container. Constraint: 1-100000. | 1000 |
| MCP_SQL_CONNECT_TIMEOUT | No | Connect and pool-acquire timeout in seconds. Constraint: > 0 and <= 60. | 5 |
| MCP_MAX_CONCURRENT_TOOLS | No | Number of concurrent tools/call slots. Constraint: 1-256. | 16 |
| MCP_SQL_APPLICATION_NAME | No | application_name seen in pg_stat_activity. Constraint: 1-63 characters. | mcp-server-suite |
| MCP_TOOL_TIMEOUT_SECONDS | No | Per-call execution deadline in seconds. Constraint: > 0 and <= 600. | 30 |
| MCP_SERVER_SUITE_LOG_LEVEL | No | stderr log verbosity. Must be a valid logging level name. | WARNING |
| MCP_METRICS_CPU_SAMPLE_SECONDS | No | CPU sampling interval in seconds. Constraint: > 0 and <= 2. | 0.1 |
| MCP_TOOL_ACQUIRE_TIMEOUT_SECONDS | No | Seconds to wait for a concurrency slot before rejecting. Constraint: 0-60. A value of 0 rejects immediately. | 5 |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| system_metricsA | Report host health: CPU utilisation, logical core count, 1-minute load average and memory usage; set include_disk for root-volume usage. Values are a point-in-time sample with a UTC timestamp. |
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 1 tool
There is only one tool, so there is no possibility of selecting the wrong one. Its purpose (host health snapshot) is stated clearly and unambiguously.
The single name system_metrics is snake_case, descriptive, and resource-oriented, with no competing conventions to clash with. Consistency cannot be violated with one tool, and the name reads predictably.
A one-tool server is too thin for a general 'mcp-server-suite' scope; everything is crammed into a single snapshot call. It is well-scoped for what it does, but the surface is minimal.
CPU, load, core count, memory, and optional disk cover the core host-health snapshot, but there is no history/time-series, network, process, uptime, or multi-host coverage. Agents needing anything beyond a point-in-time sample hit a dead end.