Drain3 MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DRAIN3_MCP_STATE_PATH | No | Path to the model snapshot file. Set to 'none' or ':memory:' to disable persistence. | data/drain3_state.bin |
| DRAIN3_MCP_CONFIG_PATH | No | Path to a custom Drain3 INI configuration file. Defaults to the package's default_drain3.ini. | default_drain3.ini |
| DRAIN3_MCP_MAX_BATCH_SIZE | No | Maximum number of log messages allowed in a single batch call. | 1000 |
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 |
|---|---|
| train_logA | Train Drain3 with one log line and return its cluster and extracted parameters. |
| train_logsA | Train Drain3 with a batch of log lines in the provided order. |
| match_logB | Match one log line against learned clusters without changing the model. |
| match_logsA | Match a batch of log lines without changing the learned model. |
| list_templatesB | List learned log templates with sorting and pagination. |
| extract_log_parametersB | Extract variable values from a log line using a Drain3 template. |
| get_statsA | Get aggregate model statistics and effective Drain3 settings. |
| save_stateA | Write an immediate snapshot of the learned model to configured persistence. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| stats_resource | Current Drain3 model statistics as JSON. |
| templates_resource | Up to the first 1000 learned templates as JSON. |
TDQS
Scored across 8 tools
Each tool maps to a distinct operation: training, matching, listing templates, extracting parameters, stats, and persistence. The singular/batch pairs are clearly differentiated by description.
All tool names follow a consistent verb_noun snake_case pattern, such as train_log, match_log, list_templates, and save_state. Minor length differences do not hurt predictability.
Eight tools is well-scoped for a Drain3-focused server. Each tool covers a necessary aspect of the log template mining workflow without redundancy beyond intentional singular/batch variants.
The core training, matching, template listing, parameter extraction, stats, and persistence workflows are covered. However, there is no explicit load_state or reset/clear operation, which leaves minor gaps in full lifecycle management.