alpha-lab-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ALPHA_LAB_MCP_DATABASE_PATH | Yes | The absolute path to the SQLite ledger database. Required to configure the MCP server. | |
| ALPHA_LAB_MCP_REPLAY_FIXTURE | No | The absolute path to a sanitized replay JSON fixture. Optional; used by replay tools. |
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 |
|---|---|
| alpha_run_statusB | Read the persisted status and counts for one existing research run. |
| alpha_run_reportB | Render the deterministic Markdown report for one existing run. |
| alpha_method_cards_listB | List stored method-card identities and human-review states. |
| alpha_replay_executeC | Execute or resume one replay-mode run using the operator-configured fixture. |
| alpha_run_stopB | Persist a fixed MCP-requested stop reason for one existing run. |
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 5 tools
Each tool targets a distinct action: stopping a run, reading status, rendering a report, listing method cards, or executing replay. There is no meaningful overlap; even run_status and run_report are clearly separated by output type.
All tools share the alpha_ prefix and snake_case, and most follow an alpha_<resource>_<action> pattern. The pattern is slightly weakened by noun-like action words such as status and report, but it remains predictable and readable.
Five tools is a well-scoped size for a focused lab-run management server. Each tool has a clear role, and the count is neither bloated nor too thin.
The run lifecycle is partially covered with status, stop, report, and replay execution, but there is no run listing, standard run creation, or method-card update/review operation. Agents may need external context to select or manage runs.