alpha-lab-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ALPHA_LAB_MCP_DATABASE_PATH | Yes | Absolute path to the SQLite ledger database used by the MCP server. | |
| ALPHA_LAB_MCP_REPLAY_FIXTURE | No | Optional absolute path to a sanitized replay fixture JSON file used for replay execution. |
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 resource and action: run stop, run status, run report, method-card listing, and replay execution. Even the three run_* tools are clearly separated by whether they write state, read status, or render output.
All names consistently use the alpha_ prefix, snake_case, and an object_operation structure. Minor inconsistency remains because stop, list, and execute are true verbs while status and report are nominalized operations.
Five tools is a well-scoped size for this server's purpose. Each tool covers a distinct function with no apparent redundancy.
The set covers the core run workflow: execute/resume, stop, status, and report, plus method-card listing. However, there is no run-listing tool and no method-card detail or mutation tools, so agents must already know run IDs to operate effectively.