feature-separate-batch-eval-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CC_EVAL_DATA_DIR | Yes | Points to the same directory used by the single-record evaluation MCP. Required so batch analysis can read the existing patent evaluations and cohorts. Batch outputs default to its `batch_analysis/` subdirectory. | |
| FEATURE_SEPARATE_BATCH_DATA_DIR | No | Optional independent path for batch analysis outputs. If omitted, outputs are written under `CC_EVAL_DATA_DIR/batch_analysis/`. |
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 |
|---|---|
| feature_separate_batch_eval_statusB | List cohorts and sample readiness; never uses network. |
| feature_separate_batch_eval_tagC | Assign patent evaluation records to a comparable cohort; never uses network. |
| feature_separate_batch_eval_checkC | Validate one cohort and show comparison readiness; never uses network. |
| feature_separate_batch_eval_runC | Discover batch-only issues after explicit network-scope confirmation. |
| feature_separate_batch_eval_insightsB | List persisted batch-only insights; never uses network. |
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: status (list cohorts), tag (assign records), check (validate one cohort), run (execute network eval), insights (list persisted results). Status and check both touch 'readiness' and status/insights both list things, which introduces mild overlap, but descriptions keep them separable.
Every tool shares the consistent 'feature_separate_batch_eval_' prefix followed by a short suffix, forming a predictable pattern. Minor deviation in that tag/check/run are verbs while status/insights are nouns, but overall highly consistent.
Five tools is a reasonable, well-scoped set for a batch-evaluation workflow (readiness, tagging, validation, execution, insights). Slightly lean but each tool has a clear role without redundancy.
The core lifecycle (list readiness, assign cohorts, validate, run, retrieve insights) is covered, but there is no way to modify/remove cohort assignments or clear/export persisted insights, leaving some dead ends.