LeakageLens MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_MODEL | No | Model name to use for Gemini review. Defaults to 'gemini-2.5-flash'. | gemini-2.5-flash |
| MCP_TRANSPORT | No | Transport for the MCP server, e.g., 'streamable-http' for remote transport. If not set, the default transport is used. | |
| GEMINI_API_KEY | No | API key for the optional Gemini semantic review feature. | |
| LEAKAGELENS_DATA_ROOT | Yes | The root directory that all file tools are restricted to. Must be an absolute path. |
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 |
|---|---|
| profile_datasetA | Profile a local CSV, Parquet, or JSONL without sending the full dataset to the model. |
| audit_datasetC | Detect target, entity and temporal leakage, PII, identifiers, and metric risks. |
| audit_training_codeA | Statically detect preprocessing or resampling before the train/test split. |
| review_feature_availabilityC | Optionally ask Gemini which features may be unavailable at the prediction moment. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| review_before_training | Create a disciplined pre-training review workflow. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| experiment_contract | Questions that define a valid supervised-learning experiment. |
TDQS
Scored across 4 tools
Each tool targets a distinct stage of leakage detection: profiling, dataset auditing, code auditing, and feature availability review. However, profile_dataset and audit_dataset could be confused by an agent since both operate on datasets, though their descriptions help separate general profiling from leakage-specific auditing.
All tool names consistently follow a verb_noun pattern using lowercase snake_case: profile_dataset, audit_dataset, audit_training_code, and review_feature_availability. This makes the tool set predictable and easy to navigate.
Four tools is well-scoped for a specialized leakage-detection server. Each tool has a clear, non-redundant role, and the count feels appropriate rather than thin or bloated.
The tool surface covers the core leakage-detection workflow: profile data, audit data for leakage, audit training code, and verify feature availability. Minor gaps exist around remediation or actionable reporting after an audit, but the main detection loop is complete.