gx-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_MODE | No | Server transport mode: 'stdio' (default) or 'http'. | stdio |
| MCP_AUTH_TOKEN | No | Authentication token for basic auth (format 'user:password') or bearer token. | |
| MCP_SERVER_URL | No | Server URL for legacy clients. | |
| MCP_SERVER_USER | No | Username for basic authentication (used with MCP_SERVER_PASSWORD). | |
| PYTHONUNBUFFERED | No | Set to '1' to disable Python output buffering (recommended for Docker). | 0 |
| MCP_SERVER_PASSWORD | No | Password for basic authentication (used with MCP_SERVER_USER). | |
| GX_ANALYTICS_ENABLED | No | Set to 'false' to disable Great Expectations anonymous usage telemetry. | true |
| MCP_CSV_SIZE_LIMIT_MB | No | Maximum CSV file size in MB (1-1024). Default is 50. | 50 |
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": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| load_datasetA | Load data (CSV string, URL, or local file) into memory and return a handle. |
| create_suiteA | Create a named ExpectationSuite, optionally profiled from a dataset. |
| add_expectationA | Add a single expectation to an existing suite (or create it). |
| get_versionA | Return the API version for MCP server. |
| run_checkpointB | Run a validation checkpoint against a dataset using an expectation suite. |
| get_validation_resultA | Fetch detailed validation results for a prior validation run. |
| pingA | Return basic health status. |
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 7 tools
Each tool addresses a distinct concern: health/version, data loading, suite/expectation management, and validation execution/result retrieval. There is no overlap between run_checkpoint and get_validation_result, as one performs the validation and the other retrieves its output.
All tools follow a snake_case verb_noun pattern (run_checkpoint, get_validation_result, load_dataset, create_suite, add_expectation, get_version), with 'ping' as the only exception but it is a standard health-check name. The convention is uniform and predictable.
Seven tools is well within the ideal range for a focused MCP server. Each tool serves a necessary function for the core workflow of building and running data validation, with no redundancy or scope creep.
The set covers the primary workflow (load data, create suite, add expectation, run checkpoint, get result), but lacks read operations for existing suites or expectations, and has no update/delete capabilities. Agents cannot discover or manage existing validation assets without extending the surface.