data-perception-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| build_data_contextB | Profile an authorized local dataset and return Data Context as text. Optional local model interpretation depends on server configuration. Statistics describe the first configured rows, not necessarily the full dataset. |
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 1 tool
Only one tool exists, so there is no possibility of confusion between tools. The single tool has a clear, specific purpose of building a data context.
With a single tool named 'build_data_context', the naming is internally consistent and follows a clear verb_noun pattern. There are no other tools to compare against, so no inconsistencies exist.
A single tool feels too thin for a server branded as 'data-perception-mcp', which implies a broader scope such as data profiling, sampling, or schema discovery. One tool does not adequately fill that apparent purpose.
The server only offers one operation, so agents cannot perform related data perception tasks like listing available datasets, configuring profiling parameters, or obtaining detailed statistics. The surface is significantly incomplete for the implied domain.