Education Data MCP Server
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_education_dataB | Retrieve education data from the Urban Institute's Education Data API |
| get_education_data_summaryC | Retrieve aggregated education data from the Urban Institute's Education Data API |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| schools/ccd/enrollment | Education data endpoint (subtopics: race, sex, race, sex). Years: 1986–2022. Main filters: year, grade |
| schools/ccd/directory | Education data endpoint. Years: 1986–2022. Main filters: year |
| school-districts/ccd/enrollment | Education data endpoint (subtopics: race, sex, race, sex). Years: 1986–2022. Main filters: year, grade |
| college-university/ipeds/directory | Education data endpoint. Years: 1980, 1984–2022. Main filters: year |
TDQS
Scored across 2 tools
The two tools have overlapping purposes that could easily cause confusion. Both retrieve education data from the same API, with 'get_education_data_summary' described as aggregated data, but the distinction between regular and aggregated data is not clearly defined in the descriptions. An agent might struggle to choose between them without more specific guidance on when to use each.
The tool names follow a perfectly consistent verb_noun pattern with 'get_education_data' and 'get_education_data_summary'. Both use snake_case and the same verb 'get', making them predictable and easy to parse. There are no deviations or mixed conventions in the naming.
With only 2 tools, this server feels too thin for its apparent scope of accessing an education data API. A typical data API server would benefit from more operations like filtering, searching, or accessing different endpoints, making this set under-scoped. The count is borderline minimal and may limit agent functionality.
The tool surface is severely incomplete for an education data API domain. There are obvious gaps: no tools for filtering data by parameters, accessing specific datasets, updating or managing data, or handling errors. This forces agents into dead ends and limits practical use to basic retrieval only.