jgrants-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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_subsidiesA | JGrantsに登録された補助金をキーワードで検索する。 |
| get_subsidy_detailA | 補助金1件の詳細を取得する。 |
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 2 tools
search_subsidies handles discovery, while get_subsidy_detail retrieves a specific subsidy by ID. Their purposes are clearly distinct, and the version parameter applies only to the detail operation.
Both tools follow the same snake_case verb_noun pattern: search_subsidies and get_subsidy_detail. There is no mixing of naming conventions.
The two tools are non-redundant and directly cover search plus detail, but the surface is thinner than the typical 3-15 tool range. For a narrow read-only API wrapper this may be adequate, but it leaves little room for auxiliary operations.
The core read-only workflow of searching subsidies and then retrieving details is well covered, including rich filters and detailed result fields. Minor gaps remain: agents cannot discover valid filter code values, cannot browse without a keyword, and pagination is not mentioned.