kids-radar-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KIDS_RADAR_MCP_ALLOW_CRAWL | No | Set to '1' to allow crawl functionality in MCP server (default blocked) | |
| KIDS_RADAR_MCP_CRAWL_SOURCES | No | Comma-separated list of source IDs to allow when crawl is enabled |
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 |
|---|---|
| list_experience_sourcesA | List registered official sources without making source HTTP requests. |
| search_nearby_experiencesB | Search the local DB by coordinates; raw source payloads are never returned. |
| get_experienceA | Get one stored event by its public 24-character event ID, without raw data. |
| render_nearby_digestB | Render a local nearby digest; this never writes files or sends webhooks. |
| get_radar_statusA | Return local database counts, last runs, and MCP refresh gate state. |
| refresh_experience_sourcesA | Run allowlisted official-source crawlers; this may take several minutes. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| find_family_experiences | Plan a safe location-based search using Kids Experience Radar. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| kids_experience_sources | Compact registry of official experience sources and run availability. |
| kids_experience_stats | Current local event counts and latest source crawl results. |
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: listing sources, fetching by ID, searching by coordinates, rendering a digest, getting status, and refreshing sources. No two tools overlap in function, making selection unambiguous.
All tools follow a consistent verb_noun snake_case pattern (e.g., list_experience_sources, get_experience, render_nearby_digest). The verbs are descriptive and the nouns consistently name the target resource, making the toolset predictable.
With 6 tools, the server covers its core workflows without bloat. Each tool earns its place, ranging from data ingestion and query to status reporting and digest rendering.
The toolset provides a complete set of operations for the radar use case: listing/refreshing sources, fetching a specific experience, searching nearby, rendering a digest, and checking system status. There are no dead ends or obvious missing operations for this domain.