MCP Playground
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WEBSHARE_PROXIES | No | Proxies for YouTube cloud deployment | |
| YOUTUBE_MAX_TOKENS | No | Transcript processing limit | 24000 |
| MCP_RETRY_MAX_ATTEMPTS | No | Auto-retry failed tool calls | 3 |
| MCP_RETRY_TYPE_COERCION | No | Auto-fix type mismatches | true |
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| web_searchB | Search web for current information using DuckDuckGo |
| analyze_urlC | Comprehensive analysis of webpage content optimized for LLM understanding |
| arxiv_searchB | Search academic papers on arXiv with full text extraction |
| get_stock_overviewC | Get comprehensive stock, crypto, and market data |
| analyze_youtube_urlB | Get YouTube video transcript and analyze content with optional specific questions |
| get_weatherB | Get current weather and 7-day forecast for any location or your current location |
| get_tide_infoC | Get Canadian coastal tide times and heights |
| get_toronto_crimeC | Get Toronto neighbourhood crime statistics and trends |
| list_toronto_neighbourhoodsA | List all available Toronto neighbourhoods for crime data |
| analyze_canadian_economyD | Canadian economic analysis and overview |
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 10 tools
Each tool targets a distinct domain or function: Canadian economy, URL analysis, YouTube, arXiv, stocks, tides, Toronto crime, weather, neighborhoods, and web search. There is no overlap or ambiguity among them.
All tool names follow a consistent verb_noun pattern (e.g., analyze_canadian_economy, get_weather, list_toronto_neighbourhoods, web_search). The naming is predictable and uniform.
The server has 10 tools, which is a reasonable number for a general-purpose playground. Each tool covers a distinct area without being overwhelming or sparse.
The tool set covers a broad range of information retrieval tasks (web, academic, financial, weather, local data). Minor gaps exist (e.g., no image analysis, no file operations), but for a playground server, the coverage is sufficient.