rgl-mcp
Enables querying RGL.gg competitive TF2 data through natural language, resolving player, team, season, division, and match information via a series of API calls.
README
rgl-mcp
MCP server that wraps the RGL API with natural-language tools. Designed for hosting on fly.io.
What it does
Translates queries like "every player who played IM in S7 of 6s" into the right sequence of API calls:
- Resolves "6s" → format/region (defaults to NA when not specified).
- Resolves "S7" → SeasonId by fuzzy-matching cached season list.
- Resolves "IM" → DivisionId scoped to the region.
- Fetches the corresponding Group, then its rosters.
- Optionally bulk-fetches profile data for every unique player.
Tools
| Tool | Purpose |
|---|---|
find_season |
Resolve season phrase → SeasonId |
find_region |
Resolve region phrase → RegionId |
find_division |
Resolve division phrase → DivisionId (scoped to a region) |
find_team |
Substring search on team name/tag |
find_player |
Substring search on player aliases |
get_player |
Profile by SteamID |
get_team |
Team data by TeamId |
get_match |
Match data by MatchId |
list_season_divisions |
Groups in a season |
list_division_teams |
Teams in a (season, division) |
list_division_players |
Every unique player in (season, division), optionally with full profile data |
list_formats |
All formats (lookup) |
list_regions |
All regions (lookup) |
Local development
npm install
npm run dev
The server reads .env.local for RGL_API_BASE_URL etc. By default it points at the production RGL API.
Deploy
fly launch --name rgl-mcp --copy-config --no-deploy # first time only
fly deploy
Then point your MCP client at https://rgl-mcp.fly.dev/mcp (Streamable HTTP transport).
Configuration
| Env var | Default | Meaning |
|---|---|---|
RGL_API_BASE_URL |
https://rglgg-api.fly.dev/v0 |
Base URL of the RGL API |
PORT |
3000 |
HTTP listen port |
CACHE_REFRESH_MS |
3600000 |
Lookup cache TTL (1h) |
DEFAULT_REGION_ID |
40 |
NA Sixes — used when only a format is given |
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.