osrs-companion
Enables AI assistants to search the OSRS Wiki, lookup Grand Exchange prices, and access synced player data (bank, skills, quests, etc.) via local RuneLite plugin files.
README
osrs-companion
An MCP server for Old School RuneScape that gives AI assistants access to wiki search, Grand Exchange prices, and your synced player data — all running locally on your machine.
Features
- Wiki Search — Search the OSRS Wiki for any article
- Page Summaries — Get introductory summaries of wiki pages
- GE Prices — Look up current Grand Exchange buy/sell prices
- WikiSync Player Data — Fetch player data via the WikiSync plugin
- Local Player Sync — Read detailed player data saved by the companion RuneLite plugin (bank, skills, quests, equipment, inventory, diaries, combat achievements)
Prerequisites
For the local player sync tools, install the OSRS MCP Companion RuneLite plugin. Wiki search, summaries, and GE prices work without it.
Installation
Claude Code / Claude Desktop
Add to your MCP configuration:
{
"mcpServers": {
"osrs-companion": {
"command": "npx",
"args": ["-y", "osrs-companion"]
}
}
}
Manual
npx -y osrs-companion
Available Tools
Wiki Tools
| Tool | Description |
|---|---|
search |
Search the OSRS Wiki for articles |
summary |
Get the intro summary of a wiki page |
price |
Look up Grand Exchange prices |
player |
Fetch player data via WikiSync |
Player Sync Tools (requires RuneLite plugin)
| Tool | Description |
|---|---|
list_synced_players |
List players with synced data |
get_my_profile |
Full player summary |
get_my_bank |
Search bank contents |
get_my_stats |
Skill levels and XP |
get_my_quests |
Quest completion status |
get_my_equipment |
Currently equipped items |
get_my_inventory |
Current inventory |
get_my_diaries |
Achievement diary progress |
get_my_combat_achievements |
Combat achievement status |
How It Works
The MCP server runs locally via stdio transport. Wiki and price tools
fetch from public OSRS APIs. Player sync tools read JSON files from
~/.runelite/osrs-companion/ that are written by the companion RuneLite plugin.
No data is stored in the cloud. No API keys required.
Attribution
Wiki content returned by the search and summary tools is sourced from the
Old School RuneScape Wiki, which is licensed
under CC BY-NC-SA 3.0.
All wiki tool responses include an attribution notice automatically.
Grand Exchange price data is provided by the OSRS Wiki Prices API. Player data is fetched via the WikiSync API or read from local files saved by the RuneLite plugin — neither contains wiki article content.
License
BSD 2-Clause "Simplified" License. See LICENSE.
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.