General Tools
l2tools.org
Provides general-purpose tools through the Model Context Protocol.
ENDPOINT 1
https://l2tools.org/api/mcp
MCP server metadata
- Name
- l2tools
- Version
- 1.0.0
Read-only Lineage 2 reference data. Always preserve the requested chronicle and include dataset provenance in answers.
Known tools 5
search_npcsSearch chronicle-scoped NPCs by name or numeric ID before opening a record.
Inferred read-onlyget_npcGet stats, traits, skills, locations and provenance for one numeric NPC ID.
Inferred read-onlyget_npc_dropsGet effective x1 drop and spoil probabilities for one numeric NPC ID.
Potential side effectsget_soul_crystal_progressionGet Soul Crystal result stages, transitions and chances for one NPC.
Inferred read-onlyget_xp_levelsGet per-level and cumulative experience values for an inclusive level range.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.l2tools]
url = "https://l2tools.org/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"l2tools": {
"type": "http",
"url": "https://l2tools.org/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: l2tools
Remote MCP URL: https://l2tools.org/api/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"l2tools": {
"url": "https://l2tools.org/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"l2tools": {
"type": "http",
"url": "https://l2tools.org/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "l2tools",
"transport": "streamable-http",
"url": "https://l2tools.org/api/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.