AgentIndex icon
AgentIndex
ToolsCategoriesTrendingNewCompare
Submit Tool
Home/
Compare/
STS2MCP vs semble
STS2MCP logo
STS2MCP
★ 377
vs
semble logo
semble
★ 4.5k

STS2MCP vs semble

STS2MCP: STS2MCP is an experimental research mod for Slay the Spire 2 that enables AI agents to play the game. It exposes game state and actions via a localhost REST API, with an optional MCP server for Claude Desktop/Claude Code integration. It supports both singleplayer and multiplayer co-op, and has been tested against STS2 v0.99.1.; semble: Semble is a high-performance code search library designed for AI agents, providing instant access to precise code snippets. It offers significantly faster indexing and querying compared to transformer models, achieving 99% of their retrieval quality while running entirely on CPU without external dependencies.

01

TL;DR

STS2MCP logoChoose STS2MCP if…

AI agents autonomously playing Slay the Spire 2

semble logoChoose semble if…

Enhancing AI agents (e.g., Claude Code, Cursor, Codex) with fast and accurate code search capabilities

02

Side-by-Side Comparison

Field
STS2MCP logoSTS2MCP
semble logosemble
Category
Dev Tooling
RAG / Knowledge Base
Stars
★ 377
★ 4.5k
License
MIT
MIT
Updated
2w ago
1d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
agentic-ai, mcp-server, mcp-servers
agents, code-search, embeddings
03

Features

STS2MCP logoSTS2MCP
01Exposes game state and actions via a localhost REST API
02Optional MCP server for Claude Desktop / Claude Code integration
03Supports singleplayer and multiplayer (co-op)
04Automatically starts HTTP server on localhost:15526
05Allows AI agents to fully automate game runs
semble logosemble
01Fast performance on CPU (indexes in ~250ms, queries in ~1.5ms)
02High accuracy (NDCG@10 of 0.854), comparable to transformer models
03Supports indexing local paths and remote Git repositories
04Functions as an MCP server for various AI agents
05Zero setup, no API keys, GPU, or external services required
04

Use Cases

STS2MCP logoSTS2MCP
↳AI agents autonomously playing Slay the Spire 2
↳Collaborative human-AI co-op runs
↳Benchmarking AI reasoning and decision-making capabilities
semble logosemble
↳Enhancing AI agents (e.g., Claude Code, Cursor, Codex) with fast and accurate code search capabilities
↳Searching local or remote codebases for specific code snippets based on natural language or code queries
↳Finding semantically similar code sections related to a given file path and line number
05

Best For

STS2MCP logoSTS2MCP
Hidden GemDev Tooling
semble logosemble
Code AssistantRAG / Knowledge Base
FAQ

FAQ

What is the difference between STS2MCP and semble?
Both STS2MCP and semble are in the Dev Tooling category. STS2MCP has 377 stars, while semble has 4.5k stars.
Which is better, STS2MCP or semble?
The best choice depends on your use case. Choose STS2MCP if AI agents autonomously playing Slay the Spire 2, and semble if Enhancing AI agents (e.g., Claude Code, Cursor, Codex) with fast and accurate code search capabilities.
Is STS2MCP free or open source?
Yes, STS2MCP is open source on GitHub (MIT).
Is semble free or open source?
Yes, semble is open source on GitHub (MIT).
→

Related

Alternatives to STS2MCP →Alternatives to semble →STS2MCP details →semble details →
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
QYSGitHubBuy me a coffee ☕

Browse by Category

Code AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.