io.github.AsterMindAI/astermind-mcp
AsterMind MCP
On-device reranking that cuts RAG context tokens ~67% while keeping a relevant passage.
alive probed 2026-10-15
10tools
2.3ktokens in Claude Opus 5.5
2.4ktokens in Claude Code
1.1 %of a 200k context window
1.3ko200k_base estimate
455 msto initialize
7 msto list tools
- Run it
- npx -y @astermind/astermind-mcp@0.1.0 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- astermind-mcp 0.1.0
- Capabilities
- tools
- Instructions
- none
- Claude count
- Claude Opus 5.5, measured 2026-10-15. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/AsterMindAI/astermind-mcp
- Website
- https://astermindai.com
- Registry
- active, updated 2026-09-25 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| classify_text | 178 | 14 % |
| filter_context | 170 | 14 % |
| rerank_documents | 168 | 13 % |
| estimate_savings | 141 | 11 % |
| compress_context | 130 | 10 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.AsterMindAI/astermind-mcp)
An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.