io.github.wjabanjj/aifp-mcp
AiFP 记忆感知系统
Persistent memory MCP server for AI coding assistants. Chinese-first and fully local.
alive probed 2026-10-15
33tools
6.7ktokens in Claude Opus 5.5
7.1ktokens in Claude Code
3.4 %of a 200k context window
4.0ko200k_base estimate
331 msto initialize
177 msto list tools
- Run it
- npx -y aifp-mcp@1.5.8 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- AiFP 记忆感知系统 1.5.8
- Capabilities
- resources, 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/wjabanjj/aifp-mcp
- Registry
- active, updated 2026-08-15 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| save_memory | 597 | 15 % |
| search_memories | 314 | 8 % |
| recall_context | 233 | 6 % |
| export_memories_md | 163 | 4 % |
| observe_turn | 137 | 3 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.wjabanjj/aifp-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.