mcpcost

io.github.qianqiuwanzi/hypermarrow-mcp

hypermarrow-memory

Is the io.github.qianqiuwanzi/hypermarrow-mcp MCP server down? No. It answered initialize and tools/list in the probe of 2026-10-30.

Local-first AI memory MCP server. Record, recall and consolidate memory on your own machine.

alive probed 2026-11-15 · unchanged since 2026-10-30

4tools
513tokens in Claude Opus 5.5
0.3 %of Claude's 200k window
0.2×the median server
327 msto initialize
5 msto list tools
Run it
npx -y hypermarrow-mcp@0.1.1 (stdio, probed in a container with the network off)
Host
npmjs.com
Reports itself as
hypermarrow-memory 0.1.0
Capabilities
tools
Instructions
none
Of a 1M window
<0.1 % of a 1M context window
Count
513 tokens in Claude Opus 5.5, exact, measured 2026-10-16. With the Claude Code prefix mcp__…__ on each tool name: 573. The o200k_base estimate is 279. Counted again when the tool definitions change. Method.
Repository
https://github.com/qianqiuwanzi/hypermarrow-mcp
Website
https://hm.qianshi.cool/
Registry
active, updated 2026-09-26 · registry entry

Most expensive tools

The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 1.84×.

Tool≈ Claude tokenso200k estimateShare of this server
record_context1779634 %
file_anchor1588631 %
recall_memory1055720 %
consolidate744014 %

Compare this server with others.

More servers

Other registry entries on npmjs.com, the ones next to this name; all of them.

Servers that mention hypermarrow or consolidate or machine.

Badge for the README

mcpcost: alive

The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.

Atom feed

A mail when this server changes

Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.

For the publisher