Repository navigation
Description
Version
codebase-memory-mcp 0.7.0
Platform
macOS (Intel)
Install channel
npm
Binary variant
standard
What happened, and what did you expect?
Hi ,
I have been using using it for quite some time but after release of Fable 5 I saw this mcp used 5% , 10% or 20% jump when I asked Claude. I noticed even worst is when we are in the middle of some task and we hit the limit and once the reset happens and it starts working then it even some times consumed 50% of token in less than 5 min so I stopped using this map in Claude code by setting it in Claude.md and etc.
Fast forward till 2 days before we saw/seeing even now this (you might be aware of heavy drain of Codex tokens) heavy drain in GPT tokens , weekly is working like hourly drain and thing that has to work for week is exhausted in less than few hours in sol 5.6 medium too.,
Note I use this only in Claude & CODEX CLI VERSION. no other web/app only for coding purpose .
Now I have stopped using , if any fix for this please let me know.
Thanks & Regards,
Veeru
Reproduction
I have written above.
Regular use in Claudecode
Just one hit consumes 1% of 5hr .
More importantly what I noticed even drastic as mentioned in the above message :
when we are in the middle of some task and we hit the limit of Claude code CLI and once the reset to 100% happens and we start or ask it to continue , it starts working then it consumes upto50% of token in less than 5 min(I realised 1st time so noticed and intentionally tried at 99% and gave a task to see if it happens after token exhaust in next session and it was running like a minute/seconds of clock) so I stopped using this map in Claude code by setting it in Claude.md and etc.
Logs
Diagnostics trajectory (memory / performance / leak issues)
Project scale (if relevant)
No response
Confirmations
- I searched existing issues and this is not a duplicate.
- My reproduction uses shareable code (a dummy snippet or a public OSS repository), not proprietary code.
Activity
DeusData commentedon Jul 28, 2026
Thanks for raising this and for describing when the jump becomes visible. The reported CBM version is 0.7.0, which predates the current compact output path. On current main, search_graph emits grouped compact rows and blocks internal fingerprint/profile/body-token fields from agent output (src/mcp/mcp.c:3014-3025).
A client quota percentage does not identify which tool response caused the spend. Could you retest with 0.9.0 or the current 0.9.1 release candidate and provide one exact CBM tool name, its arguments, and the response byte size from a high-usage turn? That will let us separate CBM payload size from client/model accounting. Marked awaiting-reporter; thank you for helping pin it down.
github-actions commentedon Jul 28, 2026
Thanks for the report! To move this forward we need a bit more so we can reproduce it ourselves:
codebase-memory-mcp --versionyou're onOnce that's here we'll pick it straight back up. Heads-up: issues left
awaiting-reporterare automatically closed after a few weeks of silence, but a comment reopens the door anytime.github-actions commentedon Aug 19, 2026
This issue has been waiting on more information for 21 days (a version, exact steps, or a public repro), so it's now marked
stale. It will not be closed automatically — a maintainer reviews stale issues by hand. Adding a comment with the details clears the label and puts it straight back in the queue. We're happy to pick it back up the moment we can reproduce it.github-actions commentedon Sep 27, 2026
This issue has been waiting on more information for 21 days (a version, exact steps, or a public repro), so it's now marked
stale. It will not be closed automatically — a maintainer reviews stale issues by hand. Adding a comment with the details clears the label and puts it straight back in the queue. We're happy to pick it back up the moment we can reproduce it.Veerus007 commentedon Sep 27, 2026
DeusData commentedon Oct 19, 2026
Thank you, Veeru, for the additional reset/session scenario. That describes when the usage jump appears, but still does not identify a particular CBM response or its size. Please share the installed CBM version and one affected tool name, arguments, and response byte count from an existing example, with private content redacted; there is no need to deliberately exhaust another account quota for this.
github-actions commentedon Oct 20, 2026
Thanks for the report! To move this forward we need a bit more so we can reproduce it ourselves:
codebase-memory-mcp --versionyou're onOnce that's here we'll pick it straight back up. Heads-up: issues left
awaiting-reporterare automatically closed after a few weeks of silence, but a comment reopens the door anytime.DeusData commentedon Oct 25, 2026
Thank you for clarifying the reset scenario. One existing affected tool call, its arguments, response byte count and installed version are still needed; please do not deliberately exhaust another quota.
github-actions commentedon Nov 17, 2026
This issue has been waiting on more information for 21 days (a version, exact steps, or a public repro), so it's now marked
stale. It will not be closed automatically — a maintainer reviews stale issues by hand. Adding a comment with the details clears the label and puts it straight back in the queue. We're happy to pick it back up the moment we can reproduce it.