modelcontextprotocol / modelcontextprotocol/servers

Huge memory occupation by sequentialthinking MCP

Open
#2,912 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug server-sequentialthinking
Dominant language
TypeScript
Stars
90.5k
Forks
11.7k
Avg merge
2d 2h
Merged PRs (30d)
5

Description

Describe the bug

After using sequentialthinking for a few hours, the RAM gets hogged up by this MCP server as much as 10GB+ RAM or more (I had this much RAM available, so..). But I doubt it is the Planning, because 10+ GB of Text is a huge amount of text, I DON'T THINK it was the TEXT. I strongly think there is a memory leak.

To Reproduce

  1. Use this MCP for a few (6-8) hours for frequent and long planning

Expected behavior
The memory should be freed after a job is done, or the memory should be offloaded to a disk space after a certain period of time. This should also help with persistent planning (Maybe, add a new tool for this).

Additional context
I have deployed this MCP as a distributed, standalone Docker container.

I love this MCP, a really great project. MANY MANY THANKS to the modelcontextprotocol Team
Regards

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the sequentialthinking workload in the reported standalone Docker deployment for 6–8 hours while profiling memory. Compare memory use across repeated planning jobs; done means confirming and localizing the leak or documenting that memory is released as expected, with a focused regression check.

Written by the indexing model from the issue text.

Assessment

Tech stack
docker, typescript
Domain
backend
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
32/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.