FRENES

Memory and knowledge · MCP server

Weighted compact: MCP server, setup and security

Weighted compact is an open-source MCP server published on GitHub that lets an AI agent search and compact Claude Code sessions from local project logs. Its repository has 5 stars and its last commit is from June 10, 2026 and it is licensed under MIT.

Score
40/100
Adoption (stars) 7/40
Maintenance 18/30
Framework (licence, registry, official) 15/30
Last commit 5 months ago

What Weighted compact does

According to its repository: “Inspectable memory for Claude Code: read-only search and session compaction over a local, signal-scored parse of its project logs, with no outbound calls.”

The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. Weighted compact is listed under Memory and knowledge, a category of 250 servers in the directory, where it ranks #245 by stars.

Topics declared by the repository: claude-code, local-first, ollama, ai-memory, anthropic-claude, claude-code-plugin.

Installing and connecting Weighted compact

No package or remote server is declared in the official MCP registry: you install it from source, following the repository README.

It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: Python.

Security: what to check

Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.

None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to Weighted compact. That does not replace reading the code.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on May 16, 2026, the zzallirog/weighted-compact repository has 5 stars and 1 forks, with 24 open issues. It has more stars than 13% of the servers in the directory. Last change 5 months ago.

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

Context7Context7 : 63.6K63.6KHindsightHindsight : 53.4K53.4KCogneeCognee : 32.7K32.7KSkill SeekersSkill Seekers : 15.2K15.2KHonchoHoncho : 7.8K7.8KBasic memoryBasic memory : 4.3K4.3KNoteDiscoveryNoteDiscovery : 2.8K2.8KMemantoMemanto : 2.3K2.3KWeighted compactWeighted compact : 55
GitHub stars of the most followed servers in the category (log scale); Weighted compact in orange. Checked October 25, 2026.

Verdict

Weighted compact is still a modest project: read its code and compare it with the alternatives before using it.

Strengths

  • Permissive licence (MIT)

Limitations

  • Few visible users
  • Install from source

Frequently asked questions

How do I install Weighted compact?

No package is declared in the MCP registry: clone the zzallirog/weighted-compact repository, follow its README, then declare the start command in your client's MCP configuration.

Is Weighted compact free?

The code is published under the MIT licence and can be used free of charge.

Is Weighted compact safe?

No risk signal found (system access, secrets, licence, abandonment). As with any MCP server, keep rights minimal and read the code before sensitive use.

Is it an official server?

Nothing says so: it is a project published by zzallirog on GitHub. Check who maintains it before giving it access.

What are the alternatives to Weighted compact?

In the same category: Context7, Basic memory, Hindsight, and Cognee. Context7 and Basic memory score higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score