MCP servers · anuj7411

Sipcode: context hygiene and token analytics for Claude Code (MCP)

A command-line tool that watches Claude Code context for bloat and duplicate file reads, and reports token use and spend.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

Sipcode is a command-line tool that runs alongside Claude Code. It monitors the context window, warns when it starts to bloat, and intercepts duplicate file reads and other waste before they reach Claude. Each saving is reported in the terminal. It is open source under the MIT license and makes no network calls during normal use.

It is relevant for long Claude Code sessions, where cost rises and answer quality can drop as the context fills. The drift command flags bloated context, repeated reads and stale signals in the latest session. The proxy stats command breaks down what was caught by each rewriter, and the today and forecast commands summarise daily spend and project month-end totals. The benchmark command runs a scripted corpus of 20 synthetic tasks, which gives a median reduction of 62.6%. The impact command measures the effect on a user's own sessions.

Sipcode is installed as a global npm package. Once installed, new Claude Code sessions use it automatically, and the drift output confirms that it is active. It also reads OpenAI Codex CLI session logs for spend analytics and usage limits, without changing how Codex works.

Limitations and requirements

The 62.6% figure comes from synthetic transcripts pairs, not live sessions, so actual savings depend on the user's workload and must be measured with the impact command. For Codex, Sipcode only reports spend and usage limits and has no hook; it reads session logs from ~/.codex folders (or the CODEX_HOME path) and does not read Cursor logs. Installation requires npm.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    Sipcode

    Context hygiene for Claude Code: drift detection, re-read dedup, and token analytics.

    v1.7.1
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
awslabs

MCP servers for AWS (AWS Labs)

A large open-source collection of MCP servers from AWS Labs for building and operating on AWS: documentation, infrastructure, databases, AI services, cost and more.

9.9K GitHub starsCloud & DevOpsData & databases
Updated 17 Nov 2026
MCP servers
microsoft

Playwright MCP (browser automation)

Microsoft's MCP server that lets an AI assistant open web pages, click, type and read them through a real browser, using the page structure instead of screenshots.

39.6K GitHub starsTesting & QAWeb, search & browser
Updated 18 Nov 2026
MCP servers
docker

Docker Hub MCP Server

Docker's MCP server that helps an AI assistant find and compare container images on Docker Hub and, with your token, manage your own repositories and tags.

171 GitHub starsCloud & DevOpsSoftware development
Updated 13 Nov 2026
MCP servers
cloudflare

Cloudflare MCP servers

Cloudflare's hosted MCP servers for its products: documentation search, sandbox containers, browser rendering, Radar internet data, logs and analytics, Workers and more.

4.5K GitHub starsCloud & DevOpsSoftware development
Updated 18 Nov 2026
Sipcode: context hygiene and token analytics for Claude Code (MCP) | AI Gate Discover