Ai Optimizer

io.github.shivam-app-developersPublished by GitHub account shivam-app-developersv0.1.0Updated Oct 24, 2026

MCP server that cuts AI coding agent token usage via framework-aware context optimization

VerifiedSTDIODesktop onlyDeveloper Tools AI & ML

Server details

Identifier: io.github.shivam-app-developers/ai-optimizer
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account shivam-app-developers for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.shivam-app-developers%2Fai-optimizer.svg)](https://sourceweft.com/mcp/io.github.shivam-app-developers%2Fai-optimizer?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Local MCP server that replaces an AI coding agent's file, search and diagnostics reads with framework-aware, token-saving versions.

What you can do: Read and list project files with framework-aware skipping, ignore globs and .gitignore, plus optional line slices
Search file contents with ignore filters, and read single symbols via LSP instead of whole files
Run language-server diagnostics and return errors with a narrow code window
Strip ANSI codes, build-tool progress and JVM warnings from shell output
Report detected frameworks, active packs and cumulative tokens saved
When to use it: Useful when an AI coding agent burns context on generated files, dependency folders and build output, or when you want cheaper, narrower reads in a large or framework-heavy repository. It is aimed at agents that speak MCP, such as Claude Code, Cursor, Cline or Zed.
Requirements: Runs as a local stdio process installed from the npm package @ai-optimizer/core (Node.js). An optional AI_OPTIMIZER_LICENSE key unlocks Pro/Team packs; the free tier needs no key. Language-server diagnostics need a matching LSP installed. License validation is the only network call.

Before you install

Pro and Team tiers are paid subscriptions, and the license key is passed in AI_OPTIMIZER_LICENSE. Optional features that change behavior or share data (scheduler, work-stealing, telemetry via AI_OPTIMIZER_TELEMETRY) are off by default and need explicit opt-in. The server intercepts file and shell reads, so review what it returns before trusting it in sensitive repositories.

Installation

In SourceWeft

Open Ai Optimizer in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

AI Token Optimizer

An MCP server that cuts AI coding-agent token usage by 60–80% via framework-aware context optimization.

[CI] [CodeQL] [npm] [License: MIT]

AI coding agents read whole files when they need 15 lines. They load *.g.dart, R.java, node_modules/, and dist/ into context — then do it again next turn. AI Token Optimizer is a Model Context Protocol server that intercepts those tool calls and strips framework noise before it reaches the model.

Works with anything that speaks MCP: Claude Code, Cursor, Cline, Continue, Zed, JetBrains AI, GitHub Copilot agent mode, Antigravity, Windsurf, OpenAI Codex CLI.

Quickstart

Then point your agent at the ai-optimizer stdio server. For Claude Code, add to ~/.claude/settings.json:

Or scaffold the config and preview your savings automatically:

bash

npx @ai-optimizer/init# "we'd skip 47 files, ~14K tokens/session, ~$0.42/session at Sonnet pricing"

npx @ai-optimizer/init# "we'd skip 47 files, ~14K tokens/session, ~$0.42/session at Sonnet pricing"

Full per-agent setup (Cursor, others), LSP install, and verification steps live in packages/core/README.md.

What it does

It registers tools the agent uses instead of its built-in file/dir/error reads:

Tool	What it saves
`optimized_read_file`	Framework-aware skip + optional line slice
`optimized_list_files`	Walks the tree applying ignore globs (+ `.gitignore`)
`optimized_grep`	Content search scoped by ignore filters
`optimized_diagnostics`	Spawns the right LSP, returns errors + a narrow code window
`read_symbol`	LSP `workspace/symbol` slice instead of a full-file read (Pro/LSP)
`strip_bash_noise`	Strips ANSI, npm/maven/gradle progress, JVM warnings
`optimizer_status`	Detected frameworks, active packs, cumulative tokens saved

When a project type is detected (e.g. Python via pyproject.toml), the matching pack's ignore rules activate automatically. .gitignore is respected on top.

Tiers

	Free (MIT core)	Pro ($9/mo)	Team ($29/seat)
Framework packs	Python, JS/TS	+ React, Flutter, Java, Kotlin, Go, Rust, C#, Swift, Ruby, Elixir, PHP, Solidity	all Pro packs
History compaction	—	✓	✓
Scheduler (`claude -p` cron)	—	✓	+ work-stealing across providers
Audit log + secret redaction + policy	—	—	✓

See PRICING.md. Behavior-changing or data-sharing features (scheduler, work-stealing, telemetry) are off by default and require explicit opt-in. Display-only features (dollar-value savings) default on.

Monorepo layout

Package	Purpose	Published
`packages/core`	MCP server + free packs	npm (MIT)
`packages/init`	`npx @ai-optimizer/init` config + savings preview	npm
`packages/sdk`	`definePack` plugin SDK	npm
`packages/context-mode-import`	Import `.contextmode` configs	npm
`packages/pro`	Pro/Team packs + scheduler + audit	private
`apps/landing`, `apps/dashboard`, `apps/vscode-extension`, `apps/license-server`	Site, local dashboard, IDE widget, license issuance	private
`tools/pack-bench`	Pack quality benchmark harness	private

Architecture details: ARCHITECTURE.md.

Development

bash

npm install            # at repo root (workspaces)npm run build          # build all packagesnpm test               # run all test suites

npm install            # at repo root (workspaces)npm run build          # build all packagesnpm test               # run all test suites

Security

Local-only by design — license validation is the only network call. Report vulnerabilities per SECURITY.md.

License

Core engine is MIT — see LICENSE. Pro/Team packs are proprietary.

Source: README.md at commit ef0a56a

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v0.1.0LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts
Declare a license in the repository or the registry entry.