Ai Optimizer

Name: Ai Optimizer
Author: shivam-app-developers

by shivam-app-developerscommunityv0.1.0

An MCP server that intercepts file, directory, grep, diagnostics, and symbol-read tool calls from coding agents and filters framework-generated noise before sending context to the model. It supports automatic ignore rules for detected project types and can reduce token usage by narrowing reads and searches.

From the registry: MCP server that cuts AI coding agent token usage via framework-aware context optimization

GitHub Repository

Install & configure

Prerequisites

required
Install AI Token Optimizer
Install the MCP server package globally via npm so the `ai-optimizer` command is available.
```
$ npm install -g @ai-optimizer/core
```

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `ai-optimizer` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install AI Token Optimizer** — Install the MCP server package globally via npm so the `ai-optimizer` command is available. Run: `npm install -g @ai-optimizer/core`

Canonical MCP server config (stdio transport):
- command: `ai-optimizer`
- args: []

Note: The README explicitly says to point the agent at the `ai-optimizer` stdio server. It also mentions `npx @ai-optimizer/init` as an optional helper to scaffold client config and preview savings, but that is not the MCP server command itself. No required environment variables are documented in this README.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: The README explicitly says to point the agent at the `ai-optimizer` stdio server. It also mentions `npx @ai-optimizer/init` as an optional helper to scaffold client config and preview savings, but that is not the MCP server command itself. No required environment variables are documented in this README.

Tools (7)

optimized_read_file

Reads a file with framework-aware skipping and optional line slicing.

optimized_list_files

Lists files while applying ignore globs and .gitignore rules.

optimized_grep

Searches file contents with ignore filters applied.

optimized_diagnostics

Runs the appropriate language server and returns errors plus a narrow code window.

read_symbol

Returns a workspace symbol slice via LSP instead of reading the whole file.

strip_bash_noise

Removes ANSI output, build progress noise, and JVM warnings from bash command output.

optimizer_status

Reports detected frameworks, active packs, and cumulative tokens saved.

Packages

@ai-optimizer/core

npmv0.1.0transport: stdio

Details

Language: TypeScript
License: NOASSERTION
Released: Jun 6, 2026
Last commit: Jun 15, 2026
Registry name: io.github.shivam-app-developers/ai-optimizer

Related Servers

Claude Flow

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

65.2k

Codebase Memory Mcp

Persistent codebase knowledge graph. Survives session restarts and context compaction.

33.0k

Serena

A powerful toolkit for coding, providing semantic retrieval and editing capabilities.

26.6k