Developer · Local MCP server
Ai Optimizer
MCP server that cuts AI coding agent token usage via framework-aware context optimization.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.shivam-app-developers/ai-optimizer- Version
- 0.1.0
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- npm
- Published
- 2026-06-06
- Updated
- 2026-06-06
- Publisher
- shivam-app-developers (GitHub)
- Repository
- github.com/shivam-app-developers/ai-optimizer
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npm | @ai-optimizer/core | 0.1.0 | stdio |
How to connect Ai Optimizer
Ai Optimizer runs locally from a Node.js package published to the npm registry: @ai-optimizer/core version 0.1.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx — the usual command is npx -y @ai-optimizer/core@0.1.0. It reads these environment variables: AI_OPTIMIZER_LICENSE (secret), AI_OPTIMIZER_LSP and AI_OPTIMIZER_TELEMETRY; set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"ai-optimizer": {
"command": "npx",
"args": [
"-y",
"@ai-optimizer/core@0.1.0"
],
"env": {
"AI_OPTIMIZER_LICENSE": "<secret>",
"AI_OPTIMIZER_LSP": "<value>",
"AI_OPTIMIZER_TELEMETRY": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More developer servers
| Server | Runs |
|---|---|
| Ai Model ExperimentsAI Model Experiments MCP ('Model Lab') — run the same prompts across many. | Remote · HTTP |
| Ai Model License LintReads the open-weight model IDs in your code and names the licence clause that binds you - 22 rules. | Local · stdio |
| Ai Model Retirement LintFinds the LLM model IDs pinned in your code that vendors have already switched off, or have dated to. | Local · stdio |
| AI Model WatchPrices, context windows, lifecycle and deprecation dates for 270+ AI/LLM models. Daily, no key. | Local · stdio |
| AI Price IndexRead-only, zero-key MCP server for point-in-time AI model API prices. Open data, CC BY 4.0. | Local · stdio |
| Ai Quality GateKill the Junior AI Era. Level up AI code to automatically Principal standards. Quality Gate. | Local · stdio |
| Ai RRead local AI agent sessions (Claude Code, Codex, OpenCode, Antigravity, Pi): intents, plans, tools. | Local · stdio |
| AI ScannerScan codebases for LLM/AI SDK usage, exposed API tokens, and hardcoded secrets. | Local · stdio |