What is litellm-proxy-mcp AGENTS.md?

Repository instructions for a Node.js server that lets MCP clients call a deployed LiteLLM proxy. LiteLLM is a service that provides a common interface to different AI models and related endpoints.

Use them when working on the MCP server, its JavaScript code, or its forwarding of chat, model, embedding, image, speech, ranking, key, and health requests.

They document the server's purpose, communication method, development rules, and supported proxy operations. This gives an agent the context needed to modify or test it correctly.

How AbhishekMore-1/litellm-proxy-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to AbhishekMore-1/litellm-proxy-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/AbhishekMore-1/litellm-proxy-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/AbhishekMore-1/litellm-proxy-mcp

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/abhishekmore-1/litellm-proxy-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/abhishekmore-1/litellm-proxy-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/abhishekmore-1/litellm-proxy-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/abhishekmore-1/litellm-proxy-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/abhishekmore-1/litellm-proxy-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/abhishekmore-1/litellm-proxy-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 698 This file is loaded in full into every session.

When invoked 698 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00698	$0.00698
Opus 5	$0.00349	$0.00349
Sonnet 5	$0.00140	$0.00140
Haiku 4.5	$0.00070	$0.00070

Measured 9d ago against content hash 1696e2da3902, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

litellm-proxy-mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Antigravity AI Agent Instructions

Welcome to the litellm-proxy-mcp project. This document provides instructions for AI coding assistants (like Antigravity) working in this repository.

Project Overview

This is a Model Context Protocol (MCP) server written in Node.js (litellm-mcp-server.js). It connects an MCP client (such as Antigravity or Claude Desktop) to a deployed LiteLLM proxy instance.

Primary Language: JavaScript (Node.js)
Architecture:
- Uses @modelcontextprotocol/sdk to define the MCP Server and capabilities.
- Communicates via stdio transport.
- Forwards CallTool requests to the configured LITELLM_BASE_URL using native fetch.

Available Tools

The server currently implements the following tools, mapping directly to LiteLLM Proxy endpoints:

chat_completion (/chat/completions)
completion (/completions)
list_models (/models)
health_check (/health)
create_embedding (/embeddings)
model_info (/model/info)
create_image (/images/generations)
create_speech (/audio/speech)
rerank (/rerank)
key_generate (/key/generate)
key_info (/key/info)

Development Guidelines

Single File Approach: The core logic is intentionally kept in litellm-mcp-server.js for simplicity.
Error Handling: Ensure that errors from the LiteLLM API are caught and returned clearly within the MCP tool execution response (isError: true).
No External Fetch Libraries: We use native Node.js fetch (requires Node 18+). Do not install axios or node-fetch.
Binary Data Handling: Some LiteLLM endpoints (like /audio/speech) return binary data (e.g., MP3 audio) or images. The makeLiteLLMRequest function is designed to convert audio/* and image/* responses into Base64 encoded strings to pass over MCP.

Testing Locally

We use the native node:test runner. To run the test suite and verify the MCP tool registrations:

npm test

To run the server manually, you need to provide environment variables:

LITELLM_BASE_URL="https://your-litellm-url.com" LITELLM_API_KEY="sk-..." npx litellm-mcp-server

Read the full file on GitHub · 56 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 56 lines · 698 tokens per session scan A 1696e2da3902

Subscribe to this mod's changes

litellm-proxy-mcp AGENTS.md is an instructions file published in the GitHub repository AbhishekMore-1/litellm-proxy-mcp (6 stars, last pushed 6mo ago), licensed MIT. It adds 698 tokens to every session, about $0.0035 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

litellm-proxy-mcp: Instructions file for Codex