agentmods.dev

mcp-litellm-searxng: Instructions file for Codex

AGENTS.md

mcp-litellm-searxng AGENTS.md is an instructions file for Codex, OpenCode from semidark/mcp-litellm-searxng. It costs 389 tokens per session, scanned A, original, MIT.

A set of project instructions for a small Node.js MCP server that provides one web-search tool. It explains the code layout, required Node version, commands, and environment settings.

In plain words
What is it for?
Use it when modifying, testing, or releasing this web-search MCP server. It is especially relevant for keeping version values aligned and diagnosing startup or test failures.
Why use it?
It tells an AI coding agent how the project is structured and how to verify changes, including the external settings needed for its integration test.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is semidark/mcp-litellm-searxng's own configuration. It tells Codex and OpenCode how to work on mcp-litellm-searxng itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-litellm-searxng configures →

not rated 0repo 5mo ago A scan 389 tokens original MIT
View source ↗ semidark/mcp-litellm-searxng
Reuse

Borrowing it

Nothing to install: this file belongs to semidark/mcp-litellm-searxng. 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/semidark/mcp-litellm-searxng/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/semidark/mcp-litellm-searxng

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.

agentmods badge for mcp-litellm-searxng AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/semidark/mcp-litellm-searxng/agents-md/github.svg)](https://agentmods.dev/instructions/semidark/mcp-litellm-searxng/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/semidark/mcp-litellm-searxng/agents-md"><img src="https://agentmods.dev/badge/instructions/semidark/mcp-litellm-searxng/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.

agentmods 80×15 button for mcp-litellm-searxng AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/semidark/mcp-litellm-searxng/agents-md"><img src="https://agentmods.dev/badge/instructions/semidark/mcp-litellm-searxng/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 389 This file is loaded in full into every session.
When invoked 389 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00389 $0.00389
Opus 5.5 $0.00156 $0.00156
Sonnet 5.5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured 2mo ago against content hash f33675afa00b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-litellm-searxng 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 2mo 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 · 26 lines

What it actually says

Overview

  • Single-package npm repo. No build, lint, typecheck, or CI config is present.
  • Runtime entrypoint is root index.js; published package only includes index.js, README.md, and LICENSE.
  • Node requirement is >=18; package is ESM ("type": "module").

Code Shape

  • The whole MCP server lives in index.js.
  • It registers exactly one tool, web_search, over stdio using @modelcontextprotocol/sdk.
  • VERSION is hardcoded in index.js and also stored in package.json; keep both in sync when bumping releases.

Verification

  • npm start runs the server directly: node index.js.
  • npm test runs the only repo-local test harness: node test.js.
  • test.js is an integration test against a real LiteLLM endpoint, not a unit test. It requires LITELLM_SEARCH_URL and LITELLM_API_KEY in the environment and will fail fast without them.

Gotchas

  • Server startup exits immediately if LITELLM_SEARCH_URL or LITELLM_API_KEY is missing.
  • LITELLM_TIMEOUT_MS defaults to 30000; timeout behavior is implemented in index.js with AbortController.
  • test.js resolves the repo root from import.meta.url; keep it portable if you refactor file layout.
  • structuredContent.results intentionally returns the raw result array while content carries the formatted text block.
  • npx -y @semidark/mcp-litellm-searxng works from outside the repo, but npm 11 on Node 25 can mis-resolve it when run from inside this package checkout. Use an isolated --prefix when testing the published package locally.
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.

  1. 2mo ago First seen · 26 lines · 389 tokens per session scan A f33675afa00b

Subscribe to this mod's changes

mcp-litellm-searxng AGENTS.md is an instructions file published in the GitHub repository semidark/mcp-litellm-searxng (0 stars, last pushed 5mo ago), licensed MIT. It adds 389 tokens to every session, about $0.0016 per session on Opus 5.5. 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.

Research
Related

mcp-litellm-searxng AGENTS.md compared with instructions from other repositories

mcp-litellm-searxng AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-litellm-searxng AGENTS.mdsemidark/mcp-litellm-searxngInstructions file05mo agoMITA389Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode