Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/madelponte/mcp-server/agents-mdgit clone --depth 1 https://github.com/madelponte/mcp-serverWrote 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.
[](https://agentmods.dev/instructions/madelponte/mcp-server/agents-md)<a href="https://agentmods.dev/instructions/madelponte/mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/madelponte/mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.04115 | $0.04115 |
| Opus 5 | $0.02057 | $0.02057 |
| Sonnet 5 | $0.00823 | $0.00823 |
| Haiku 4.5 | $0.00411 | $0.00411 |
Grade A, and why
mcp-server 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repository guidance for coding agents and contributors.
What this is
A single FastMCP v3 server that bundles five tool groups — Agentic Web Search (the search_web and fetch_page tools, where fetch_page also returns YouTube video transcripts), Stock Data, Wolfram Alpha, Geocoding & Place Search (OpenStreetMap Nominatim + Overpass), and Email (send_email, send-only SMTP) — originally written as Open WebUI tools and ported to MCP. Default transport is streamable-http, reachable at http://<host>:8000/mcp.
The web tool group has two registered modules, tools/web_search.py and tools/fetch_page.py, plus helpers. tools/web_fetch.py owns SSRF-guarded provider transports, streamed direct-resource probing, Tika extraction, and the raw page cache. tools/page_acquire.py owns fetch_page's browser-first acquisition policy (FlareSolverr, quality assessment, optional hedged Firecrawl, and the host circuit breaker); tools/page_quality.py contains the deterministic quality gate and optional OpenAI-compatible classifier. tools/web_extract.py contains pure HTML→content helpers: markdown/plain-text rendering, structured metadata, single-section extraction, and reference-link resolution — [12]-style in-page citation markers are rewritten to their footnote's external source URL so a model can follow a page's references; the structured description falls back to JSON-LD and toc is the heading outline.
YouTube transcript retrieval used to be its own tool; it was folded into fetch_page (which detects a YouTube video URL and returns the transcript) so a model has one fewer tool to choose between. The logic still lives in tools/youtube_transcript.py, now exposed as the fetch_transcript / is_youtube_video_url helpers rather than a registered tool.
Commands
# Run locally (default streamable-http transport)
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env # then edit it
python server.py
# Run as a stdio MCP server instead (no network, no auth)
MCP_TRANSPORT=stdio python server.py
# Full stack incl. web-search support services (SearXNG, FlareSolverr, Tika)
docker compose up # Pull/start the stack; MCP at http://localhost:8000/mcp
# Server-only image (non-web tools have no local-service deps)
docker build -t openwebui-tools-mcp .
docker run --rm -p 8000:8000 --env-file .env openwebui-tools-mcp
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.
- 3d ago First seen · 84 lines · 4,115 tokens per session scan A 05d3de07d96a
mcp-server AGENTS.md is an instructions file published in the GitHub repository madelponte/mcp-server (0 stars, last pushed 4d ago), licensed MIT. It adds 4,115 tokens to every session, about $0.0206 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.
Other instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.