What is freshrss-mcp AGENTS.md?

Project instructions for freshrss-mcp, a server that connects FreshRSS to AI agents through the Streamable HTTP version of MCP. It covers the project structure, architecture, setup, and issue tracking.

Use it when developing or operating the FreshRSS server, its feed and article tools, YouTube transcript support, configuration, or deployment.

It gives developers the information needed to understand, run, and modify the project correctly.

How zhiyuan7/freshrss-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to zhiyuan7/freshrss-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/zhiyuan7/freshrss-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/zhiyuan7/freshrss-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/zhiyuan7/freshrss-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/zhiyuan7/freshrss-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/zhiyuan7/freshrss-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/zhiyuan7/freshrss-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/zhiyuan7/freshrss-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/zhiyuan7/freshrss-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,228 This file is loaded in full into every session.

When invoked 1,228 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	$0.01228	$0.01228
Opus 5	$0.00614	$0.00614
Sonnet 5	$0.00246	$0.00246
Haiku 4.5	$0.00123	$0.00123

Measured 8d ago against content hash 0663468eadea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

freshrss-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 8d 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 · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

This project uses bd (beads) for issue tracking. Run bd onboard to get started.

What This Project Is

FreshRSS MCP server using Streamable HTTP transport. It wraps the FreshRSS Google Reader API and exposes 12 MCP tools for feed management, full-article extraction, and YouTube transcripts.

Transport: Streamable HTTP (POST to /mcp) -- NOT stdio. The OpenClaw MCP bridge discovers tools via HTTP POST with JSON-RPC 2.0, not by spawning a subprocess.

Runtime: Python 3.12+, managed by uv. Deployed on NixOS as a systemd service.

Project Layout

freshrss-mcp/
  pyproject.toml          # uv/PEP 621 — entry point: freshrss-mcp
  uv.lock                 # Committed lockfile
  .python-version         # 3.13
  flake.nix               # Dev shell + NixOS module (systemd service)
  src/freshrss_mcp/
    server.py             # FastMCP entry point (streamable-http transport)
    tools.py              # 10 MCP tool definitions with error boundaries
    client.py             # FreshRSS Google Reader API client (async, httpx)
    config.py             # pydantic-settings config from env vars
    models.py             # Article and Feed dataclasses
    article_fetcher.py    # Public-only article fetch and readable-text extraction
    youtube_transcript.py # Supadata transcript client and persistent cache
  tests/                  # 90 unit tests
    test_config.py        # Config validation, defaults, secret masking
    test_client.py        # Auth, feeds, articles, ID extraction, edge cases
    test_tools.py         # Every tool happy path + error boundary
    test_models.py        # Serialization, construction, mutability

Key Architecture Decisions

Lazy authentication: client.py calls _ensure_authenticated() before every API method. No need to pre-auth at startup.
Error boundaries: Every tool in tools.py catches all exceptions and returns "Error: ..." strings. MCP protocol never sees uncaught exceptions.

Read the full file on GitHub · 143 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.

8d ago First seen · 143 lines · 1,228 tokens per session scan A 0663468eadea

Subscribe to this mod's changes

freshrss-mcp AGENTS.md is an instructions file published in the GitHub repository zhiyuan7/freshrss-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 1,228 tokens to every session, about $0.0061 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.

ai-agents freshrss mcp raspberry-pi rss youtube-transcripts

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

freshrss-mcp: Instructions file for Codex