agentmods.dev

fred-mcp AGENTS.md

fred-mcp AGENTS.md is an instructions file for Codex, OpenCode from zachspar/fred-mcp. It costs 600 tokens per session, scanned A, original, MIT.

Project instructions for a Python MCP server that provides economic data from FRED, the Federal Reserve Bank of St. Louis database. The instructions cover setup, required credentials, transport modes, testing, and dependency compatibility.

In plain words
What is it for?
Setting up FRED_API_KEY, starting the server through standard input or HTTP, running lint and tests, and understanding the server’s data domains and tool structure.
Why use it?
They explain how to run the server correctly and what reviewers or contributors must check before changing it.

Instructions file for CodexOpenCode

not rated 1 3mo ago A scan 600 tokens original MIT
View the source file zachspar/fred-mcp
Install

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.

agentmods
npx agentmods add instructions/zachspar/fred-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/zachspar/fred-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.

agentmods badge for fred-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zachspar/fred-mcp/agents-md.svg)](https://agentmods.dev/instructions/zachspar/fred-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zachspar/fred-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/zachspar/fred-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 600 This file is loaded in full into every session.
When invoked 600 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00600 $0.00600
Opus 5 $0.00300 $0.00300
Sonnet 5 $0.00120 $0.00120
Haiku 4.5 $0.00060 $0.00060

Measured 4d ago against content hash 25f99af8dfd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fred-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 4d 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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Cursor Cloud specific instructions

Overview

A Python MCP server (v1.0.0) for FRED economic data built on FastMCP 3.x. Exposes 31 tools across five domains (series, categories, releases, sources, tags) via fastmcp wrapping fred-py-api. Single-service project with no databases or external infrastructure beyond the FRED API.

Required secrets

Running the server

# streamable-http mode (preferred for testing, default in Docker)
FRED_API_KEY=$FRED_API_KEY MCP_SERVER_TRANSPORT=streamable-http MCP_SERVER_PORT=8000 MCP_SERVER_HOST=0.0.0.0 fred-mcp

# stdio mode (default, for MCP client integration)
FRED_API_KEY=$FRED_API_KEY fred-mcp

The streamable-http endpoint is at http://localhost:8000/mcp.

Linting and testing

Per the README Development section:

ruff check src tests
pytest

Dependency compatibility

When installing, fastmcp-slim (a dependency of fastmcp) must install its source .py files alongside .pyc files. If from fastmcp.exceptions import ToolError fails with ModuleNotFoundError, run:

pip install --force-reinstall fastmcp-slim fastmcp

This resolves a packaging race condition where .py source files are missing from the fastmcp/ namespace directory.

Project layout

src/fred_mcp/
  main.py              — Entry point, mounts sub-servers, transport config
  config.py            — Settings dataclass, env var parsing
  credentials.py       — API key resolution (env var or HTTP header)
  series/tools.py      — 10 series tools
  categories/tools.py  — 6 category tools
  releases/tools.py    — 9 release tools
  sources/tools.py     — 3 source tools
  tags/tools.py        — 3 tag tools
  common/tools.py      — Shared call_fred helper
  common/errors.py     — ToolError wrapper
  common/types.py      — TypeAlias definitions for FRED API parameters
tests/
  test_tools.py        — Series tool tests + 31-tool count assertion
  test_credentials.py  — API key resolution and settings tests
  test_modules.py      — Parametrized module delegation tests
pyproject.toml         — Build config, dependencies, ruff/pytest config
Dockerfile             — Alpine-based container image

Read the full file on GitHub · 66 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.

  1. 4d ago First seen · 66 lines · 600 tokens per session scan A 25f99af8dfd6

Subscribe to this mod's changes

fred-mcp AGENTS.md is an instructions file published in the GitHub repository zachspar/fred-mcp (1 stars, last pushed 3mo ago), licensed MIT. It adds 600 tokens to every session, about $0.0030 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.

FREDfred-apimcppython-mcp
Related

Other instructions, from other repositories

tako-mcp AGENTS.md

AGENTS.md instructions for TakoData/tako-mcp, covering agents.md, project overview, build & run, hosted worker (typescript) and install.

TakoData/tako-mcp · 2,917 tokens

fred-mcp CLAUDE.md

Claude Code instructions for mcpwright/fred-mcp, covering fred-mcp — working agreement, non-negotiable policies and layout.

mcpwright/fred-mcp · 884 tokens

ferric-fred CLAUDE.md

Claude Code instructions for agpalindrome/ferric-fred, covering ferric-fred — claude code guidance, keep documentation current, repo settings are code, mcp quality review (glama) and deletion & creation.

agpalindrome/ferric-fred · 1,620 tokens

openecon-data AGENTS.md

AGENTS.md instructions for hanlulong/openecon-data, covering openecon agent guide, operating mode, engineering agreements, critical decision gate and semantic resolution rules.

hanlulong/openecon-data · 1,076 tokens

openecon-data CLAUDE.md

Claude Code instructions for hanlulong/openecon-data, covering claude.md, important: re-read after context compaction, critical rules, 1. service management — production vs dev and 2. oecd provider - low priority.

hanlulong/openecon-data · 4,071 tokens

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