EODHD-MCP-Server CLAUDE.md

EODHD-MCP-Server CLAUDE.md is an instructions file for Claude Code from EodHistoricalData/EODHD-MCP-Server. It costs 1,785 tokens per session, scanned A, original, MIT.

A set of instructions for EODHD-MCP-Server, a service that gives AI clients access to financial-market data through 88 tools. It covers how the Python project is structured, run, tested, checked, and secured.

In plain words
What is it for?
Use it when developing, testing, formatting, type-checking, or security-scanning this financial-data server.
Why use it?
It gives a coding agent the project’s commands and working rules, reducing guesswork when changing or checking the server.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

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/eodhistoricaldata/eodhd-mcp-server/claude-md
Clone the repo
git clone --depth 1 https://github.com/EodHistoricalData/EODHD-MCP-Server

Made for: Claude Code.

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 EODHD-MCP-Server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/eodhistoricaldata/eodhd-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/eodhistoricaldata/eodhd-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/eodhistoricaldata/eodhd-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/eodhistoricaldata/eodhd-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,785 This file is loaded in full into every session.
When invoked 1,785 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 5.1 $0.01785 $0.01785
Opus 5 $0.00892 $0.00892
Sonnet 5 $0.00357 $0.00357
Haiku 4.5 $0.00178 $0.00178

Measured 6d ago against content hash 02acdf952ef3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

EODHD-MCP-Server CLAUDE.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 6d 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.

CLAUDE.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EODHD MCP Server v1

MCP server exposing 88 EODHD financial data API tools via HTTP, SSE, and stdio transports.

Stack

Python 3.10+, FastMCP >=3.4, httpx (async HTTP), Ruff, MyPy, pytest, Bandit, Semgrep, pip-audit

Commands

# Tests
pytest tests/auto/ -v --tb=short
pytest tests/auto/ -v --cov=app --cov-report=term-missing

# Lint & format
ruff check app/ server.py
ruff format --check app/ server.py

# Type checking
mypy app/ server.py --ignore-missing-imports --explicit-package-bases

# Security
bandit -r app/ -ll -ii -x app/resources/
semgrep scan --config p/python --config p/owasp-top-ten --config p/secrets --config p/jwt --error app/
pip-audit --ignore-vuln CVE-2026-4539

# Run server
python server.py
python server.py --stdio
python server.py --sse
python server.py --http --port 9000

Architecture

app/
  config.py           - env vars, API base URL
  api_client.py       - shared async httpx client, retry, rate-limit, auth injection
  input_formatter.py  - input sanitisation, date coercion, URL helpers
  response_formatter.py - MCP EmbeddedResource formatting and API error raising
  tools/              - 88 tool modules, each exports register(mcp)
    __init__.py       - ALL_TOOLS list, register_all(mcp), safe dynamic import
  prompts/            - example workflows
  resources/          - markdown reference docs exposed as MCP resources
server.py             - entry point, transport selection, argparse

Tool Categories

  • MAIN_TOOLS - core EODHD endpoints
  • MARKETPLACE_TOOLS - marketplace partner endpoints
  • THIRD_PARTY_TOOLS - praams, investverte partner tools

Conventions

  • Every tool file exports register(mcp: FastMCP).
  • All tools are read-only (readOnlyHint=True) except the three Praams report tools, which generate a report and email it to the caller-supplied address (readOnlyHint=False).
  • Sanitize inputs with helpers from app/input_formatter.py.
  • Raise ToolError for user-facing failures.
  • Route all HTTP traffic through make_request() in app/api_client.py.
  • Return MCP resources via response_formatter helpers, not raw json.dumps.
  • Preserve explicit upstream API errors; do not silently pass through {"error": ...} payloads as successful results.
  • No cross-tool imports.
  • No print() in app code; use logging.
  • Use X | None instead of Optional[X].

Read the full file on GitHub · 145 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. 6d ago First seen · 145 lines · 1,785 tokens per session scan A 02acdf952ef3

Subscribe to this mod's changes

EODHD-MCP-Server CLAUDE.md is an instructions file published in the GitHub repository EodHistoricalData/EODHD-MCP-Server (19 stars, last pushed 5d ago), licensed MIT. It adds 1,785 tokens to every session, about $0.0089 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 2026-08-30.

Related

Other instructions, from other repositories