What is alpha_vantage_mcp CLAUDE.md?

A project instruction file for an Alpha Vantage MCP server, which lets AI tools access financial data from Alpha Vantage. It documents the code layout, technologies, development commands, and recurring patterns.

Use it when developing, running, deploying, or extending the server, command-line tool, analytics pipeline, web viewer, or related examples.

It gives a coding agent the project context it needs to work consistently, instead of making it rediscover the structure and setup each time.

How alphavantage/alpha_vantage_mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to alphavantage/alpha_vantage_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/alphavantage/alpha_vantage_mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/alphavantage/alpha_vantage_mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/alphavantage/alpha_vantage_mcp/claude-md/github.svg)](https://agentmods.dev/instructions/alphavantage/alpha_vantage_mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/alphavantage/alpha_vantage_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/alphavantage/alpha_vantage_mcp/claude-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/alphavantage/alpha_vantage_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/alphavantage/alpha_vantage_mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,101 This file is loaded in full into every session.

When invoked 1,101 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	$0.01101	$0.01101
Opus 5.5	$0.00440	$0.00440
Sonnet 5.5	$0.00220	$0.00220
Haiku 4.5	$0.00110	$0.00110

Measured 2mo ago against content hash 49d6ff99d5f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

alpha_vantage_mcp 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 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.

CLAUDE.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Alpha Vantage MCP Server

Official MCP server exposing Alpha Vantage financial data APIs (100+ endpoints) to LLMs.

Project Structure

Monorepo using uv workspace:

api/ — Shared API client library (alphavantage-core): HTTP client, tool registry, context vars
mcp/ — MCP server (stdio + Lambda HTTP): direct tool exposure, OAuth 2.0
cli/ — CLI tool (marketdata-cli): terminal access via Click
analytics/ — AWS analytics pipeline: log compaction, CloudWatch → S3 → Athena
examples/agent/ — OpenAI Agents example with session persistence
web/ — Next.js 15 artifacts viewer site (S3 + CloudFront deployment)
skills/ — Y-Agent skill definitions
scripts/ — Deployment and infrastructure scripts

Tech Stack

Python 3.13+, async/await throughout
uv package manager, hatchling build backend
AWS SAM for Lambda deployment (us-east-1)
Next.js 15 + Tailwind 4 for web
Key deps: mcp>=1.12.3, httpx, click, loguru, python-dotenv

Development

uv sync                                    # Install all deps
uv run marketdata-mcp-server $API_KEY      # Run stdio server
uv run marketdata-cli global_quote AAPL    # Run CLI
uv run pytest                              # Run tests

Key Patterns

Direct Tool Exposure

All ~100 real Alpha Vantage tools are listed directly as normal MCP tools in both the stdio and Lambda paths, with direct tools/call dispatch. Clients do their own (client-side) discovery over the listed tools. Each tool carries behavior hints (readOnly/destructive/openWorld), a derived human-readable title, and a permissive outputSchema (with matching structuredContent). The legacy TOOL_LIST/TOOL_GET/TOOL_CALL meta-tools (mcp/src/av_mcp/tools/meta_tools.py) are additively registered alongside the flat catalog in both transports, for backward compatibility with historical clients that still have them cached.

Tool Definition

Tools defined with @tool decorator in api/src/av_api/tools/ by category
Names auto-converted to UPPERCASE_WITH_UNDERSCORES
Entitlement parameter added dynamically for delayed vs. realtime data

Read the full file on GitHub · 83 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.

2mo ago First seen · 83 lines · 1,101 tokens per session scan A 49d6ff99d5f0

Subscribe to this mod's changes

alpha_vantage_mcp CLAUDE.md is an instructions file published in the GitHub repository alphavantage/alpha_vantage_mcp (226 stars, last pushed 1mo ago), licensed MIT. It adds 1,101 tokens to every session, about $0.0044 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 2026-08-30.

Finance and fintech

alpha_vantage_mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
alpha_vantage_mcp CLAUDE.mdalphavantage/alpha_vantage_mcp	Instructions file	226	1mo ago	MIT	A	1,101	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

alpha_vantage_mcp: Instructions file for Claude Code