What is edgarmcp CLAUDE.md?

A Claude Code instruction file for edgarmcp, a local server that reads and searches SEC EDGAR company filings. SEC EDGAR is the U.S. regulator's public database of company reports.

Use it to install and run edgarmcp, connect it to Claude Code, search filings, read documents, view financial data, and understand its cache and file-loading structure.

It documents setup and operating modes so the server can be run consistently and connected to Claude Code.

How lucasastorian/edgarmcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lucasastorian/edgarmcp. 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/lucasastorian/edgarmcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/lucasastorian/edgarmcp

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/lucasastorian/edgarmcp/claude-md/github.svg)](https://agentmods.dev/instructions/lucasastorian/edgarmcp/claude-md)

Your own site

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

Per session 840 This file is loaded in full into every session.

When invoked 840 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	$0.00840	$0.00840
Opus 5	$0.00420	$0.00420
Sonnet 5	$0.00168	$0.00168
Haiku 4.5	$0.00084	$0.00084

Measured 9d ago against content hash acda1f944dab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

edgarmcp 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 9d 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 · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

edgarmcp

Standalone, zero-infrastructure SEC EDGAR MCP server. 5 tools: get_filings, read_document, search_filings, view_financials, search_edgar.

Setup

uv venv .venv
source .venv/bin/activate
uv pip install -e "."
export EDGAR_IDENTITY="Your Name [email protected]"

Package manager: uv — always use uv pip install, never bare pip.

Running

# stdio (default, for Claude Code)
python -m edgarmcp

# streamable HTTP (localhost)
python -m edgarmcp --http --port 8000

# public HTTP (auto-generates API key)
python -m edgarmcp --http --host 0.0.0.0 --port 8000

# Add to Claude Code
claude mcp add edgarmcp -- python -m edgarmcp

Architecture

src/edgarmcp/server.py — FastMCP setup, imports + registers all tools
src/edgarmcp/types.py — FormType, AttachmentType, SectionType, StatementType, ReportType
src/edgarmcp/company.py — Ticker/CIK/name → edgartools Company + L2 cached resolution
src/edgarmcp/cache.py — L1 LRU cache for parsed filings + accession→filing map
src/edgarmcp/storage.py — L2 persistent cache backend (FilesystemCache or S3Cache)
src/edgarmcp/filing_loader.py — Load HTML → sec2md parse → sections/notes/attachments + L2 cache
src/edgarmcp/sections.py — Section type mappings + extraction via sec2md
src/edgarmcp/attachment_types.py — Exhibit classification (EX-99→press_release, etc.)
src/edgarmcp/auth.py — API key auth middleware + /health + citation/filing HTML serving
src/edgarmcp/tools/ — One file per tool
src/edgarmcp/financials/ — Statement merger (Q4 inference, YTD, splits, TTM) + formatter
Dockerfile + railway.json — Remote deployment to Railway

Key design decisions

All tools return str (markdown) — no structured_content
Standalone — copies logic from intellifin, does not import it
accession_to_filing mapping lets read_document resolve filings without re-querying
Two-level cache: L1 in-memory LRU (~20 filings), L2 persistent (filesystem or S3). SEC filings are immutable — no TTL.
BM25 via rank-bm25 — no GPU/API needed
Auto-generated API key when binding publicly (0.0.0.0). Auth required on MCP endpoints; /health, /cite/, /filing/ are public.
Citations work remotely — filing HTML served through main ASGI app via /cite/ and /filing/ routes. Set EDGARMCP_BASE_URL for remote citation links.

Read the full file on GitHub · 63 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.

9d ago First seen · 63 lines · 840 tokens per session scan A acda1f944dab

Subscribe to this mod's changes

edgarmcp CLAUDE.md is an instructions file published in the GitHub repository lucasastorian/edgarmcp (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 840 tokens to every session, about $0.0042 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.

Documents LLM PDF Research claude mcp model-context-protocol sec-edgar

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

edgarmcp: Instructions file for Claude Code