edgar-fair-access

edgar-fair-access is a cursor rule for Cursor from SebAustin/mcp-financial-data. It costs 0 tokens per session (422 once invoked), scanned A, original, MIT.

A set of coding rules for accessing EDGAR, the U.S. Securities and Exchange Commission’s public company-filing database, while following its Fair Access policy.

In plain words
What is it for?
It guides code that downloads SEC company submissions, financial facts, and archived filings, including related configuration and tests.
Why use it?
It prevents requests from being rejected or your IP address being blocked by enforcing the required User-Agent, request rate, retries, and caching rules.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit It guides code that downloads SEC company submissions, financial facts, and archived filings, including related configuration and tests.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/sebaustin/mcp-financial-data/edgar-fair-access
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.

Clone the repo
git clone --depth 1 https://github.com/SebAustin/mcp-financial-data

Made for: Cursor.

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 edgar-fair-access

README.md
[![agentmods](https://agentmods.dev/badge/rules/sebaustin/mcp-financial-data/edgar-fair-access.svg)](https://agentmods.dev/rules/sebaustin/mcp-financial-data/edgar-fair-access)
Your own site
<a href="https://agentmods.dev/rules/sebaustin/mcp-financial-data/edgar-fair-access"><img src="https://agentmods.dev/badge/rules/sebaustin/mcp-financial-data/edgar-fair-access.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 422 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00422
Opus 5 $0.00000 $0.00211
Sonnet 5 $0.00000 $0.00084
Haiku 4.5 $0.00000 $0.00042

Measured 6d ago against content hash 0bea6f15ce1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

edgar-fair-access 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.

.cursor/rules/edgar-fair-access.mdc · 37 lines

What it actually says

EDGAR Fair Access compliance

The SEC publishes a Fair Access policy for the EDGAR public APIs. Violation gets your IP banned. We treat compliance as a hard build constraint.

Hard rules

  1. User-Agent header is required and sourced from env.
    • Env var: EDGAR_USER_AGENT.
    • Format: "<Sender Name> <[email protected]>".
    • Missing or empty UA → raise EdgarConfigError BEFORE any HTTP call.
  2. Rate limit ≤ 10 requests / second across the process.
    • Implement with a single shared asyncio.Semaphore(10) plus a token-bucket timer; do NOT rely on per-task throttling.
  3. Retries.
    • Use tenacity with exponential backoff on 429 / 5xx.
    • Maximum 3 retries, total wait ≤ 8 s.
  4. Caching.
    • Cache GET responses for ≥ 24 h in Postgres (evals/.cache.sqlite for local CI). Key on full URL + Accept header.
  5. Endpoints used.
    • https://data.sec.gov/submissions/CIK{...}.json
    • https://data.sec.gov/api/xbrl/companyfacts/CIK{...}.json
    • https://www.sec.gov/Archives/edgar/data/{CIK}/{accn}/{file}
    • All other endpoints require an ADR before use.
  6. Tests.
    • One test asserts the UA header is present and matches the env value.
    • One test asserts that 10 concurrent calls take ≥ 0.9 s wall-clock (rate-limit smoke).
    • One test asserts a 429 response triggers exactly one retry path.
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 · 37 lines · 0 tokens per session scan A 0bea6f15ce1d

Subscribe to this mod's changes

edgar-fair-access is a cursor rule published in the GitHub repository SebAustin/mcp-financial-data (0 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 422 tokens. 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.