MCP Tiers

The edgar.tools MCP server advertises a tier-aware tool list. When your AI client calls tools/list, it sees the tools your account's tier includes — not the full 23. The prompts/list endpoint behaves the same way for recipe prompts. Cross-tier invocations return a structured tier_denied envelope so the AI can route around it gracefully.

This page is the canonical mapping. The visual ladder lives at the AI plugin landing page; this page is the operational reference for engineers and analysts who need to know exactly what each tier exposes.

Source of truth. The mapping below mirrors src/lib/mcp-tier-map.ts in the open server. If a tool ships at a different tier than this page says, the server wins and the page is stale — file an issue.

Quick reference

Tier	Price	Tools advertised	Recipe prompts	Verb
Free	$0	4	0	Read
Pro	$24.99/mo	17 (Free + 13)	0	Track
Analyst	$79.99/mo	23 (Pro + 6)	5	Research
Builder	$499/mo · waitlist	23 (Analyst set, v1)	5	Run

Tools and prompts accumulate as you climb tiers — Pro sees Free's tools plus Pro's, Analyst sees everything below. Builder ships the same tool set as Analyst for v1; richer Builder-only tools (configurable presets, custom prompts) land later.

Free — 4 tools

The starter surface. Every account gets this; no payment required.

Tool	What it does
`search_companies`	Find any SEC-registered company by name, ticker, or CIK.
`company_filings`	Browse a company's filing history — every form, sorted by date.
`company_brief`	One-call intelligence snapshot — profile, headline financials, recent activity.
`account_status`	Current tier, gated tools, upgrade URL, and remaining quota. Useful when a higher-tier call fails.

Free tier returns truncated results on these tools (e.g. 10 filings per call, basic profile data). Upgrade prompts surface in the response when fuller data is available at a higher tier.

Pro — 17 tools

Pro adds 13 tools on top of Free. The shape: financial intelligence, signals, lookup feeds, and the fund/adviser surface.

Tool	What it does
`financial_snapshot`	Key financial ratios from the latest 10-K — profitability, returns, liquidity, leverage.
`financial_statements`	Full XBRL financial statements — income statement, balance sheet, cash flow.
`financial_trends`	Multi-year revenue, margin, and growth trends with directional classification.
`compare_companies`	Side-by-side financial comparison across up to 10 companies.
`insider_activity`	Form 4 trades with sentiment scoring and per-insider detail.
`institutional_ownership`	13F holders ranked by position size, with quarter-over-quarter changes.
`material_events`	Real-time 8-K events with structured item codes (1.01 acquisitions, 5.02 executive changes, 2.02 earnings).
`live_filings`	Live SEC filing feed — 48-hour rolling window, filterable by form type and CIK.
`search_filings`	Full-text search across every SEC filing since 2001 — phrase, NEAR, boolean operators; or a count-over-time trend via `interval`.
`fund_profile`	Detailed mutual-fund / ETF profile — share classes, top holdings, expense ratios.
`adviser_profile`	Investment adviser profile by CRD — AUM, executives, related funds, regulatory history.
`search_funds`	Find mutual funds and ETFs by name, ticker, or fund family.
`search_advisers`	Find SEC-registered investment advisers by firm name or CRD number.

Plus everything Free includes.

Analyst — 23 tools + 5 recipe prompts

Analyst adds 6 tools and 5 recipe prompts on top of Pro. The shape: AI-powered analysis, narrative-text intelligence, and an aggregation layer designed to be consumed by recipe prompts.

Tool	What it does
`analyze_filing`	AI-powered filing analysis — paste a URL or accession number. Form-type aware: Form 4s get insider transactions, 8-Ks get material events, 10-Ks get financial summaries plus notes TOC, 13F-HRs get top holdings.
`disclosure_search`	Search narrative text disclosures across XBRL TextBlocks — find specific risk language, accounting policies, or commitments.
`edgar_notes`	Search financial-statement notes by topic — pension, leases, debt covenants, segment reporting.
`position_intel`	Single-call bundle for one ticker — catalysts, ownership shifts (insider + 13F), and the risk-factor diff between the two latest 10-Ks.
`peer_facts`	Structured peer-comparison rows for one target ticker against up to 10 peers along one dimension.
`portfolio_events`	Bulk 8-K material events across up to 50 tickers.

Plus everything Pro includes.

Analyst also unlocks five recipe prompts available via prompts/list and prompts/get. In Claude Desktop and Claude.ai they appear under the edgar slash-command namespace.

Prompt	What it produces
`position_thesis`	Single-name thesis: Setup, Catalysts, Risk Deltas, Ownership Signal, View + Confidence
`peer_comparison`	Peer table + Spread paragraph + Outliers list along one dimension
`portfolio_pulse`	Themes paragraph, Top 3 Material Events, Quiet Names
`earnings_postmortem`	Headline, Beats and Misses, Guide Changes, Red Flags
`filing_red_flags`	Ranked Alerts list with severity tags (high/medium/low)

See MCP Prompts for the per-recipe argument tables and example invocations.

Builder — 23 tools + 5 recipe prompts (v1)

Builder ships the same tool set and recipe prompts as Analyst for v1. The Builder waitlist is open at /pricing.

When the Builder tier opens for general availability, it will add Builder-only tools — configurable analysis presets, custom prompts, and unmetered call volumes. Those land here when filed.

How tier gating works

Two layers, so a client can't bypass it:

`tools/list` filter. The MCP server inspects your bearer token's tier and returns only the tools your tier includes. Free users see 4 tools, Pro sees 17, Analyst sees 23. The prompts/list endpoint applies the same filter — recipe prompts only appear at Analyst+. The AI never knows tools or prompts above your tier exist.
Invoke-time check. Even if a client somehow constructs a call to a higher-tier tool (cached schemas from a prior session, manual JSON-RPC), the dispatcher rejects with a structured tier_denied error envelope:

{
  "error": {
    "code": "tier_denied",
    "message": "This tool requires the Analyst tier.",
    "required_tier": "analyst",
    "current_tier": "pro",
    "upgrade_url": "https://app.edgar.tools/pricing"
  }
}

The AI assistant reads tier_denied and routes around it — typically by surfacing the upgrade URL to you in chat or by trying a lower-tier alternative.

After upgrading

When you upgrade tiers, your existing token still has the old tier baked in. To pick up the new tools:

Disconnect the edgar.tools server in your MCP client (Claude → Settings → Connectors → ⋯ → Disconnect, or remove from mcp.json).
Reconnect using the same URL. OAuth issues a fresh token tagged with your new tier.
The tool list refreshes — Pro users see 17 tools where they used to see 4, Analyst users see 23 tools plus 5 recipe prompts, etc.

Tokens otherwise last 90 days. After a tier downgrade or cancellation, the next refresh issues a token at the new tier.

What's next

AI plugin landing — visual tier ladder + setup walkthroughs for Claude, ChatGPT, Cursor, Windsurf
MCP Setup — connect your AI client step by step
MCP Tools reference — parameter tables and per-tool behaviour
MCP Prompts reference — the 5 Analyst recipe prompts
Pricing — full tier comparison including web-app features