Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

EdgarTools

PYPI · EDGARTOOLS

Open-source SEC EDGAR toolkit — 13 tools, 7 prompts, every filing type. No API key required.

Available components

+3 this week 76 Trust /100

Last scanned (10 hours ago)

Scores higher than 69% of PyPI servers

Category Finance and Payments

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 4 of 39 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability77
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 3018 tokens (~201/item across 15 items; 13 tools + 2 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management40
  • Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 20 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Nov 26 +1
    • Package version: 6.2.0 → 6.3.0 functional
  • 15 Nov 26 −14
    • Malware scan: pass → unverified ▼ security
    • Package version: 6.1.0 → 6.2.0 functional
  • 14 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 13 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Nov 26 +1
    • Stability: unverified → 0.10 ▲ functional
    • Package version: 6.0.0 → 6.1.0 functional
  • 9 Nov 26 +17
    • Malware scan: pass → unverified ▼ security
    • Injection markers: unverified → pass ▲ security
    • First check of Judged manipulation: pass security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • Tool coverage: unverified → 100 ▲ functional
    • MCP protocol: unverified → pass ▲ functional
    • Schema quality: unverified → 100 ▲ functional
    • First check of Schema quality: fail functional
    • First check of Schema quality: excellent functional
    • First check of Destructive annotations: pass functional
    • First check of Schema quality: fail functional
    • First check of Tool coverage: 100 functional
    • Package version: 5.62.1 → 6.0.0 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed pypi/edgartools@6.3.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi
Reason No attestation published

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend Known build tool hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 39 packages
Packages resolved 39
Stale 3
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 13 exposed · ~2,989 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
edgar_company ~212

Use this as the starting point for any company-level question. Returns profile, financials, recent filings, and ownership data in one call. Control what's included with the 'include' parameter. Examples: - Company overview: identifier="AAPL" - Financials only: identifier="MSFT", include=["financials"], periods=8 - Full analysis: identifier="AAPL", include=["profile", "financials", "filings", "ownership"]

NameTypeReqDescription
annualboolean–Deprecated. Use 'period' instead. Annual (true) or quarterly (false) financials
identifierstringyesCompany ticker (AAPL), CIK (320193), or name (Apple Inc)
includearray–Data to include. Default: profile, financials, filings
periodstring–Period type: 'annual', 'quarterly', or 'ttm' (trailing twelve months)
periodsinteger–Number of financial periods (default 4)

No output schema declared.

No examples provided.

edgar_compare ~190

Use this to compare companies side-by-side on financial metrics, or analyze an industry sector with automatic peer selection. Examples: - Compare companies: identifiers=["AAPL", "MSFT", "GOOGL"] - Industry analysis: industry="software", limit=5 - Bank comparison: identifiers=["JPM", "BAC", "WFC"], metrics=["revenue", "net_income", "assets"]

NameTypeReqDescription
annualboolean–Annual (true) or quarterly (false)
identifiersarray–Companies to compare (2-10 tickers/CIKs)
industrystring–OR select industry for automatic peer selection
limitinteger–Max companies for industry comparison (default 5, max 10)
metricsarray–Metrics to compare (default: revenue, net_income)
periodsinteger–Number of periods (default 3)

No output schema declared.

No examples provided.

edgar_filing ~342

Use this to examine any SEC filing. Returns structured context: what the filing is, key data, and available next steps. If the filing has a typed data object (10-K, 10-Q, 8-K, Form 4, 13F, DEF 14A, etc.), returns extracted financials, sections, ownership, transactions, etc. Two ways to specify the filing: 1. By company + form type: identifier="AAPL", form="10-K" (gets the latest) 2. By accession number or URL: input="0000320193-23-000077" Examples: - Apple's latest 10-K: identifier="AAPL", form="10-K" - Latest 8-K: identifier="TSLA", form="8-K" - By accession: input="0000320193-23-000077" - From URL: input="https://www.sec.gov/Archives/edgar/data/320193/000032019323000077/..." - Minimal overview: identifier="MSFT", form="10-Q", detail="minimal"

NameTypeReqDescription
detailstring–Detail level for context output (default: standard)
formstring–Form type (10-K, 10-Q, 8-K, DEF 14A, 4, 13F-HR, etc.). Used with 'identifier'.
identifierstring–Company ticker (AAPL), CIK (320193), or name. Used with 'form' to get the latest filing.
inputstring–Accession number or URL containing an accession number (alternative to identifier+form)

No output schema declared.

No examples provided.

edgar_fund ~248

Use this for mutual fund, ETF, BDC, and money market fund analysis. Supports fund lookup, portfolio holdings, money market yields, and BDC investments. Actions: lookup (find fund by ticker/CIK), search (by name), portfolio (NPORT holdings), money_market (yields/NAV), bdc_search, bdc_portfolio. Examples: - Fund lookup: action="lookup", identifier="VFINX" - Fund search: action="search", query="Vanguard 500" - Fund portfolio: action="portfolio", identifier="VFINX" - Money market: action="money_market", identifier="VMFXX" - BDC search: action="bdc_search", query="Ares" - BDC portfolio: action="bdc_portfolio", identifier="ARCC"

NameTypeReqDescription
actionstringyesThe action to perform
identifierstring–Fund ticker, series ID (S000XXXXX), class ID (C000XXXXX), or CIK
limitinteger–Max results to return (default 20, max 50)
querystring–Search text for fund or BDC name

No output schema declared.

No examples provided.

edgar_monitor ~148

Use this to see what was just filed with the SEC. Returns the latest filings from today's live feed, updated every few minutes. Filter by form type to track specific events. Examples: - All latest: (no parameters) - Today's 8-Ks: form="8-K" - Insider trades: form="4" - Latest 10-Ks: form="10-K" - More results: limit=50

NameTypeReqDescription
formstring–Filter by form type (e.g., '8-K', '4', '10-K', '10-Q', '13F-HR')
limitinteger–Max filings to return (default 20, max 100)

No output schema declared.

No examples provided.

edgar_notes ~232

Drill into the notes and disclosures behind financial statement numbers. Use this when you need to explain WHY a number is what it is — debt terms, revenue recognition policies, lease schedules, contingencies, etc. Returns the note's narrative text, which statement line items it explains, and structured table data. Examples: - What does Apple's debt note say? topic="debt", identifier="AAPL" - Revenue recognition policy: topic="revenue", identifier="MSFT" - All notes overview: identifier="TSLA" (no topic = table of contents)

NameTypeReqDescription
detailstring–Detail level: minimal (titles only), standard (context + tables), full (includes DataFrame data)
formstring–Filing form type (default: 10-K). Use 10-Q for quarterly notes.
identifierstringyesCompany ticker (AAPL), CIK (320193), or name
topicstring–Note topic to search for (e.g., 'debt', 'revenue', 'leases', 'contingencies'). Omit for table of contents.

No output schema declared.

No examples provided.

edgar_ownership ~210

Use this for insider trading activity (Form 4) or institutional fund portfolios (13F). For companies, use analysis_type="insiders". For funds/institutions, use analysis_type="fund_portfolio" with the fund's CIK. Examples: - Insider trades: identifier="AAPL", analysis_type="insiders" - Berkshire portfolio: identifier="1067983", analysis_type="fund_portfolio" - Portfolio changes: identifier="1067983", analysis_type="portfolio_diff"

NameTypeReqDescription
analysis_typestringyesinsiders=Form 4 insider trades, fund_portfolio=13F holdings, portfolio_diff=quarter-over-quarter changes
daysinteger–Only Form 4s filed in the last N days (default 90)
identifierstringyesCompany ticker/CIK (for insiders) OR fund/institution CIK (for fund_portfolio/portfolio_diff)
limitinteger–Max results (default 20, max 100)

No output schema declared.

No examples provided.

edgar_proxy ~118

Use this for CEO compensation, executive pay, and corporate governance questions. Extracts compensation tables, pay-vs-performance metrics, and governance data from DEF 14A proxy statements. Examples: - CEO pay: identifier="AAPL" - Compare pay: identifier="MSFT" - Prior year: identifier="AAPL", filing_index=1

NameTypeReqDescription
filing_indexinteger–Which proxy filing to use (0=latest, 1=previous, etc.)
identifierstringyesCompany ticker, CIK, or name

No output schema declared.

No examples provided.

edgar_read ~431

Use this to read the text content of specific sections from a filing. Extracts narrative content like risk factors, MD&A, business descriptions, financial tables, and event items. Use edgar_filing first to identify a filing, then edgar_read to extract its content. Available sections by form type: - 10-K/10-Q: business, risk_factors, mda, financials, controls, legal - 20-F: business, risk_factors, mda, financials, directors, shareholders, controls - 8-K: items, press_release, earnings - DEF 14A: compensation, pay_performance, governance - SC 13D / SCHEDULE 13D: ownership, purpose - SC 13G / SCHEDULE 13G: ownership - 13F-HR: holdings, summary Examples: - Read risk factors: identifier="AAPL", form="10-K", sections=["risk_factors"] - Read 8-K event: identifier="AAPL", form="8-K", sections=["items"] - Read CEO pay: identifier="AAPL", form="DEF 14A", sections=["compensation"] - Read every 13F holding: identifier="1067983", form="13F-HR", sections=["holdings"], limit=0

NameTypeReqDescription
accession_numberstring–Filing accession number (e.g., 0000320193-23-000077)
formstring–Form type (used with identifier to get most recent)
identifierstring–Company identifier (alternative - gets most recent filing of form type)
limitinteger–Max rows in the 13F-HR 'holdings' section (default 30). 0 returns every row, which for large managers can be thousands of rows and a large payload. Validated for all forms, applied only to 13F holdin…
sectionsarray–Sections to extract. Use 'summary' for metadata only, 'all' for everything. Available sections depend on form type.

No output schema declared.

No examples provided.

edgar_screen ~212

Use this to discover or screen companies by industry, exchange, or state. Returns matching companies from SEC reference data — instant results, no API calls. Combine filters to narrow results. Examples: - By industry: industry="software" - By SIC code: sic=2834 (pharmaceutical) - By exchange: exchange="NYSE" - By state: state="DE" (Delaware) - Combined: industry="semiconductor", exchange="Nasdaq", limit=20

NameTypeReqDescription
exchangestring–Stock exchange filter
industrystring–Industry keyword to search SIC descriptions (e.g., 'software', 'pharmaceutical', 'banking')
limitinteger–Max companies to return (default 25, max 100)
sicinteger–Exact SIC code (e.g., 2834 for pharma, 7372 for software)
statestring–US state code for state of incorporation (e.g., 'DE', 'CA', 'NY')

No output schema declared.

No examples provided.

edgar_search ~212

Use this to find companies by name or list filings by form type and company. This searches metadata (names, form types, dates) — not filing text content. For full-text content search, use edgar_text_search instead. Examples: - Find companies: query="software", search_type="companies" - Company's 8-Ks: identifier="AAPL", form="8-K", search_type="filings" - Recent 10-Ks: form="10-K", search_type="filings"

NameTypeReqDescription
formstring–Filter filings by form type (10-K, 10-Q, 8-K, DEF 14A, 13F-HR, etc.)
identifierstring–Limit filing search to specific company (ticker/CIK)
limitinteger–Maximum results per category (default 20)
querystring–Search term for company name or description
search_typestring–What to search: companies, filings, or all

No output schema declared.

No examples provided.

edgar_text_search ~244

Use this to find filings that mention specific topics, products, risks, or events. Searches the actual text content of all SEC filings via EDGAR's full-text search index (EFTS). Different from edgar_search which only searches metadata. Examples: - Topic search: query="artificial intelligence" - 8-K events: query="cybersecurity incident", forms=["8-K"] - Date range: query="supply chain disruption", start_date="2024-01-01" - Company-specific: query="tariff impact", forms=["10-K"], identifier="AAPL"

NameTypeReqDescription
end_datestring–End date for filing date range (YYYY-MM-DD)
formsarray–Filter by form types (e.g., ['10-K', '8-K']). Default: all forms.
identifierstring–Optional company ticker or CIK to scope results
limitinteger–Max results to return (default 20, max 50)
querystringyesFull-text search query (searches filing content)
start_datestring–Start date for filing date range (YYYY-MM-DD)

No output schema declared.

No examples provided.

edgar_trends ~190

Use this for financial trend analysis over time. Returns XBRL-sourced time series with growth rates for revenue, income, EPS, and other metrics across multiple periods. Examples: - Revenue trend: identifier="AAPL", concepts=["revenue"] - Multi-metric: identifier="MSFT", concepts=["revenue", "net_income", "eps"], periods=10 - Quarterly: identifier="TSLA", period="quarterly", periods=8

NameTypeReqDescription
conceptsarray–Financial concepts to track (default: revenue, net_income)
identifierstringyesCompany ticker (AAPL), CIK (320193), or name
include_growthboolean–Calculate YoY/QoQ growth rates (default true)
periodstring–Period type (default: annual)
periodsinteger–Number of periods to retrieve (default 8)

No output schema declared.

No examples provided.

Install

How do I install the EdgarTools MCP server?

EdgarTools runs locally as a PyPI package, launched with uvx --with 'edgartools[ai]==6.3.0' edgartools mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

pypi · edgartools

# add to Claude Code
claude mcp add dgunning-edgartools -- uvx --with 'edgartools[ai]==6.3.0' edgartools mcp
Common questions

What is the EdgarTools MCP server?

EdgarTools is an MCP server listed in the public MCP registry as io.github.dgunning/edgartools. Open-source SEC EDGAR toolkit, 13 tools, 7 prompts, every filing type. No API key required. This page covers its PyPI package (edgartools).

Is the EdgarTools MCP server safe to use?

EdgarTools scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the EdgarTools MCP server expose?

EdgarTools exposes 13 tools: edgar_company, edgar_search, edgar_filing, edgar_read, edgar_compare, and 8 more. Their descriptions and schemas cost roughly 2,989 tokens of context every time the server is loaded.

Is the EdgarTools MCP server still maintained?

EdgarTools is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the EdgarTools MCP server under?

EdgarTools declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the EdgarTools MCP server?

VerifyMCP ran 16 checks on EdgarTools, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.