Skip to main content
Glama

arelle-mcp

The definitive MCP server for XBRL processing, validation, and financial analysis.

PyPI Python License

Built by King Hippopotamus.
Uses Arelle — the world's only free, open-source XBRL-certified processor — as its core engine. No other XBRL MCP server exists. This is the first.


What it does

arelle-mcp gives LLMs (Claude, GPT, etc.) full access to XBRL financial data through 46 tools. That number is the tool registry's, not a figure typed into this file — count it yourself against any checkout:

python -c "import asyncio; from arelle_mcp.server import mcp; \
  print(len(asyncio.run(mcp.list_tools())))"

tests/test_tool_count.py runs that count in CI and fails if this README drifts from it.

Category

Tools

Description

Filing Ops

xbrl_load_filing, xbrl_filing_summary, xbrl_compare_filings, xbrl_close_filing, xbrl_list_filings

Load, inspect, compare, and manage XBRL/iXBRL filings

Validation

xbrl_validate

Validate against SEC EFM, EU ESEF, UK HMRC, or generic rules

Fact Extraction

xbrl_extract_facts, xbrl_fact_details

Query financial data points with filtering by concept, period, dimension, unit

Taxonomy

xbrl_browse_taxonomy, xbrl_concept_details

Search and explore the taxonomy (standard + company extensions)

Relationships

xbrl_presentation_tree, xbrl_calculation_tree, xbrl_dimension_structure

Navigate financial statement hierarchies, calculation trees, and dimensional breakdowns

SEC EDGAR

xbrl_fetch_sec_filing, xbrl_search_sec_concept, xbrl_company_facts

Fetch SEC filings by ticker/CIK, search historical concept data

Rendering

xbrl_render_statement

Reconstruct financial statements (Balance Sheet, Income Statement, Cash Flow)

Document Intelligence

xbrl_extract_text, xbrl_search_text, xbrl_get_footnotes, xbrl_list_sections, xbrl_get_cover_page, xbrl_get_html_tables, xbrl_get_exhibits, xbrl_get_raw_xml

Read the narrative: MD&A, risk factors, footnotes, cover page, tables, exhibits

Analysis Engine

xbrl_financial_ratios, xbrl_trend_analysis, xbrl_segment_breakdown, xbrl_anomaly_detection, xbrl_smart_summary, xbrl_peer_comparison

Ratios, trends, segment splits, anomaly flags, peer comparison

Formula & Validation+

xbrl_run_formula, xbrl_list_formulas, xbrl_dts_comparison, xbrl_check_calculations, xbrl_validate_extended

XBRL Formula execution, DTS diffing, calculation-linkbase checks

EDGAR Pro

xbrl_edgar_search, xbrl_edgar_company_info, xbrl_edgar_filing_index, xbrl_edgar_bulk_facts, xbrl_edgar_insider_trades

Full-text search, company metadata, filing index, bulk facts, Form 4

Export

xbrl_export_json, xbrl_export_csv, xbrl_export_concepts, xbrl_export_dts, xbrl_create_instance

Emit JSON/CSV/concept lists/DTS, and author new instances

Plus 5 resources (reference data) and 5 prompt templates (guided analysis workflows).


Related MCP server: mcp-edgar

Quick Start

Install

pip install arelle-mcp

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "arelle-mcp": {
      "command": "arelle-mcp",
      "env": {
        "ARELLE_MCP_MAX_FILINGS": "5"
      }
    }
  }
}

Claude Code

claude mcp add arelle-mcp -- arelle-mcp

Cursor / Other MCP Clients

{
  "arelle-mcp": {
    "command": "python",
    "args": ["-m", "arelle_mcp"]
  }
}

HTTP Mode (Remote)

ARELLE_MCP_TRANSPORT=streamable-http ARELLE_MCP_PORT=8000 arelle-mcp

Usage Examples

Analyze Apple's Latest 10-K

"Fetch Apple's latest 10-K and give me a financial summary"

The LLM will:

  1. Call xbrl_fetch_sec_filing(ticker="AAPL", filing_type="10-K")

  2. Extract key metrics with xbrl_extract_facts

  3. Render financial statements with xbrl_render_statement

Validate a Filing

"Validate this SEC filing: https://www.sec.gov/Archives/edgar/data/..."

Compare Two Quarters

"Compare Apple's Q2 and Q3 2024 10-Q filings"

Historical Revenue Trend

"Show me Microsoft's revenue history from SEC EDGAR"

The LLM calls xbrl_search_sec_concept(cik="789019", concept="Revenues") — no filing load needed.


Architecture

Core Design Decisions

1. Single-Session Lock — Arelle uses global state that isn't thread-safe. All operations are serialized via asyncio.Lock and offloaded to a ThreadPoolExecutor to avoid blocking the MCP event loop.

2. LRU Filing Cache — Each loaded filing consumes 30-60MB. An OrderedDict-based LRU cache (default: 5 filings) automatically evicts the oldest filing when capacity is reached, calling model.close() to free memory.

3. Lazy Imports — Arelle is heavy (~200MB with taxonomies). All Arelle imports happen lazily inside tool functions, keeping server startup fast.

Project Structure

src/arelle_mcp/
├── server.py            # FastMCP instance, lifespan, registration
├── arelle_wrapper.py    # ArelleManager — session lifecycle, concurrency, caching
├── serializers.py       # Arelle objects → JSON/markdown
├── constants.py         # Arcroles, disclosure systems, SEC config
├── tools/
│   ├── filing.py        # Load, summary, compare, close, list
│   ├── validation.py    # Validate against disclosure systems
│   ├── facts.py         # Extract and filter facts
│   ├── taxonomy.py      # Browse concepts, get details
│   ├── relationships.py # Presentation, calculation, dimension trees
│   ├── edgar.py         # SEC EDGAR API integration
│   └── rendering.py     # Financial statement rendering
├── resources/           # Reference data (disclosure systems, common concepts)
└── prompts/             # Guided analysis workflow templates

stdout is the protocol

Under the stdio transport, stdout is the JSON-RPC wire. A single stray byte on it is a framing error, and a compliant client will tear the transport down and lose every in-flight call.

Arelle is chatty: left to its defaults it prints iXBRL namespace and validation messages (ix11, xmlSchema, ...) to stdout while loading a filing. In v2.1.0 that output landed on the wire and killed long extraction sessions. Since v2.1.1 the server reserves stdout for the protocol at startup (arelle_mcp.stdio_guard), on three independent levels:

  • the real stdout is duplicated to a private descriptor and fd 1 is re-pointed at stderr, so even C-level writes are safe;

  • sys.stdout is replaced by a proxy whose .buffer is that private descriptor — what the MCP transport wraps — while every text write goes to stderr;

  • the arelle logger is pinned to stderr, Arelle runs with logFile="logToStdErr", and every synchronous Arelle call is wrapped in redirect_arelle_output().

Nothing is silenced — all diagnostics still appear on stderr, where your MCP client shows them. tests/test_stdout_is_clean.py proves it end to end by running a real MCP handshake and a real iXBRL load in a child process and asserting the parent sees only parseable JSON-RPC.


Configuration

Environment Variable

Default

Description

ARELLE_MCP_MAX_FILINGS

5

Max filings cached in memory

ARELLE_MCP_CACHE_DIR

(none)

Directory for taxonomy cache

ARELLE_MCP_TRANSPORT

stdio

Transport: stdio or streamable-http

ARELLE_MCP_PORT

8000

HTTP port (when using streamable-http)

ARELLE_MCP_LOG_LEVEL

INFO

Logging level


Development

git clone https://github.com/TheKingHippopotamus/Arelle-MCP.git
cd Arelle-MCP
pip install -e ".[dev]"

# Run tests
pytest

# Type check
mypy src/arelle_mcp

# Lint
ruff check src/

# Test with MCP Inspector
npx @modelcontextprotocol/inspector arelle-mcp

Supported File Formats

  • XBRL Instance Documents (.xbrl, .xml)

  • Inline XBRL (.htm, .html) — SEC mandated since June 2021

  • iXBRL Document Sets

  • ZIP archives containing XBRL

  • SEC EDGAR URLs (auto-fetched)

  • Taxonomy Packages (.zip)

Supported Disclosure Systems

  • SEC EFM — US Securities and Exchange Commission

  • ESEF — European Single Electronic Format (EU/ESMA)

  • HMRC — UK HM Revenue & Customs

  • GFM — Global Filing Manual


License

Apache 2.0 — same as Arelle itself.


Built by King Hippopotamus — with zero compromises.

Available Tools

46 tools
xbrl_anomaly_detectionA
Read-onlyIdempotent

Detect unusual patterns or potential issues in a filing.

Checks for: negative values where unexpected, extreme period changes, calculation mismatches, missing expected concepts, zero values.

Args: params: Filing ID.

Returns: str: JSON with anomaly list, severity, and descriptions.

Inputs: params (required). Returns: result

xbrl_browse_taxonomyA
Read-onlyIdempotent

Search and browse concepts in the filing's taxonomy (DTS).

The Discoverable Taxonomy Set includes all standard taxonomy concepts (us-gaap, dei, srt, ifrs) plus company extensions. Filter by name, type, namespace, or whether concepts have facts.

Args: params (BrowseTaxonomyInput): Search and filter parameters.

Returns: str: JSON with matching concepts and pagination info.

Inputs: params (required). Returns: result

xbrl_calculation_treeA
Read-onlyIdempotent

Get calculation relationships showing how totals are computed.

The calculation linkbase defines mathematical relationships between concepts — e.g., Assets = CurrentAssets + NoncurrentAssets. Each component has a weight (+1 or -1) indicating addition or subtraction.

Args: params (CalculationTreeInput): Filing ID and filter options.

Returns: str: JSON with calculation trees showing components and weights.

Inputs: params (required). Returns: result

xbrl_check_calculationsB
Read-onlyIdempotent

Verify calculation consistency for totals and their components.

For each calculation relationship, compares the reported total with the sum of components, reporting mismatches.

Args: params: Filing ID, optional concept filter, max results.

Returns: str: JSON with calculation check results.

Inputs: params (required). Returns: result

xbrl_close_filingA
DestructiveIdempotent

Close a loaded filing and free its memory (30-60MB per filing).

Args: params (FilingIdInput): The filing_id to close.

Returns: str: Confirmation message.

Inputs: params (required). Returns: result

xbrl_company_factsA
Read-onlyIdempotent

Get all available XBRL facts for a company from SEC EDGAR.

Returns a summary of all concepts reported by the company across all filings, organized by taxonomy. Does NOT require loading a filing first.

Args: params (CompanyFactsInput): CIK and optional concept filter.

Returns: str: JSON with available concepts, their observation counts, and units.

Inputs: params (required). Returns: result

xbrl_compare_filingsA
Read-onlyIdempotent

Compare two loaded XBRL filings.

Identifies added, removed, and changed facts between two filings. Useful for analyzing changes between quarterly or annual reports. Both filings must be loaded first with xbrl_load_filing.

Args: params (CompareFilingsInput): Two filing IDs to compare.

Returns: str: JSON with added/removed/changed facts and counts.

Inputs: params (required). Returns: result

xbrl_concept_detailsA
Read-onlyIdempotent

Get full details for a taxonomy concept.

Returns all labels (standard, terse, verbose, documentation), references to accounting standards, data type, period type, balance direction, substitution group, and sample reported facts.

Args: params (ConceptDetailsInput): Filing ID and concept name.

Returns: str: JSON with comprehensive concept information.

Inputs: params (required). Returns: result

xbrl_create_instanceB

Create a new XBRL instance document from scratch.

Generates a valid XBRL instance with the specified facts, contexts, and units. Returns the XML as a string.

Args: params: Schema ref, entity info, and list of facts.

Returns: str: JSON with the generated XBRL XML.

Inputs: params (required). Returns: result

xbrl_dimension_structureA
Read-onlyIdempotent

Get the dimensional structure of a filing.

XBRL Dimensions enable multi-dimensional data breakdowns. Returns hypercubes, dimensions (axes), domains, and members. Example: Revenue broken down by ProductOrServiceAxis with members like SoftwareMember, HardwareMember.

Args: params (DimensionStructureInput): Filing ID and optional dimension filter.

Returns: str: JSON with dimensional hierarchy.

Inputs: params (required). Returns: result

xbrl_dts_comparisonA
Read-onlyIdempotent

Compare two taxonomy/filing schemas.

Identifies concepts, relationships, and labels that were added, removed, or changed between two filings or taxonomy versions.

Args: params: Two filing IDs.

Returns: str: JSON with added/removed/changed concepts and relationships.

Inputs: params (required). Returns: result

xbrl_edgar_bulk_factsA
Read-onlyIdempotent

Bulk download fact data for multiple concepts across multiple companies.

Returns a matrix of company × concept with the most recent value. No filing load required.

Args: params: List of CIKs, list of concepts, taxonomy.

Returns: str: JSON matrix of values.

Inputs: params (required). Returns: result

xbrl_edgar_company_infoA
Read-onlyIdempotent

Get comprehensive company profile from SEC EDGAR.

Returns: name, CIK, SIC code, state, addresses, former names, and recent filing history by type.

Args: params: CIK or ticker.

Returns: str: JSON with company profile.

Inputs: params (required). Returns: result

xbrl_edgar_filing_indexB
Read-onlyIdempotent

Get the full index of documents within a specific SEC filing.

Lists all exhibits, schemas, instances, and other documents in a filing with their types, sizes, and URLs.

Args: params: CIK and accession number.

Returns: str: JSON with document list.

Inputs: params (required). Returns: result

xbrl_edgar_insider_tradesA
Read-onlyIdempotent

Get insider trading data from SEC Forms 3, 4, 5.

Returns recent insider transactions including the filer name, form type, and filing date.

Args: params: Company CIK and limit.

Returns: str: JSON with insider filing list.

Inputs: params (required). Returns: result

xbrl_export_conceptsB
Read-onlyIdempotent

Export taxonomy concepts as structured data.

Returns all concepts in the filing's DTS with their properties.

Args: params: Filing ID, namespace filter, with_facts_only flag.

Returns: str: JSON with concept list.

Inputs: params (required). Returns: result

xbrl_export_csvA
Read-onlyIdempotent

Export facts as CSV format for spreadsheet analysis.

Returns CSV string with customizable columns.

Args: params: Filing ID, columns, filters, limit.

Returns: str: CSV-formatted string.

Inputs: params (required). Returns: result

xbrl_export_dtsA
Read-onlyIdempotent

Export the Discoverable Taxonomy Set (DTS) document map.

Lists all schemas, linkbases, and instance documents in the DTS with their types and URLs.

Args: params: Filing ID.

Returns: str: JSON with DTS document list.

Inputs: params (required). Returns: result

xbrl_export_jsonA
Read-onlyIdempotent

Export all facts from a filing as structured JSON.

Returns a complete JSON export of filing facts, suitable for data pipelines, database import, or further processing.

Args: params: Filing ID, filters, and limit.

Returns: str: JSON array of serialized facts.

Inputs: params (required). Returns: result

xbrl_extract_factsA
Read-onlyIdempotent

Extract and filter XBRL facts from a loaded filing.

Supports filtering by concept name, period type, dimensions, units, and more. Returns paginated results with full fact details including values, contexts, periods, and dimensional breakdowns.

The filing must be loaded first with xbrl_load_filing.

Args: params (ExtractFactsInput): Filtering and pagination parameters.

Returns: str: JSON with filtered facts, total count, and pagination info.

Inputs: params (required). Returns: result

xbrl_extract_textA
Read-onlyIdempotent

Extract clean text from a specific section of a loaded filing.

Sections: 'mda' (Management Discussion & Analysis), 'risk_factors', 'financial_statements', 'notes', 'controls', 'legal', 'cover', 'all'.

This extracts the actual human-readable text from the iXBRL/HTML document, not just XBRL-tagged data points. Useful for MD&A analysis, risk assessment, and qualitative content extraction.

Args: params: Filing ID, section name, and max characters.

Returns: str: Clean text content from the requested section.

Inputs: params (required). Returns: result

xbrl_fact_detailsA
Read-onlyIdempotent

Get comprehensive details for all facts of a specific concept.

Returns every reported value for the concept across all periods and dimensions, plus the concept's taxonomy definition with labels, data type, and balance direction.

Args: params (FactDetailsInput): Filing ID and concept name.

Returns: str: JSON with concept definition and all reported facts.

Inputs: params (required). Returns: result

xbrl_fetch_sec_filingA

Fetch an SEC EDGAR filing by CIK or ticker symbol.

Finds the specified filing type (10-K, 10-Q, etc.) from SEC EDGAR, returns filing metadata, and optionally loads it for analysis.

Either cik or ticker must be provided. If ticker is provided, it will be resolved to a CIK automatically.

Args: params (FetchSecFilingInput): CIK/ticker and filing type.

Returns: str: JSON with filing metadata and optionally a filing_id.

Inputs: params (required). Returns: result

xbrl_filing_summaryA
Read-onlyIdempotent

Get detailed metadata about a loaded filing.

Returns entity name, CIK, document type, reporting period, fact/context/unit counts, namespaces used, and more.

Args: params (FilingIdInput): The filing_id from xbrl_load_filing.

Returns: str: JSON with comprehensive filing metadata.

Inputs: params (required). Returns: result

xbrl_financial_ratiosB
Read-onlyIdempotent

Compute standard financial ratios from a loaded filing.

Returns liquidity, profitability, leverage, and per-share ratios calculated from the most recent period's data.

Args: params: Filing ID.

Returns: str: JSON with computed ratios and their interpretations.

Inputs: params (required). Returns: result

xbrl_get_cover_pageA
Read-onlyIdempotent

Extract complete cover page data from a filing.

Returns all DEI (Document Entity Information) facts as a structured object: company name, CIK, ticker, fiscal year, filing date, period, shares, etc.

Args: params: Filing ID.

Returns: str: JSON with all DEI facts.

Inputs: params (required). Returns: result

xbrl_get_exhibitsA
Read-onlyIdempotent

List exhibits attached to a filing.

SEC filings include exhibits like press releases (EX-99.1), certifications (EX-31, EX-32), and other documents. Returns exhibit list with types and descriptions.

Args: params: Filing ID.

Returns: str: JSON with exhibit list.

Inputs: params (required). Returns: result

xbrl_get_footnotesA
Read-onlyIdempotent

Extract footnotes linked to XBRL facts.

XBRL filings can attach footnotes to specific facts, providing additional context or explanations. This tool extracts those footnotes.

Args: params: Filing ID, optional concept filter, limit.

Returns: str: JSON with footnotes and their linked facts.

Inputs: params (required). Returns: result

xbrl_get_html_tablesC
Read-onlyIdempotent

Extract HTML tables from the filing document.

Finds tables in the HTML content, with optional text search filter. Returns tables as structured row/column data.

Args: params: Filing ID, optional search filter, table index, limits.

Returns: str: JSON with table data.

Inputs: params (required). Returns: result

xbrl_get_raw_xmlA
Read-onlyIdempotent

Access raw XML/HTML content from the filing document.

Allows XPath queries against the document tree. Useful for advanced extraction when other tools don't cover a specific need.

Args: params: Filing ID, optional XPath, max chars.

Returns: str: Raw XML string of matched elements.

Inputs: params (required). Returns: result

xbrl_list_filingsA
Read-onlyIdempotent

List all currently loaded filings with their IDs and basic info.

Returns: str: JSON array of loaded filing summaries.

Inputs: no named parameters. Returns: result

xbrl_list_formulasB
Read-onlyIdempotent

List all formulas, assertions, and validation rules in a filing's DTS.

Args: params: Filing ID.

Returns: str: JSON with formula names, types, and descriptions.

Inputs: params (required). Returns: result

xbrl_list_sectionsA
Read-onlyIdempotent

Map the complete document structure of a filing.

Identifies major sections (Items, Parts) and their approximate positions and sizes. Useful for navigating large 10-K/10-Q documents.

Args: params: Filing ID.

Returns: str: JSON with section titles, positions, and sizes.

Inputs: params (required). Returns: result

xbrl_load_filingA

Load an XBRL or iXBRL filing for analysis.

Accepts local file paths, HTTP/HTTPS URLs (including SEC EDGAR), and ZIP archives. Returns a filing_id for use with all other tools, plus a summary with entity name, document type, period, and fact counts.

This is the entry point — call this first before using any other tool.

Args: params (LoadFilingInput): Filing path/URL and options.

Returns: str: JSON with filing_id and filing summary.

Inputs: params (required). Returns: result

xbrl_peer_comparisonA
Read-onlyIdempotent

Compare a concept across multiple companies using SEC EDGAR Frames API.

Returns a ranked list of companies with values for the specified concept in the given period. No filing load required.

Args: params: Concept, taxonomy, unit, period, limit.

Returns: str: JSON with ranked company list.

Inputs: params (required). Returns: result

xbrl_presentation_treeA
Read-onlyIdempotent

Get the presentation hierarchy (financial statement structure).

The presentation linkbase defines how concepts are organized for display — each extended link role typically represents one financial statement (Balance Sheet, Income Statement, Cash Flow, etc.).

Use role_filter to get a specific statement, or list_roles_only=true to see what statements are available.

Args: params (PresentationTreeInput): Filing ID and filter options.

Returns: str: JSON with hierarchical tree structure per role.

Inputs: params (required). Returns: result

xbrl_render_statementA
Read-onlyIdempotent

Render financial statements from XBRL data.

Reconstructs balance sheet, income statement, cash flow statement, or equity statement using the presentation linkbase hierarchy, filling in actual reported values from the instance document.

Args: params (RenderStatementInput): Filing ID, statement type, and format.

Returns: str: Financial statement in markdown or JSON format.

Inputs: params (required). Returns: result

xbrl_run_formulaA
Read-onlyIdempotent

Execute XBRL formulas defined in the filing's linkbase.

Runs value assertions, existence assertions, and consistency assertions. Returns pass/fail results for each formula.

Args: params: Filing ID and trace option.

Returns: str: JSON with formula execution results.

Inputs: params (required). Returns: result

xbrl_search_sec_conceptA
Read-onlyIdempotent

Search SEC EDGAR for a specific XBRL concept across all filings.

Returns historical values for a concept (e.g., Assets, Revenue) across all available filing periods. Uses SEC's companyconcept API. Does NOT require loading a filing first.

Args: params (SearchSecConceptInput): CIK, concept name, and taxonomy.

Returns: str: JSON with historical values, periods, and units.

Inputs: params (required). Returns: result

xbrl_search_textA
Read-onlyIdempotent

Full-text search within a loaded filing's content.

Searches the entire document text (not just XBRL facts) for the query string. Returns matching passages with surrounding context. Useful for finding guidance, forward-looking statements, specific disclosures, etc.

Args: params: Filing ID, search query, context size, max results.

Returns: str: JSON with matching passages and their positions.

Inputs: params (required). Returns: result

xbrl_segment_breakdownA
Read-onlyIdempotent

Extract dimensional breakdowns for a concept.

Shows how a total (e.g., Revenue) breaks down by segments, geographies, products, or other dimensions.

Args: params: Filing ID, concept name, optional dimension filter.

Returns: str: JSON with dimensional breakdown including values and percentages.

Inputs: params (required). Returns: result

xbrl_smart_summaryB
Read-onlyIdempotent

Generate an LLM-optimized structured summary of a filing.

Returns a compact (<4K tokens) JSON with company info, key metrics, period comparisons, and notable items. Designed for efficient use of LLM context windows.

Args: params: Filing ID and focus area.

Returns: str: Compact JSON summary.

Inputs: params (required). Returns: result

xbrl_trend_analysisA
Read-onlyIdempotent

Analyze trends across periods within a single filing.

10-K filings contain 3 years of data, 10-Q has 2 quarters. Computes absolute and percentage changes for specified concepts.

Args: params: Filing ID and list of concepts.

Returns: str: JSON with per-concept period values and changes.

Inputs: params (required). Returns: result

xbrl_validateA
Read-onlyIdempotent

Validate an XBRL/iXBRL filing against a disclosure system.

Returns structured validation results including errors, warnings, and informational messages. Supports SEC EFM, EU ESEF, UK HMRC, and generic XBRL validation.

The filing does NOT need to be loaded first — this tool loads, validates, and closes in one operation.

Args: params (ValidateFilingInput): Filing path and validation options.

Returns: str: JSON with validation results (valid, error_count, warning_count, errors, warnings).

Inputs: params (required). Returns: result

xbrl_validate_extendedA
Read-onlyIdempotent

Extended validation with granular control over which checks to run.

Supports: xbrl21, calculations, dimensions, utr, duplicates. Returns results grouped by category with severity filtering.

Args: params: Filing ID or path, checks to run, severity filter.

Returns: str: JSON with categorized validation results.

Inputs: params (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 46 tools

    Disambiguation3/5

    Several tools have overlapping purposes (e.g., multiple fact extraction tools like xbrl_extract_facts, xbrl_fact_details, xbrl_company_facts), and the distinction between them may not be immediately clear to an agent. However, each tool has a specific use case described, reducing ambiguity somewhat.

    Naming Consistency4/5

    All tools start with 'xbrl_' and use snake_case, providing a consistent prefix. However, the naming pattern mixes verb-first (e.g., xbrl_load_filing) and noun-first (e.g., xbrl_anomaly_detection) approaches, leading to minor inconsistency.

    Tool Count3/5

    With 46 tools, the server is on the high end of tool counts. While the XBRL domain is complex and justifies many tools, there is some redundancy (e.g., multiple export formats) that could be consolidated.

    Completeness4/5

    The tool set covers a wide range of XBRL operations: loading, browsing, extraction, validation, comparison, and EDGAR-specific features. Minor gaps exist, such as no direct tool for modifying metadata, but overall the surface is comprehensive for its domain.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables LLMs to download, parse, and analyze SEC EDGAR filings, including 10-K/Q reports, XBRL financial statements, and insider trading data. It provides structured access to institutional holdings, corporate events, and financial facts for comprehensive investment research.
      19
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables LLMs to access SEC EDGAR data: search filings, extract sections, pull structured financials, and track insider transactions.
      20 npm
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Standardizes XBRL financial data from US SEC and European ESEF filings for LLM agents, enabling querying normalized financial facts like revenue and total assets across issuers and taxonomies.
      21
      45 PyPI
      Apache 2.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables searching SEC EDGAR for companies, retrieving recent filings (e.g., 10-K, 10-Q), and accessing structured XBRL financial facts.
      143 npm
      MIT