Skip to main content

MCP server for querying SEC-registered financial advisor data

Project description

AdvisorFinder MCP Server

An MCP server that gives AI assistants access to SEC-registered financial advisor data. Look up advisors by CRD number, search by name or firm, check disclosure histories, and get risk assessments — all from within Claude or any MCP-compatible client.

Quick Start

Install

pip install advisorfinder-mcp

Configure Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "advisorfinder": {
      "command": "advisorfinder-mcp"
    }
  }
}

Restart Claude Desktop. The AdvisorFinder tools are now available.

Alternative: Run with uvx (no install needed)

{
  "mcpServers": {
    "advisorfinder": {
      "command": "uvx",
      "args": ["advisorfinder-mcp"]
    }
  }
}

Tools

Tool Description
lookup_advisor Full advisor profile by CRD number — employment, exams, designations, disclosures, risk score
search_advisors Search by name, state, or firm
verify_advisor Quick status check — active/inactive, disclosures, risk level, recommendation
get_risk_profile Detailed risk assessment with individual factors and severity
get_firm_info Firm details — advisor count, disclosure rates, location
get_database_stats Database-wide statistics — totals, top states, disclosure rates

Resources

The server includes reference data that AI assistants can read for context:

Resource Description
advisorfinder://risk-scoring-methodology How risk scores are calculated (point values, risk levels)
advisorfinder://credentials-guide Guide to financial advisor credentials (CFP, CFA, CPA, Series 7, etc.)
advisorfinder://data-sources Information about SEC IAPD, FINRA BrokerCheck, and how to verify data

Prompts

Prompt Description
advisor_due_diligence Comprehensive due diligence workflow — chains lookup, risk profile, and firm analysis
compare_advisors Side-by-side comparison of two or more advisors

Example Queries

Once configured, ask your AI assistant:

  • "Look up financial advisor CRD 1234567"
  • "Search for advisors named Smith in California"
  • "Is CRD 9876543 an active registered advisor? Any red flags?"
  • "Compare advisors CRD 1234567 and CRD 9876543"
  • "Run a due diligence check on advisor CRD 1234567"
  • "How many registered advisors are in the database?"

Data Source

All data is sourced from the SEC Investment Adviser Public Disclosure (IAPD) database, which is maintained by the U.S. Securities and Exchange Commission and updated weekly. You can verify any information directly:

Disclaimer

This MCP server is provided by AdvisorFinder and is intended for informational and research purposes only. It is not financial, legal, or investment advice.

The data served through this tool originates from publicly available SEC and FINRA databases. AdvisorFinder acts as an intermediary to make this public data more accessible — we do not independently verify, endorse, or guarantee the accuracy or completeness of the underlying data.

Important:

  • A disclosure on an advisor's record does not necessarily indicate wrongdoing. Always review the full context of any disclosure event through the official SEC and FINRA sources linked above.
  • AI assistants may interpret or summarize data in ways that are incomplete or inaccurate. Always verify AI-generated assessments against official sources before making decisions.
  • AdvisorFinder is not responsible for conclusions, recommendations, or claims made by AI assistants using this data.
  • This tool should not be used as the sole basis for selecting, evaluating, or dismissing a financial advisor.

Use at your own discretion. For personalized financial guidance, consult a qualified professional.

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

advisorfinder_mcp-1.0.0.tar.gz (10.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

advisorfinder_mcp-1.0.0-py3-none-any.whl (11.5 kB view details)

Uploaded Python 3

File details

Details for the file advisorfinder_mcp-1.0.0.tar.gz.

File metadata

  • Download URL: advisorfinder_mcp-1.0.0.tar.gz
  • Upload date:
  • Size: 10.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.2

File hashes

Hashes for advisorfinder_mcp-1.0.0.tar.gz
Algorithm Hash digest
SHA256 7b3205cb742a0abec1f0de6df97afb3ca23ac85501fd7c10db92560a2d0ab367
MD5 a49b83ac295fd4c30ac99d3c7da8cd11
BLAKE2b-256 1da9d2883b2410cf8ea94b134ef3ecc4f3ef75e7a4bb8797fd4ee0299a7dc08d

See more details on using hashes here.

File details

Details for the file advisorfinder_mcp-1.0.0-py3-none-any.whl.

File metadata

File hashes

Hashes for advisorfinder_mcp-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3af4052bf064b6bc959070f90abcb543a9b450999bc9b4fdc5e8a08ba12d1224
MD5 c79a4868911f26a521c9f4cef8b541ec
BLAKE2b-256 acd43c81fa93ded535c39adf97c96dae07f8d7724c9e55a313fbd0c6ebbf79f8

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page