What are the prerequisites to run the server?
Docker, Node.js, Claude Desktop, and an Azure OpenAI API key. Python 3.12+ and the `uv` package manager are required for local development.
@trailblazelabs
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"fca-mcp": {
"command": "npx",
"args": [
"mcp-remote",
"http://localhost:8080/mcp/",
"--allow-http",
"--debug"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
An open-source MCP server that provides real-time, conversational access to live FCA (Financial Conduct Authority) Register data through AI interfaces. Designed for financial services firms, it bridges AI assistants like Claude Desktop with FCA regulatory data, reducing research time by turning manual searches into natural language queries.
Install prerequisites (Docker, Node.js, Claude Desktop, Azure OpenAI API key), clone the repository, configure .env with Azure OpenAI credentials, run make dev_setup_from_scratch, then connect to Claude Desktop using the configuration provided. After setup, ask natural language questions such as "Search for wealth management firms in London" or "Find recent enforcement notices about market manipulation".
Docker, Node.js, Claude Desktop, and an Azure OpenAI API key. Python 3.12+ and the `uv` package manager are required for local development.
It continuously ingests data from all FCA Register endpoints, processes and normalises it, embeds it using Azure OpenAI for semantic search, and indexes it into Elasticsearch.
`search_fca_handbook`, `search_policy_statements`, `search_consultation_papers`, `search_authorised_firms`, `search_enforcement_notices`, `get_firm_details`, `search_guidance_documents`, and `get_regulatory_updates`.
Data is stored in Elasticsearch indices with semantic search enabled via Azure OpenAI embeddings. The server returns real-time results with citations.
The server is open source under the MIT license with zero licensing costs. You only need your own Azure OpenAI API key and infrastructure (Docker, Elasticsearch).
351 read-only tools on institutional data: stocks since 1926, vol surfaces since 1996, CDS, bonds, private markets, 13F, macro. One OAuth connection.

Cash-pay lab tests without insurance: catalog search, all-in quotes by US state, Quest/Labcorp/BioReference draw sites by ZIP, physician-reviewed reference ranges, measured turnaround, price comparison vs other providers

Household finance planner for AI assistants: cash flow, net worth, bills, debts, savings goals and retirement projections from your own Beyond Payday data. OAuth sign-in; read-only or read & write.

Market data and research for AI assistants: perpetual futures across 40 venues, the rules and pricing of 22 perps prop firms, and dated investment theses on more than 6,100 US equities. Remote, read-only, no API key.

See what your software really costs and what to cut: cheaper plans, alternatives and build-it-yourself paths, priced from public list prices and your own usage.
Comments