# AlphaCreek SEC Filings MCP MCP server

Access SEC filings efficiently (10-K, 10-Q, etc), save time and tokens, and get cited answers.

## Links
- Registry page: https://www.getdrio.com/mcp/ai-alphacreek-alphacreek-mcp
- Website: https://www.alphacreek.ai/mcp-docs

## Install
- Endpoint: https://mcp.alphacreek.ai/mcp
- Auth: Auth required by registry metadata

## Setup notes
- Remote header: Authorization (required; secret)
- The upstream registry signals required auth or secrets.
- Remote endpoint: https://mcp.alphacreek.ai/mcp
- Header: Authorization

## Tools
- get_latest_filing - Return latest filing metadata for a company or ticker. Endpoint: https://mcp.alphacreek.ai/mcp
- list_filings - List available filings for a ticker (newest first) with artifact_document_id and dates. Use filing_registry=fca_nsm for UK FCA annual reports. Use this first when you need a specific reporting period. Endpoint: https://mcp.alphacreek.ai/mcp
- get_filing_toc - Return the full filing table of contents for one filing. If artifact_document_id is omitted, resolves the single latest filing for ticker/company (and optional document_type) only. Use list_filings first to discover a specific reporting period. For FCA filings, pass filing_registry=fca_nsm; TOC node ids are HTML page element ids (e.g. pf2a, page12, pageView1). Endpoint: https://mcp.alphacreek.ai/mcp
- read_node_content - Return content for one or more navigation nodes in a filing. Pass one node via node_id or several via node_ids, using the node ids from TOC lines. These are the same values shown as NODE_ID lines in read_node_content output. The authoritative node content is returned as plain MCP text only: an ARTIFACT_DOCUMENT_ID header, then per-node blocks with NODE_ID, TITLE, CITATION_URL, CONTENT_START … CONTENT_END. A TOC node may expand into more granular child NODE_ID blocks; cite those granular NODE_ID/CITATION_URL pairs when they support the claim. For every material claim or logical paragraph in your answer, place one or more relevant CITATION_URL links immediately next to the claim, using the URL paired with each supporting NODE_ID. Endpoint: https://mcp.alphacreek.ai/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: ai.alphacreek
- Version: 1.0.1
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jun 12, 2026
- Source: https://registry.modelcontextprotocol.io