AlphaCreek MCP for product teams

Ship financial AI without building SEC retrieval.

AlphaCreek gives your agents a hosted MCP connection to structured, citation-ready SEC filings — so your team can focus on product logic, not ingestion pipelines.

Connect from Python, JavaScript, or any MCP-compatible client. Skip EDGAR crawlers, chunking experiments, and citation plumbing.

Hosted remote MCPOAuth + API keysPython & JavaScript6,000+ US tickersCitation URLs
Agent workflow · AlphaCreek MCP

# 1. List filings for a ticker

await mcp.call("list_filings", {ticker: "NVDA"})

# 2. Navigate the filing map

await mcp.call("get_filing_toc", {artifact_document_id: "…"})

# 3. Read targeted nodes with citations

await mcp.call("read_node_content", {node_ids: ["item-1a-risk-factors"]})

→ CITATION_URL per NODE_ID for verifiable answers

Stop building infrastructure

Stop building retrieval pipelines.
Start shipping AI agents.

Most teams power financial AI by stitching together complex stacks from scratch. AlphaCreek replaces brittle pipelines and months of engineering with a single MCP connection.

Without AlphaCreek

Generic RAG Pipeline

Months of engineering. Brittle infrastructure.

  • Custom SEC crawlers to build & maintain
  • Naive text splitting that breaks financial structure
  • Similarity or naive searching - scans whole documents
  • Bloated token usage drives up cost & latency
  • No citations — hard to verify answers
★ Recommended
With AlphaCreek

AlphaCreek MCP

One MCP connection. Production-ready in days.

  • Continuous SEC monitoring, fully managed
  • Hierarchical parsing preserves filing structure
  • Pre-generated tables of contents allows precise navigation
  • Up to 80% fewer tokens — faster, cheaper answers
  • Every fact cited to its passage inside the filing
Token consumption
🪙
100%
~20%
AlphaCreekRaw pipeline
Up to 80% fewer tokens sent to your LLM — lower cost, faster responses.
Integration time
🕒
Hours
Days
AlphaCreekBuild yourself
No ingestion pipelines, no parsing, no chunking — just one MCP connection.
Answer reliability
Weak
Cited
Evidence-backedGeneric RAG
Multi-signal scoring with source citations — fewer hallucinations.
Use cases

Built for teams shipping financial AI.

Use AlphaCreek when your AI product needs filing-backed answers, source-linked context, and a retrieval path your users can verify.

Filing Q&A

Let users ask questions across 10-Ks, 10-Qs, 20-Fs, 6-Ks, and 8-Ks with source-linked answers.

Risk factor analysis

Retrieve and compare Item 1A disclosures across periods.

MD&A analysis

Pull management commentary, operating drivers, liquidity discussion, and margin explanations.

Segment and revenue context

Retrieve original filing language behind segment, product, and geographic performance.

Due diligence agents

Give agents traceable context for business, legal, accounting, and risk disclosures.

Internal research copilots

Bring SEC filings into Claude, Perplexity, Cursor, Claude Code, or another MCP-compatible workflow.

Try it in code

Connect to AlphaCreek MCP with less than 50 lines of code

Snippets are illustrative only. Follow the link on the code card for runnable examples and the MCP reference.

1# Illustrative — Claude + AlphaCreek MCP (Streamable HTTP).
2# Runnable script: project_ff/alphacreek_mcp/examples/python_anthropic.py — docs: /docs#python-anthropic-example
3
4import asyncio
5import functools
6import mcp.types as T
7from anthropic import Anthropic
8from mcp import ClientSession
9from mcp.client.streamable_http import streamablehttp_client
10
11MCP_URL = "https://mcp.alphacreek.ai/mcp"
12HEADERS = {"Authorization": "Bearer <ALPHACREEK_API_KEY>"}
13QUESTION = "What are NVIDIA's biggest risks in the latest 10-K?"
14
15async def ask_with_filing_tools() -> None:
16    ac = Anthropic(api_key="<ANTHROPIC_API_KEY>")
17    async with streamablehttp_client(MCP_URL, headers=HEADERS, timeout=120, sse_read_timeout=300, terminate_on_close=True) as (read, write, _):
18        async with ClientSession(read, write, client_info=T.Implementation(name="demo", version="0")) as session:
19            await session.initialize()
20            listed = await session.list_tools()
21            atools = [
22                {
23                    "name": t.name,
24                    "description": ((t.description or "").strip() or "(MCP tool)"),
25                    "input_schema": t.inputSchema if isinstance(t.inputSchema, dict) else {"type": "object", "properties": {}},
26                }
27                for t in listed.tools
28            ]
29            messages = [{"role": "user", "content": QUESTION}]
30            call = functools.partial(
31                ac.messages.create,
32                model="claude-sonnet-4-6",
33                max_tokens=8192,
34                system="Answer using only AlphaCreek filing tools; ground claims in tool output.",
35                messages=messages,
36                tools=atools,
37                tool_choice={"type": "auto"},
38            )
39            resp = await asyncio.to_thread(call)
40            # If stop_reason is tool_use: await session.call_tool(...), append assistant + user tool_result
41            # blocks to messages, then messages.create again until end_turn (see /docs).
42
What we do

AlphaCreek enables your
AI agent to
use SEC filings efficiently

We transforms every filing into high-signal, LLM-ready context so your AI can reason over real financial data with precision.

Agent query
"What are Apple's key risks for FY2025?"
AAPL 10-K · Table of Contents
Item 1 — Business
Item 1A — Risk Factorsnavigated
↳ Operations & Supply Chain
↳ Macroeconomic Conditions
↳ Legal & Regulatory
Item 7 — MD&A
Item 8 — Financial Statements
↓ Targeted retrieval
10-K - 1A Risk Factors · AAPL · 2025
Supply chain concentration in China…
~420 tok
Navigable Filing Map

Smart navigation

We generate a table of contents for every filing we ingest. This allows AI agents to understand the filing structure and then navigate to the most relevant sections efficiently, instead of reading the entire document or searching naively.

Why this matters
  • Agents understand the filing structure without reading it fully
  • No blind spots - agents know where to zoom in
  • Mirrors the way human analysts actually read filings
Agent Context Payload
GOOG · 10-K 2025 · Revenue by Segment~420 tokens
"We report our segment results as Google Services, Google Cloud, and Other Bets:, Google Services includes products and services such as ads, Android..."
↗ SEC EDGAR · Filed 2026-02-04 · Accession 0000320193-23-000106
GOOG · 10-Q Q3 2025 · Notes~310 tokens
"Our revenue growth rate could decline over time as a result of a number of factors, including changes in customer usage and demand ..."
↗ SEC EDGAR · Filed 2025-10-04 · Accession 0000320193-23-000077
Token footprint vs. raw filing
AlphaCreek contextRaw filing (100%)
Token-Efficient Retrieval

Pay for insight, not for noise

The smart navigation allows agents to consume only what's important for the query at hand. The result: dramatically lower token consumption, faster responses, and more model headroom for the reasoning that actually matters.

Why this matters
  • Agents skip the noise and zero in on what matters
  • Lower API costs that compound at production scale
  • Frees model attention for analysis, not skimming pages
GOOG · 10-K 2025
Parsed & cited chunks
✓ Citation-ready
§ 1A — Risk Factors
AI competition & regulatory scrutiny pose material risks…
↗ GOOG · 10-K 2025 · p.9
§ 7 — MD&A
Cloud revenue $58.7B, up 36% YoY; Search remains #1…
↗ GOOG · 10-K 2025 · p.33
§ 8 — Financial Statements
Total revenue $402.8B; net income $132.2B for FY2025…
↗ GOOG · 10-K 2025 · p.32
Citation-Grade Accuracy

Answers backed by "citations"

Each filing is broken down into referable logical chunks. This enables agents to answer questions with precision and cite the exact parts of the filing that were used to answer the question.

Why this matters
  • Every fact is sourced to a specific filing, section, and passage
  • Answers are easily verifiable
  • Higher trustworthiness of answers
Get started

From API key to cited filing answers in minutes.

Start with self-serve docs and an API key. If you are planning a production integration, talk to us so we can help with rollout, limits, and the right retrieval workflow.

1. Get credentials

Create a free AlphaCreek account and generate an API key from your dashboard for programmatic MCP access.

2. Read the docs

Follow tool schemas, auth flows, and runnable Python or JavaScript examples for OpenAI, Anthropic, and Gemini.

3. Plan production rollout

Use hosted MCP with OAuth or API keys, align on expected usage, and give your users citation URLs they can verify.