finsec-mcp
Connects AI agents to over 4 million certified SEC EDGAR financial facts with cryptographic provenance and zero hallucination.
README
FINSEC ā Certified SEC Memory MCP Server
Official Model Context Protocol (MCP) connector for Calera Labs FINSEC. Connects AI agents (Claude Desktop, Cursor, Zed, VS Code, and custom autonomous swarms) directly to 4.06M certified SEC EDGAR facts powered by the Calera Episteme-1 Engine.
"Frontier Models Reason ā The Calera Lattice Supplies Ground Truth."
ā” Key Guarantees
- 0.00% Statistical Hallucination: Fact recall is deterministic and geometric ($A_4$ Pentatope lattice memory). No language model exists in the fact retrieval path.
- Cryptographic Provenance: Every returned financial metric includes exact SEC filing accessions, dates, concepts, and SHA-256 audit hashes.
- Honest Refusal (
SAFE_REFUSAL): If a metric is not present in official SEC filings or is ambiguous, the engine returns an honest safe refusal rather than confabulating numbers. - Ultra-Low Latency & High Gross Margins: Sub-25ms response serialization with low token footprint mode.
š 1-Click Quickstart Integrations
1. Cursor IDE
Add the following to your project's .cursor/mcp.json (or global Cursor Settings ā Features ā MCP):
{
"mcpServers": {
"finsec": {
"url": "https://finsec.caleralabs.com/mcp",
"headers": {
"X-License-Key": "clabs_live_YOUR_KEY"
}
}
}
}
(Get your free API key at dashboard.caleralabs.com)
2. Claude Desktop
Add to your claude_desktop_config.json:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"finsec": {
"url": "https://finsec.caleralabs.com/mcp",
"headers": {
"X-License-Key": "clabs_live_YOUR_KEY"
}
}
}
}
3. Smithery CLI (1-Click Terminal Command)
Install automatically across Claude or Cursor using Smithery (smithery.ai/servers/calera-labs/finsec):
# For Claude Desktop
npx -y @smithery/cli install financesec-mcp --client claude
# For Cursor
npx -y @smithery/cli install financesec-mcp --client cursor
4. Zed Editor
Add to ~/.config/zed/settings.json:
{
"experimental.context_servers": {
"finsec": {
"command": {
"url": "https://finsec.caleralabs.com/mcp",
"headers": {
"X-License-Key": "clabs_live_YOUR_KEY"
}
}
}
}
}
š ļø Certified Tools Surface Area
The FINSEC MCP server exposes 7 certified tools:
| Tool Name | Description |
|---|---|
query_financial_sec |
Natural-language query over 4.06M certified SEC EDGAR facts with provenance or honest SAFE_REFUSAL. |
valuation_inputs |
12 Certified Valuation Packs (DCF inputs, FCF, Altman Z', Beneish M, DuPont 5-step, Piotroski F). |
query_sec_metric_exact |
Exact single-cell EDGAR metric recall for company + period + concept. |
compute_sec_cagr |
Exact compound annual growth rate (CAGR) calculation over verified SEC filing facts with zero confabulation. |
lattice_arith_evaluate |
Deterministic zero-error algebraic solver (cagr, ratio, multiply, divide, yoy_series, product_chain). |
vln_capabilities_overview |
Dynamic scope overview and capability boundaries. |
query_sec_sector_peers |
Multi-company sector & industry financial comparisons. |
š” Example Queries for Your Agent
Once connected, simply ask your agent in plain English:
- "What was Apple's FY2023 total revenue and gross margin in USD?"
- "Compare Microsoft and Alphabet Q3 2024 operating income."
- "Calculate Nvidia's 3-year revenue CAGR from FY2021 to FY2024."
- "Pull the DuPont 5-step analysis inputs for Tesla in 2023."
šļø Low-Token Mode for High-QPS Agent Swarms
To eliminate context exhaustion in multi-turn reasoning agents, pass "low_tokens": true in your queries for a 71.7% token reduction:
{
"id": "q112",
"st": "OK",
"val": 383285000000,
"cur": "USD",
"concept": "us-gaap:RevenueFromContractWithCustomerExcludingAssessedTax",
"per": "FY2023",
"hash": "5ce23625"
}
š Authentication & API Keys
Generate your free or enterprise API key on the Universal Dashboard:
š https://dashboard.caleralabs.com
š”ļø Security & Provenance Policy
- No Language Model in the Fact Path: All returned numbers originate from XBRL/EDGAR filing tables verified against SEC accessions.
- IP Cloud Boundary: Substrate algorithms and $A_4$ Pentatope lattice weights operate inside Calera Labs secure cloud runtimes. Public clients receive only verified outputs and schema responses.
š License & Attribution
- Connector specification and client schemas are licensed under the Apache-2.0 License.
- Powered by Calera Episteme-1 / Calera Labs (DBA of Pyrotope Inc., Subsidiary of Calera Computing, Inc.).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.