About Calera FINSEC — Certified SEC Memory
Calera FINSEC is an MCP server for agents that need financial data from SEC EDGAR filings. It offers certified metrics with filing provenance, valuation inputs, and explicit refusals when facts are missing or ambiguous.
Key features
- 01Natural-language SEC fact queries
- 02Exact metric and period retrieval
- 03Certified valuation input packs
- 04CAGR and arithmetic calculations
- 05Filing accessions and audit hashes
- 06Safe refusal for uncertain facts
Use cases
- 01Verify a company's reported revenue
- 02Compare company financial results
- 03Calculate growth from filing data
- 04Gather inputs for valuation analysis
MCP support
Exposes seven tools to MCP clients for querying certified SEC EDGAR facts, retrieving valuation inputs, calculating metrics, and comparing sector peers. Results include filing provenance or a safe refusal when data is unavailable or ambiguous.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://finsec.caleralabs.com/mcpclaude mcp add --transport http calera-labs-finsec https://finsec.caleralabs.com/mcp{"mcpServers":{"calera-labs-finsec":{"type":"http","url":"https://finsec.caleralabs.com/mcp"}}}Open in Cursor{"servers":{"calera-labs-finsec":{"type":"http","url":"https://finsec.caleralabs.com/mcp"}}}Open in VS Code{"mcpServers":{"calera-labs-finsec":{"type":"http","url":"https://finsec.caleralabs.com/mcp"}}}{"mcpServers":{"calera-labs-finsec":{"serverUrl":"https://finsec.caleralabs.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://finsec.caleralabs.com/mcpAuth requiredTools
7| Parameter | Type | Required | Description |
|---|---|---|---|
| metric | string | Yes | EDGAR metric to compound, e.g. revenue, free cash flow, net income |
| company | string | Yes | Company ticker or name, e.g. AAPL |
| end_period | string | Yes | End fiscal period, e.g. FY2023 |
| low_tokens | boolean | No | Optional. When true, returns compact JSON schema. |
| start_period | string | Yes | Start fiscal period, e.g. FY2020 |
Details
From the project READMEFINSEC — 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 — The Calera Lattice Supplies Ground Truth."
⚡ 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.
- 2026-07-28 Stateless Protocol Core: Fully compliant with the 2026-07-28 Stateless MCP Specification (SEP-2243, SEP-2575, SEP-2549) with sub-5ms zero-handshake direct tool calls and intelligent caching (
ttlMs: 86400000). - 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.
🚀 1-Click Quickstart Integrations
1. Cursor IDE
Add the following to your project's .cursor/mcp.json (or global Cursor Settings → Features → 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"
}
}
}
}
}
5. Stdio JSON-RPC & Zero-Config Auto-Bridge
For local agent workflows (Cursor, Claude Code, Antigravity, or custom runners) using stdio:
{
"mcpServers": {
"finsec": {
"command": "npx",
"args": ["-y", "@caleralabs/finsec-mcp"]
}
}
}
🔗 Zero-Config Cross-MCP Credential Sharing
When executed via stdio, @caleralabs/finsec-mcp automatically discovers and links credentials stored at ~/.calera/icx.env or created when running @caleralabs/llm-vm-mcp (claim_free_icx_tokens).
A single Calera API key (ICX_API_KEY) unifies your entire AI stack:
- FINSEC Ground Truth: 4.06M certified SEC EDGAR facts with zero hallucination.
- LLM-VM Execution: Hermetic zero-escape MicroVM sandboxes.
- ICX Memory: Shared infinite-context memory space across agent sessions.
🛠️ 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. |
💡 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."
🏎️ 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"
}
🔑 Authentication & API Keys
Generate your free or enterprise API key on the Universal Dashboard:
👉 https://dashboard.caleralabs.com
🛡️ 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.
💬 Customer Support & Immediate Slack Pipeline
Have a question, encountered an edge case, or need a quota increase for your team?
We have a 3-tier Slack customer response pipeline wired directly into our engineering and executive teams:
1. Directly in Your AI Assistant (Claude, Cursor, Zed, Cline)
Use the built-in MCP tool submit_support_ticket:
{
"title": "Need 50k req/min quota for quant backtesting cluster",
"description": "We are running systematic macro backtests across 500 tickers simultaneously.",
"inquiry_type": "quota_increase",
"priority": "high",
"contact_email": "[email protected]"
}
2. Live Web Portal & Slack Escalation Center
Submit tickets, questions, or feature requests directly from the Universal Dashboard: 👉 https://dashboard.caleralabs.com/dashboard#customer_service
3. Response SLAs
| Tier | Responder | SLA Guarantee |
|---|---|---|
| Tier 1 (Normal) | Customer Success Manager (@manager_oncall) | < 4 Hours |
| Tier 2 (High / Quota) | Operations Owner (@owner_oncall) | < 2 Hours |
| Tier 3 (Critical / VIP) | Founder & CEO Casey (@casey) | < 1 Hour |
🔗 Related Calera MCP Servers
- Calera Infinite Context (ICX) MCP: Persistent epistemic memory and sub-5ms associative recall on the Volumetric Lattice Network for AI agents (Glama Hub · Smithery).
📄 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.).
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.