{
  "markdown": "# FINSEC — Certified SEC Memory MCP Server\n\n[![MCP Registry](https://img.shields.io/badge/MCP-Registry_Indexed-blue.svg)](https://registry.modelcontextprotocol.io)\n[![smithery badge](https://smithery.ai/badge/calera-labs/finsec)](https://smithery.ai/servers/calera-labs/finsec)\n[![Glama MCP](https://glama.ai/mcp/servers/Calera-Labs/finsec-mcp/badge)](https://glama.ai/mcp/servers/Calera-Labs/finsec-mcp)\n[![Glama MCP Score](https://glama.ai/mcp/servers/Calera-Labs/finsec-mcp/badges/score.svg)](https://glama.ai/mcp/servers/Calera-Labs/finsec-mcp)\n[![License](https://img.shields.io/badge/License-Apache_2.0-green.svg)](LICENSE)\n[![Facts](https://img.shields.io/badge/SEC_Facts-4.06M_Certified-emerald.svg)](https://finsec.caleralabs.com)\n[![Zero Hallucination](https://img.shields.io/badge/Hallucination_Rate-0.00%25_(∂²=0)-purple.svg)](https://finsec.caleralabs.com)\n\nOfficial **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**.\n\n> **\"Frontier Models Reason — The Calera Lattice Supplies Ground Truth.\"**\n\n---\n\n## ⚡ Key Guarantees\n\n* **0.00% Statistical Hallucination:** Fact recall is deterministic and geometric ($A_4$ Pentatope lattice memory). No language model exists in the fact retrieval path.\n* **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`).\n* **Cryptographic Provenance:** Every returned financial metric includes exact SEC filing accessions, dates, concepts, and SHA-256 audit hashes.\n* **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.\n* **Ultra-Low Latency & High Gross Margins:** Sub-25ms response serialization with low token footprint mode.\n\n---\n\n## 🚀 1-Click Quickstart Integrations\n\n### 1. Cursor IDE\n\nAdd the following to your project's `.cursor/mcp.json` (or global Cursor Settings → Features → MCP):\n\n```json\n{\n  \"mcpServers\": {\n    \"finsec\": {\n      \"url\": \"https://finsec.caleralabs.com/mcp\",\n      \"headers\": {\n        \"X-License-Key\": \"clabs_live_YOUR_KEY\"\n      }\n    }\n  }\n}\n```\n*(Get your free API key at [dashboard.caleralabs.com](https://dashboard.caleralabs.com))*\n\n---\n\n### 2. Claude Desktop\n\nAdd to your `claude_desktop_config.json`:\n* **macOS:** `~/Library/Application Support/Claude/claude_desktop_config.json`\n* **Windows:** `%APPDATA%\\Claude\\claude_desktop_config.json`\n* **Linux:** `~/.config/Claude/claude_desktop_config.json`\n\n```json\n{\n  \"mcpServers\": {\n    \"finsec\": {\n      \"url\": \"https://finsec.caleralabs.com/mcp\",\n      \"headers\": {\n        \"X-License-Key\": \"clabs_live_YOUR_KEY\"\n      }\n    }\n  }\n}\n```\n\n---\n\n### 3. Smithery CLI (1-Click Terminal Command)\n\nInstall automatically across Claude or Cursor using Smithery ([smithery.ai/servers/calera-labs/finsec](https://smithery.ai/servers/calera-labs/finsec)):\n\n```bash\n# For Claude Desktop\nnpx -y @smithery/cli install financesec-mcp --client claude\n\n# For Cursor\nnpx -y @smithery/cli install financesec-mcp --client cursor\n```\n\n---\n\n### 4. Zed Editor\n\nAdd to `~/.config/zed/settings.json`:\n\n```json\n{\n  \"experimental.context_servers\": {\n    \"finsec\": {\n      \"command\": {\n        \"url\": \"https://finsec.caleralabs.com/mcp\",\n        \"headers\": {\n          \"X-License-Key\": \"clabs_live_YOUR_KEY\"\n        }\n      }\n    }\n  }\n}\n```\n\n---\n\n## 🛠️ Certified Tools Surface Area\n\nThe FINSEC MCP server exposes **7 certified tools**:\n\n| Tool Name | Description |\n|---|---|\n| `query_financial_sec` | Natural-language query over 4.06M certified SEC EDGAR facts with provenance or honest `SAFE_REFUSAL`. |\n| `valuation_inputs` | 12 Certified Valuation Packs (DCF inputs, FCF, Altman Z', Beneish M, DuPont 5-step, Piotroski F). |\n| `query_sec_metric_exact` | Exact single-cell EDGAR metric recall for company + period + concept. |\n| `compute_sec_cagr` | Exact compound annual growth rate (CAGR) calculation over verified SEC filing facts with zero confabulation. |\n| `lattice_arith_evaluate` | Deterministic zero-error algebraic solver (`cagr`, `ratio`, `multiply`, `divide`, `yoy_series`, `product_chain`). |\n| `vln_capabilities_overview` | Dynamic scope overview and capability boundaries. |\n| `query_sec_sector_peers` | Multi-company sector & industry financial comparisons. |\n\n---\n\n## 💡 Example Queries for Your Agent\n\nOnce connected, simply ask your agent in plain English:\n\n* *\"What was Apple's FY2023 total revenue and gross margin in USD?\"*\n* *\"Compare Microsoft and Alphabet Q3 2024 operating income.\"*\n* *\"Calculate Nvidia's 3-year revenue CAGR from FY2021 to FY2024.\"*\n* *\"Pull the DuPont 5-step analysis inputs for Tesla in 2023.\"*\n\n---\n\n## 🏎️ Low-Token Mode for High-QPS Agent Swarms\n\nTo eliminate context exhaustion in multi-turn reasoning agents, pass `\"low_tokens\": true` in your queries for a **71.7% token reduction**:\n\n```json\n{\n  \"id\": \"q112\",\n  \"st\": \"OK\",\n  \"val\": 383285000000,\n  \"cur\": \"USD\",\n  \"concept\": \"us-gaap:RevenueFromContractWithCustomerExcludingAssessedTax\",\n  \"per\": \"FY2023\",\n  \"hash\": \"5ce23625\"\n}\n```\n\n---\n\n## 🔑 Authentication & API Keys\n\nGenerate your free or enterprise API key on the **Universal Dashboard**:  \n👉 **[https://dashboard.caleralabs.com](https://dashboard.caleralabs.com)**\n\n---\n\n## 🛡️ Security & Provenance Policy\n\n* **No Language Model in the Fact Path:** All returned numbers originate from XBRL/EDGAR filing tables verified against SEC accessions.\n* **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.\n\n---\n\n## 💬 Customer Support & Immediate Slack Pipeline\n\nHave a question, encountered an edge case, or need a quota increase for your team?\n\nWe have a 3-tier Slack customer response pipeline wired directly into our engineering and executive teams:\n\n### 1. Directly in Your AI Assistant (Claude, Cursor, Zed, Cline)\nUse the built-in MCP tool `submit_support_ticket`:\n```json\n{\n  \"title\": \"Need 50k req/min quota for quant backtesting cluster\",\n  \"description\": \"We are running systematic macro backtests across 500 tickers simultaneously.\",\n  \"inquiry_type\": \"quota_increase\",\n  \"priority\": \"high\",\n  \"contact_email\": \"quant-lead@firm.com\"\n}\n```\n\n### 2. Live Web Portal & Slack Escalation Center\nSubmit tickets, questions, or feature requests directly from the Universal Dashboard:\n👉 **[https://dashboard.caleralabs.com/dashboard#customer_service](https://dashboard.caleralabs.com/dashboard#customer_service)**\n\n### 3. Response SLAs\n| Tier | Responder | SLA Guarantee |\n| :--- | :--- | :--- |\n| **Tier 1 (Normal)** | Customer Success Manager (`@manager_oncall`) | < 4 Hours |\n| **Tier 2 (High / Quota)** | Operations Owner (`@owner_oncall`) | < 2 Hours |\n| **Tier 3 (Critical / VIP)** | Founder & CEO Casey (`@casey`) | < 1 Hour |\n\n---\n\n## 🔗 Related Calera MCP Servers\n\n* **[Calera Infinite Context (ICX) MCP](https://github.com/Calera-Labs/icx-mcp):** Persistent epistemic memory and sub-5ms associative recall on the Volumetric Lattice Network for AI agents ([Glama Hub](https://glama.ai/mcp/servers/Calera-Labs/icx-mcp) · [Smithery](https://smithery.ai/servers/calera-labs/icx-mcp)).\n\n---\n\n## 📄 License & Attribution\n\n* Connector specification and client schemas are licensed under the [Apache-2.0 License](LICENSE).\n* Powered by **Calera Episteme-1** / **Calera Labs** (DBA of Pyrotope Inc., Subsidiary of Calera Computing, Inc.).\n",
  "bytes": 7745,
  "sha": "8c127f6a3fc1fbebbe5b6f2a156fe0434daeb90e1ec9125492335190dd280e55",
  "repo_slug": "calera-labs/finsec-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_caseyyahbara_finsec_bb903820/readme"
}