{"slug": "i-built-an-mcp-server-that-gives-ai-agents-exact-high-precision-finance-math", "title": "I built an MCP server that gives AI agents exact, high-precision finance math", "summary": "A developer has built PrecisionCalc MCP, a Model Context Protocol server that provides AI agents with deterministic, arbitrary-precision financial calculations. The server, available at precisioncalc-mcp.pages.dev/mcp, offers 11 tools that return exact values, formulas, inputs, and assumptions, avoiding the floating-point errors and hallucinations common in LLM arithmetic. It is free to start, integrates with Cursor, Claude Desktop, and other MCP clients, and is listed in the official MCP Registry.", "body_md": "LLMs are shockingly bad at arithmetic. Ask an agent to chain a CAC payback with a churn-adjusted LTV, convert it to EUR, and discount three years of cash flows, and you will get an answer that *looks* right and is quietly wrong. Floating point, dropped steps, and confident hallucination are a bad combination when the output is a number someone makes a decision on.\n\nSo I built **PrecisionCalc MCP** — a deterministic [Model Context Protocol](https://modelcontextprotocol.io) server that gives AI agents a calculator they can actually trust. Every monetary/financial value is computed with arbitrary-precision decimals (**never floats**), and every response includes the exact value, the **formula used**, the **inputs**, the unit, and any assumptions — so the agent (and you) can audit it.\n\nIt's live, free to start, and takes about 30 seconds to add.\n\nIt's a remote server over Streamable HTTP — no install:\n\n```\nhttps://precisioncalc-mcp.pages.dev/mcp\n```\n\n**Cursor** (`~/.cursor/mcp.json`\n\n) or any generic client:\n\n```\n{\n  \"mcpServers\": {\n    \"precisioncalc\": {\n      \"url\": \"https://precisioncalc-mcp.pages.dev/mcp\"\n    }\n  }\n}\n```\n\n**Claude Desktop** (uses the `mcp-remote`\n\nbridge):\n\n```\n{\n  \"mcpServers\": {\n    \"precisioncalc\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"mcp-remote\", \"https://precisioncalc-mcp.pages.dev/mcp\"]\n    }\n  }\n}\n```\n\nAlso works with VS Code, Windsurf, Cline, Zed, and anything speaking MCP. It's listed in the official MCP Registry as `io.github.inity13/precisioncalc-mcp`\n\n.\n\n11 tools, all returning the same clean, parseable envelope:\n\nA call to `net_present_value`\n\nwith `rate=0.10, cashflows=[-10000, 3000, 4200, 6800]`\n\nreturns:\n\n```\n{\n  \"status\": \"success\",\n  \"value\": \"1307.2877535687...\",\n  \"formatted_value\": \"$1,307.29\",\n  \"formula\": \"NPV = sum(CF_t / (1 + rate)^t) for t = 0..n\",\n  \"inputs_used\": { \"rate\": \"0.10\", \"cashflows\": [\"-10000\",\"3000\",\"4200\",\"6800\"] },\n  \"unit\": \"USD\",\n  \"notes\": [\"Period 0 cashflow is not discounted.\", \"...\"]\n}\n```\n\nThe full-precision `value`\n\nis serialized as a string so no precision is lost in JSON transport. The engine is pure and deterministic — same inputs, same output, every time. It ships with a unit-test suite plus Hypothesis property tests that assert invariants like PV↔FV round-trips and NPV(IRR) ≈ 0.\n\n`decimal`\n\nmodule and the official MCP SDK. Runs over stdio or streamable HTTP, with optional API-key auth, rate limiting, structured logging, and OpenTelemetry.`decimal.js`\n\n— verified with 17/17 exact output parity against the Python implementation. That's what powers the free public endpoint.When an agent hits the free limit, the tool returns a structured error containing the checkout URL — so an autonomous agent can surface the paywall and the user is two clicks from a key. Prefer to self-host? The whole thing is MIT-licensed with a Docker image and Fly.io/Render blueprints — run it with unlimited calls and your own keys.\n\n`llms.txt`\n\n: If you build agents that touch money, give it a try and tell me what tool you'd want next. I'm considering bond pricing, WACC, and options (Black-Scholes).", "url": "https://wpnews.pro/news/i-built-an-mcp-server-that-gives-ai-agents-exact-high-precision-finance-math", "canonical_source": "https://dev.to/datanestdigital/i-built-an-mcp-server-that-gives-ai-agents-exact-high-precision-finance-math-40pl", "published_at": "2026-08-10 11:13:46+00:00", "updated_at": "2026-08-10 11:18:17.968642+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "ai-infrastructure"], "entities": ["PrecisionCalc MCP", "Model Context Protocol", "Cursor", "Claude Desktop", "MCP Registry", "Hypothesis", "OpenTelemetry", "Docker"], "alternates": {"html": "https://wpnews.pro/news/i-built-an-mcp-server-that-gives-ai-agents-exact-high-precision-finance-math", "markdown": "https://wpnews.pro/news/i-built-an-mcp-server-that-gives-ai-agents-exact-high-precision-finance-math.md", "text": "https://wpnews.pro/news/i-built-an-mcp-server-that-gives-ai-agents-exact-high-precision-finance-math.txt", "jsonld": "https://wpnews.pro/news/i-built-an-mcp-server-that-gives-ai-agents-exact-high-precision-finance-math.jsonld"}}