The RateSpot MCP Server enables users to access and analyze real-time mortgage rates and loan calculations directly within Claude Desktop.
Retrieve Real-time Mortgage Rates: Get current rates based on specific criteria like location, loan amount, type, term, and credit score
Compare Loan Products: Evaluate different loan options by analyzing financial specifics
Calculate Monthly Payments: Determine estimated payments including interest, PMI, HOA fees, taxes, and insurance
Manage Data Files: List, read, download, delete, and copy CSV files containing mortgage data
Analyze and Compare Data: Perform various analyses (summary, detailed, rates) and compare data between different files
Customize Output Formats: Export mortgage rate data in various formats (markdown, CSV, JSON)
Utilizes .ENV for environment variable management to securely store and access the RateSpot API key
Supports Git for version control and contribution workflow when extending the RateSpot MCP server
Hosted on GitHub for distribution, issue tracking and collaboration on the RateSpot MCP server
Provides specific configuration instructions for running the RateSpot MCP server on macOS with Claude Desktop
Integrates with Node.js as the runtime environment for executing the RateSpot MCP server
Built with TypeScript for type safety and better developer experience when extending the RateSpot MCP server
Incorporates Zod for input validation using schemas to ensure API requests are properly formatted
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@RateSpot MCP Server What are today's mortgage rates for a $500K loan?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Get real-time mortgage rates directly in Claude Desktop with the RateSpot MCP Server.
Claude Desktop: Download and install from claude.ai/download
RateSpot API Key: Get yours at app.ratespot.io
Just like installing a browser extension - no technical knowledge required!
Download: ratespot-mcp-2.0.3.dxt
Double Click the downloaded file into Claude Desktop
Enter your RateSpot API key when prompted
Done! Start asking about mortgage rates immediately
No Node.js, no Terminal, no configuration files needed!
📖 Complete DXT Installation Guide
Note: Version 2.0.3 adds foreclosure listings search with interactive map visualization, streaming support for handling long-running requests, and exposes all CSV/file management tools in the streaming server.
curl -fsSL https://raw.githubusercontent.com/zad0xlik/ratespot-mcp/main/installers/macos/quick-install.sh | bashDownload RateSpot-MCP-Installer.app from installers/macos
Double-click and follow the setup wizard
Download and run setup.bat from installers/windows
Sign up for free at https://app.ratespot.io
Get your API key from Account Settings
To install RateSpot MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @zad0xlik/ratespot-mcp --client claudeAsk Claude about mortgage rates! Try questions like: "Can you get current mortgage rates for a $400,000 loan?"
Related MCP server: DeFi Rates MCP Server
Once installed, you can ask Claude to:
Get Current Rates: "What are today's mortgage rates for a $500K loan?"
Search Foreclosures: "Show me foreclosure listings within 10 miles of 94949"
View Property Maps: "Display foreclosures on an interactive map"
Compare Loan Products: "Compare 15-year vs 30-year mortgages for my situation"
Calculate Payments: "Calculate monthly payment for $400K at 6.5% interest"
Analyze Market Trends: "Show me rate trends for the past 30 days"
Pre-qualify: "Can I qualify for a loan with 750 credit score and $80K income?"
Installation Guides - Detailed installation instructions and troubleshooting
User Guides & Features - Complete feature documentation and usage examples
Manual Setup Instructions - Step-by-step manual configuration for Claude Desktop and Cline
API Documentation - Technical API reference
Testing Guide - Test files and validation scripts
Examples - Usage examples and sample code
Sample Data - Example CSV and JSON data files
If you prefer to install manually or need to customize the setup:
Clone the repository
git clone https://github.com/your-username/ratespot-mcp.git
cd ratespot-mcpInstall dependencies
npm installBuild the server
npm run buildConfigure your API key
cp .env.example .env
# Edit .env and add your RateSpot API keyConfigure Claude Desktop
See installers/manual/CLAUDE_DESKTOP_INSTALLATION.md for detailed instructions
Open Claude Desktop
Click on the settings icon (⚙️)
Go to "Extensions"
Find "RateSpot MCP" in the list
Click "Remove" or the trash icon
Restart Claude Desktop
If you installed manually or need to clean up files:
Remove MCP configuration
rm -rf ~/.config/claude/mcp/ratespot-mcpRemove from Claude Desktop settings
rm -rf "~/Library/Application Support/Claude/mcp/ratespot-mcp"Remove DXT file (if installed via DXT)
rm -f ~/Downloads/ratespot-mcp-2.0.3.dxtRemove DXT streaming server file
rm -f "/Users/[username]/Library/Application Support/Claude/Claude Extensions/local.dxt.ratespot.ratespot-mcp/server/ratespot_mcp_server_streaming.js"Clean up data directory
rm -rf ~/.local/share/claude/mcp/ratespot-mcpUpdate Claude Desktop config file
# Config file location: ${HOME}/Library/Application Support/Claude/claude_desktop_config.json
# Open the file in your preferred editor and remove the ratespot-mcp entry from the extensions sectionCheck and kill any running server processes
# Check if anything is running on port 3001
lsof -i :3001
# If a process is found, kill it using its PID
kill $(lsof -t -i:3001)After uninstallation, restart Claude Desktop to ensure all changes take effect.
Installation Issues: Check docs/installation/ for troubleshooting guides
Usage Questions: See docs/guides/ for feature documentation
API Problems: Visit RateSpot.io Support
MIT License - see LICENSE file for details.
Ready to get started? Download the installer for your platform and you'll be getting mortgage rates in Claude within minutes! 🏠💰
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Path to the file to analyze |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| loanAmount | No | Loan amount in dollars | |
| creditScore | No | Credit score (300-850) | |
| downPayment | No | Down payment amount in dollars | |
| propertyValue | No | Property value in dollars | |
| loanType | No | Loan type (conventional, fha, va, usda) | |
| propertyType | No | Property type (single_family, condo, townhouse, multi_family) | |
| occupancy | No | Occupancy type (primary, secondary, investment) | |
| state | No | State abbreviation (e.g., CA, TX, NY) | |
| zipCode | No | ZIP code | |
| loanTerm | No | Loan term in years (15, 30, etc.) | |
| rateType | No | Rate type (fixed, arm) | |
| format | No | Output format | markdown |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| sessionId | Yes | Session ID from get-mortgage-rates | |
| format | No | Output format | markdown |
| pollInterval | No | Polling interval in milliseconds | |
| maxAttempts | No | Maximum number of polling attempts | |
| stopOnStable | No | Stop polling when record count stabilizes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Path to the directory to list | |
| recursive | No | Whether to list files recursively |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| format | No | Filter by file format | all |
| sortBy | No | Sort results by | date |
| limit | No | Maximum number of files to list |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Path to the file to read |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| sessionId | Yes | Session ID from get-mortgage-rates | |
| format | No | Output format | csv |
| fileName | No | Optional custom filename (without extension) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0analyze-fileget-mortgage-ratesget-streaming-resultslist-directorylist-saved-resultsread-filesave-streaming-resultsScored across 7 tools
The tools are split across unrelated domains—mortgage rates, streaming results, and file operations—so broad purposes are clear. However, 'get-streaming-results' and 'list-saved-results' could easily be confused, and 'analyze-file' vs 'read-file' overlap in intent.
All tool names use a consistent lowercase kebab-case format with a verb-object pattern (get-, save-, list-, analyze-, read-). Minor inconsistency exists in mixing 'streaming-results' and 'saved-results', but the overall pattern is predictable.
Seven tools is a reasonable count and not overwhelming. The count feels slightly scattered because it appears to cover at least three unrelated domains, but no individual tool seems redundant enough to cut.
The tool set lacks a clear central domain, making it hard to assess complete coverage. Mortgage rates have only a read operation, streaming results have get/save/list but no delete, and file tools lack write/delete operations, leaving obvious lifecycle gaps.
Loan & mortgage calculator, compound interest, ROI, crypto prices, FX conversion for AI agents.
US mortgage calculator and amortization API with 50-state property tax, PMI, and affordability data.
Crypto yield data for AI agents: lending, savings, staking, borrowing & stablecoin rates. 18 tools.
Broker-only credit/lending discovery shim for AI agents
