Skip to main content
Glama
sgoley

home-slice-mcp

by sgoley
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Home Slice MCP Server

MCP server that provides mortgage calculation tools with live interest rates from Home Slice.

Claude Tools

Features

  • Fetch latest 30-year and 15-year mortgage rates from Home Slice

  • Calculate monthly payments including principal, interest, taxes, insurance, and HOA

  • Support for down payment as percentage or dollar amount

  • Automatic rate fetching or manual rate input

  • Comprehensive cost breakdown

Related MCP server: kakao_mcp_checktime

Installation

Option 1: Docker

# Build the image
docker build -t home-slice-mcp .

# Run the container
docker run -i home-slice-mcp

# Or use docker-compose
docker-compose up

Option 2: Local installation

npm install
npm start

Tools

get_mortgage_rates

Retrieves the latest mortgage rates from Home Slice.

Returns:

  • 30-year mortgage rate

  • 15-year mortgage rate

  • Last updated date

calculate_mortgage

Calculates monthly payment and total costs.

Parameters:

  • purchase_price (required): Home purchase price

  • down_payment (required): Down payment as "20%" or 50000

  • interest_rate (optional): Annual rate %. If omitted, fetches latest from Home Slice

  • loan_term_years (optional): Loan term, default 30

  • property_tax_annual (optional): Annual property tax

  • home_insurance_annual (optional): Annual insurance premium

  • hoa_monthly (optional): Monthly HOA fees

Returns:

  • Monthly breakdown (P&I, taxes, insurance, HOA)

  • Total monthly payment

  • Total interest paid

  • Total cost of ownership

API Access

This project builds on the work of @thejoeosborne and his homeslice-public-api project.

You must request an API key to use this server. Get your API key at: https://www.homesliceapp.ai/api-access

Usage with Claude Desktop

Add to your claude_desktop_config.json:

Using Docker

{
  "mcpServers": {
    "home-slice-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "HOMESLICE_API_KEY='my-api-key-1238792837-598273498'",
        "home-slice-mcp"
      ],
      "env": {}
    }
  }
}

Using local installation

{
  "mcpServers": {
    "home-slice-mcp": {
      "command": "node",
      "args": ["/path/to/home-slice-mcp/index.js"]
    }
  }
}

Available Tools

2 tools
calculate_mortgageB

Calculate monthly mortgage payment with live state-specific rates using HomeSlice API

ParametersJSON Schema
NameRequiredDescriptionDefault
stateYesTwo-letter state code (e.g., FL, CA, TX). Used to determine the average interest rate
loan_termNoLoan term in years (15, 20, 30, or 40)
home_priceYesThe listing price of the home
monthly_hoaNoMonthly cost of homeowner's association (HOA) fees in dollars
monthly_pmiNoMonthly cost of private mortgage insurance (PMI) in dollars
interest_rateNoAnnual interest rate as percentage (e.g., 6.5). If not provided, uses current average rate for the state
down_payment_amtYesDown payment amount. If down_payment_type is "percent", enter percentage (e.g., 10 for 10%). If "amount", enter dollar amount (e.g., 80000)
yearly_insuranceNoYearly cost of homeowner's insurance in dollars
down_payment_typeYesType of down payment: "percent" or "amount"percent
yearly_property_taxNoYearly cost of property tax in dollars

TDQS

B3.3/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description only reveals that it uses live rates from an external API. It does not disclose whether the tool is read-only, what errors might occur, network dependencies, or any limitations, leaving the agent without crucial safety or behavior context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that immediately states the action and key context. Every word earns its place with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

While the schema fully documents all 10 parameters, the description lacks any mention of return value format or potential limitations (e.g., unsupported states). The complexity of external API usage and optional parameters calls for more context, but the core purpose is adequately communicated for a straightforward calculator if the agent can infer the output.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with detailed parameter descriptions in the schema itself. The tool description adds no parameter-specific semantics beyond saying 'live state-specific rates,' which is already captured in the state parameter description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function with a specific verb ('Calculate') and resource ('monthly mortgage payment'), and adds context ('live state-specific rates using HomeSlice API'). This distinguishes it from the sibling get_mortgage_rates, which presumably only retrieves rates.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is used for mortgage payment calculations but provides no explicit guidance on when to use it versus get_mortgage_rates. There are no exclusions, prerequisites, or alternative tool references.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_mortgage_ratesA

Retrieve live mortgage rates for a specific state from HomeSlice API

ParametersJSON Schema
NameRequiredDescriptionDefault
stateYesTwo-letter state code (e.g., FL, CA, TX)

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden. It discloses that the rates are 'live' and come from the 'HomeSlice API', adding some context. However, it does not mention potential latency, errors, or read-only nature, leaving behavioral details sparse.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, front-loaded with the action and resource, with no redundant text. It is concise and immediately understandable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with one fully documented parameter and no output schema. The description effectively communicates the purpose and input, though it could optionally mention the response format or error behavior. Given the low complexity, it is sufficiently complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema fully describes the single parameter 'state' with a clear example and format. The description adds no extra semantic meaning beyond 'specific state', so the schema provides all necessary parameter info, matching the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Retrieve' and the resource 'live mortgage rates', scoped to 'a specific state', which distinguishes it from the sibling tool 'calculate_mortgage' that likely computes rates rather than fetches them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use this tool (when you need live mortgage rates for a state) but does not explicitly mention alternatives, exclusions, or when not to use it. The sibling tool 'calculate_mortgage' is not referenced.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv1.0.0
    • First observedcalculate_mortgage
    • First observedget_mortgage_rates
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.7/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: one retrieves live rate data, the other performs a calculation using those rates. There is no overlap in functionality, so an agent can easily select the correct tool based on the task.

Naming Consistency5/5

Both tool names follow the same verb_noun pattern ('get_mortgage_rates', 'calculate_mortgage'), with specific and descriptive nouns. The consistent structure makes the API predictable and easy to navigate.

Tool Count3/5

With only two tools, the server feels thin, but the narrow scope of mortgage rate retrieval and payment calculation justifies the minimal count. It is borderline on the low end of the typical 3-15 tool range.

Completeness4/5

The core workflow is covered: fetch rates and calculate a mortgage payment. Missing features like custom rate input or amortization schedules are minor gaps that agents can work around for typical use cases.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers