Skip to main content
Glama
matt1as

Booli MCP Server

by matt1as
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Booli MCP Server

A Model Context Protocol (MCP) server for accessing Swedish real estate data from Booli.se through GraphQL API. This server enables AI assistants to search and analyze property listings using natural language queries.

Features

  • Property Search: Search for apartments and houses with comprehensive filtering options

  • Location Discovery: Find area IDs and location names for targeted property searches

  • Natural Language Queries: AI assistants can interpret conversational property requests

  • GraphQL Integration: Efficient API communication with Booli's GraphQL endpoint

  • Structured Responses: Returns property data in standardized format with rich text formatting

Installation

npm install
npm run build

Configuration

  1. Copy the environment template:

cp .env.example .env

  1. Set the Booli GraphQL endpoint in .env:

BOOLI_GRAPHQL_URL=https://api.booli.se/graphql

Usage

Development

npm run dev

Production

npm start

With Claude Desktop

Add to your Claude Desktop MCP configuration:

{
  "mcpServers": {
    "booli": {
      "command": "node",
      "args": ["/path/to/booli-mcp-server/dist/index.js"],
      "env": {
        "BOOLI_GRAPHQL_URL": "https://api.booli.se/graphql"
      }
    }
  }
}

Available Tools

search_locations

Find location suggestions and area IDs for property searches:

  • query (string, required): Search query to find location suggestions (e.g., "ektorp", "stockholm", "nacka")

  • limit (number, optional): Maximum results to return (default: 10)

Example usage: Use this tool first to discover location IDs, then use those IDs in property searches for more targeted results.

search_properties

Search for properties with comprehensive filtering options:

Basic Parameters:

  • location (string): Location to search (area ID or name, e.g., "Stockholm", "509")

  • minPrice (number): Minimum price in SEK

  • maxPrice (number): Maximum price in SEK

  • minRooms (number): Minimum number of rooms

  • maxRooms (number): Maximum number of rooms

  • minArea (number): Minimum living area in m²

  • maxArea (number): Maximum living area in m²

  • propertyType (string): "apartment" or "house"

Advanced Parameters:

  • minPricePerSqm (number): Minimum price per square meter

  • maxPricePerSqm (number): Maximum price per square meter

  • minPlotArea (number): Minimum plot area for houses

  • maxPlotArea (number): Maximum plot area for houses

  • minConstructionYear (number): Minimum construction year

  • maxConstructionYear (number): Maximum construction year

  • maxRent (number): Maximum monthly rent for cooperatives

  • daysActive (number): Maximum days listing has been active

  • amenities (string): Comma-separated amenities list

  • floor (string): "bottomFloor" or "topFloor"

  • showOnly (string): Special filters (e.g., "priceDecrease,newConstruction")

  • limit (number): Maximum results to return (default: 10)

Example Queries

Location Discovery:

  • "Find locations matching 'ektorp'"

  • "Search for areas in Stockholm"

  • "What locations are available in Nacka?"

Property Search:

  • "Show me 2-bedroom apartments under 4M SEK in Stockholm"

  • "Find houses in Göteborg with at least 100m² living area"

  • "Search for properties in Södermalm between 2-5M SEK"

  • "Find apartments in area 509 with balcony"

Combined Workflow:

  1. First: "Find locations matching 'södermalm'"

  2. Then: "Search properties in area 123 with 2-3 rooms under 5M SEK"

Development

# Install dependencies
npm install

# Build the project
npm run build

# Run tests
npm test

# Type checking
npm run typecheck

# Linting
npm run lint

# Start development server
npm run dev

Testing

The project includes comprehensive test coverage:

# Run all tests
npm test

# Run specific test files
npm test tests/location-types.test.ts
npm test tests/types.test.ts

# Run tests with coverage
npm run test:coverage

Test coverage includes:

  • Type validation with Zod schemas

  • GraphQL client functionality

  • MCP tool implementations

  • Error handling and edge cases

  • Integration tests with real API calls

License

MIT

Available Tools

3 tools
get_property_detailsB

Retrieve comprehensive details for a specific property using its property ID

ParametersJSON Schema
NameRequiredDescriptionDefault
propertyIdYesUnique identifier of the property to retrieve details for (e.g., "12345")

TDQS

B3.1/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'retrieve' and 'comprehensive details', implying a read-only operation, but doesn't specify aspects like rate limits, authentication needs, error handling, or what 'comprehensive details' entails, leaving significant gaps in behavioral 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, efficient sentence that front-loads the key information ('Retrieve comprehensive details') without any wasted words. It is appropriately sized for a simple tool with one parameter, earning a high score for clarity and brevity.

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?

Given the tool's low complexity (1 parameter, no output schema, no annotations), the description is minimally adequate. It states the purpose but lacks details on usage guidelines, behavioral traits, and output expectations, making it incomplete for optimal agent performance despite the simple context.

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 description coverage is 100%, with the parameter 'propertyId' well-documented in the input schema. The description adds no additional meaning beyond what the schema provides, such as format examples or constraints, so it meets the baseline score for high schema coverage without compensating value.

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

Purpose4/5

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

The description clearly states the action ('Retrieve comprehensive details') and resource ('for a specific property'), making the purpose understandable. However, it doesn't differentiate from sibling tools like 'search_properties' or 'search_locations', which might have overlapping functionality, preventing a perfect score.

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 provides no guidance on when to use this tool versus alternatives like 'search_properties' or 'search_locations'. It lacks context about prerequisites, such as needing a property ID, or exclusions, leaving the agent to infer usage from the tool name alone.

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

search_locationsB

Search for location suggestions on Booli.se to find area IDs and names

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query to find location suggestions (e.g., "ektorp", "stockholm", "nacka")
limitNoMaximum number of results to return (default: 10)

TDQS

B3.1/5.0
Behavior2/5

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

No annotations are provided, so the description carries full burden. It mentions the tool searches for suggestions and returns IDs/names, but doesn't disclose behavioral traits like rate limits, authentication needs, pagination, or error handling. For a search tool with zero annotation coverage, this is a significant gap.

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, efficient sentence that front-loads the key action and purpose without unnecessary details. Every word earns its place, making it appropriately sized and well-structured.

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?

Given the tool's moderate complexity (search with 2 parameters), no annotations, and no output schema, the description is minimally adequate. It states the purpose but lacks completeness in behavioral context, usage guidelines, and output details, leaving gaps for an AI agent.

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 description coverage is 100%, so the schema already documents both parameters (query and limit) with descriptions and defaults. The description adds no additional meaning beyond what the schema provides, such as examples or constraints, meeting the baseline for high coverage.

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

Purpose4/5

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

The description clearly states the action ('Search for location suggestions') and the resource ('on Booli.se'), specifying the purpose is to find area IDs and names. It distinguishes from sibling tools (get_property_details, search_properties) by focusing on locations rather than properties, though it doesn't explicitly contrast them.

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?

No guidance is provided on when to use this tool versus alternatives like search_properties, nor any context about prerequisites or exclusions. The description implies usage for finding area IDs/names but lacks explicit when/when-not instructions.

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

search_propertiesC

Search for properties on Booli.se with comprehensive filtering options

ParametersJSON Schema
NameRequiredDescriptionDefault
locationNoLocation to search in (e.g., "Stockholm", "Södermalm", "509" for area ID)
minPriceNoMinimum list price in SEK
maxPriceNoMaximum list price in SEK
minRoomsNoMinimum number of rooms
maxRoomsNoMaximum number of rooms
minAreaNoMinimum living area in square meters
maxAreaNoMaximum living area in square meters
propertyTypeNoType of property to search for
minPricePerSqmNoMinimum price per square meter in SEK
maxPricePerSqmNoMaximum price per square meter in SEK
minPlotAreaNoMinimum plot area in square meters (for houses)
maxPlotAreaNoMaximum plot area in square meters (for houses)
minConstructionYearNoMinimum construction year
maxConstructionYearNoMaximum construction year
maxRentNoMaximum monthly rent in SEK (for tenant-owned cooperatives)
daysActiveNoMaximum days the listing has been active
amenitiesNoComma-separated amenities (e.g., "hasBalconyOrPatio,hasFireplace,buildingHasElevator")
floorNoSpecific floor preference
showOnlyNoSpecial filters (e.g., "priceDecrease,tenureOwnership,newConstruction")
limitNoMaximum number of results to return (default: 10)

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure but offers minimal information. It doesn't mention whether this is a read-only operation, potential rate limits, authentication requirements, or what the output format looks like (especially problematic since there's no output schema). The phrase 'comprehensive filtering options' hints at functionality but lacks concrete behavioral details.

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, efficient sentence that immediately communicates the core functionality. Every word earns its place - 'Search for properties' establishes the action, 'on Booli.se' specifies the context, and 'with comprehensive filtering options' hints at the tool's capabilities without unnecessary elaboration.

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

Completeness2/5

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

For a complex tool with 20 parameters and no output schema, the description is insufficient. It doesn't explain what kind of results are returned, how filtering works in practice, or provide any context about the Booli.se platform. With no annotations and no output schema, the description should do more to help an agent understand how to effectively use this search functionality.

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?

With 100% schema description coverage, the schema already documents all 20 parameters thoroughly. The description adds no additional parameter information beyond what's in the schema - it doesn't explain parameter relationships, filtering logic, or provide usage examples. The baseline of 3 is appropriate since the schema does the heavy lifting.

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

Purpose4/5

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

The description clearly states the action ('Search for properties') and resource ('on Booli.se'), making the purpose immediately understandable. It distinguishes itself from 'get_property_details' by focusing on search rather than retrieval of specific details, though it doesn't explicitly differentiate from 'search_locations' which might be a related search function.

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 provides no guidance on when to use this tool versus alternatives like 'search_locations' or 'get_property_details'. It mentions 'comprehensive filtering options' but doesn't explain when these filters are appropriate or what scenarios warrant this search tool over others.

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. 3 tool updatesv1.0.0
    • First observedget_property_details
    • First observedsearch_locations
    • First observedsearch_properties
Deploy Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.4/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: get_property_details retrieves details for a specific property ID, search_locations finds location suggestions, and search_properties searches properties with filters. There is no overlap in functionality, making it easy for an agent to select the correct tool without confusion.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with snake_case: get_property_details, search_locations, and search_properties. This predictable naming scheme enhances readability and usability for agents.

Tool Count4/5

With 3 tools, the server is well-scoped for a property search domain, but it feels slightly thin as it lacks update or delete operations. However, given the domain (search and retrieval), the count is reasonable and each tool earns its place.

Completeness4/5

The tools cover core search and retrieval workflows for properties and locations on Booli.se, with no dead ends. A minor gap exists in not providing update or delete capabilities, but these may not be applicable to the domain, and agents can work effectively with the available tools.

Resources

Related MCP Connectors