Skip to main content
Glama
ashev87

Propstack MCP

search_properties

Search and filter properties in Propstack CRM using fulltext queries, status, type, price range, size, and custom fields to narrow results.

Instructions

Search and filter properties (Objekte) in Propstack CRM.

Use this tool to:

  • Find properties by address, ID, or exposé ID (use 'q' for fulltext)

  • Filter by status, type, marketing type, or project

  • Find properties in a price/rent range

  • List properties by size, rooms, or construction year

  • Filter by custom fields with cf_ prefix parameters

The 'q' parameter searches: unit_id, street, zip code, city, district, exposé ID.

Range filter pattern: 11 numeric fields each have _from and _to variants. For example, price_from=200000 & price_to=400000 finds properties priced 200–400k. Available range fields: price, base_rent, total_rent, property_space_value, living_space, plot_area, number_of_rooms, number_of_bed_rooms, number_of_bath_rooms, floor, construction_year.

Common queries:

  • "Apartments 300–400k in Berlin": q="Berlin", marketing_type=BUY, rs_type=APARTMENT, price_from=300000, price_to=400000

  • "All available rentals": marketing_type=RENT, status=<available_id from get_property_statuses>

  • "Properties on market 90+ days": sort_by=created_at, order=asc

  • "What's in Project X?": project_id=

Always returns total count. Use expand=true for custom fields.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoFulltext search across unit_id, street, zip, city, district, exposé ID
pageNoPage number (default: 1)
exactNoUse exact matching for text search
groupNoFilter by tag/group ID (Merkmal)
orderNoSort order (default: desc)
expandNoInclude full details and custom fields
statusNoComma-separated property status IDs (use get_property_statuses to look up)
countryNoFilter by country code (e.g. 'DE')
rs_typeNoProperty type filter
sort_byNoField to sort results by (default: unit_id)
archivedNoArchive filter: '-1' = all (including archived), '1' = archived only. Omit for non-archived only (default).
floor_toNoMaximum floor
per_pageNoResults per page (default: 25)
price_toNoMaximum purchase price (EUR)
floor_fromNoMinimum floor
price_fromNoMinimum purchase price (EUR)
project_idNoFilter by project ID
object_typeNoObject category: LIVING (Wohnen), COMMERCIAL (Gewerbe), INVESTMENT (Anlage)
base_rent_toNoMaximum base rent (EUR/month)
plot_area_toNoMaximum plot area (m²)
property_idsNoFilter to specific property IDs
total_rent_toNoMaximum total rent (EUR/month)
base_rent_fromNoMinimum base rent (EUR/month)
marketing_typeNoFilter by marketing type: BUY (Kauf) or RENT (Miete)
plot_area_fromNoMinimum plot area (m²)
living_space_toNoMaximum living space (m²)
total_rent_fromNoMinimum total rent (EUR/month)
include_variantsNoInclude property variants
living_space_fromNoMinimum living space (m²)
number_of_rooms_toNoMaximum number of rooms
construction_year_toNoBuilt before this year
number_of_rooms_fromNoMinimum number of rooms
construction_year_fromNoBuilt after this year
number_of_bed_rooms_toNoMaximum bedrooms
number_of_bath_rooms_toNoMaximum bathrooms
property_space_value_toNoMaximum property space (m²)
number_of_bed_rooms_fromNoMinimum bedrooms
number_of_bath_rooms_fromNoMinimum bathrooms
property_space_value_fromNoMinimum property space (m²)
Behavior3/5

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

Without annotations, the description carries the behavioral transparency burden. It mentions that the tool always returns total count and optionally expand custom fields. It does not discuss rate limits, error handling, or detailed output structure. While adequate for a read tool, more transparency about pagination or defaults would improve it.

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

Conciseness4/5

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

The description is well-structured with bullet points and examples, front-loading the purpose. It is somewhat lengthy but justified given the tool's complexity (39 parameters). Every sentence adds value, though a slight trim could improve conciseness.

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?

Given the large number of parameters and no output schema, the description covers usage patterns well, including examples and total count mention. It lacks description of return structure (e.g., object fields), but for a search tool, it is fairly complete.

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

Parameters4/5

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

With 100% schema coverage, baseline is 3. The description adds value by explaining the range filter pattern (from/to), grouping numeric fields, and clarifying the scope of the 'q' parameter. Examples demonstrate common usage, going beyond the schema.

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 ('search and filter') and resource ('properties in Propstack CRM'), distinguishing it from sibling tools like get_property (single property) and list_projects (projects). It provides specific details about search criteria.

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

Usage Guidelines4/5

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

The description includes explicit guidance on when to use the tool, such as finding properties by address, ID, or filtering by various fields. It provides common query examples. However, it does not explicitly state when not to use it or alternatives, though sibling differentiation is implicit.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ashev87/propstack-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server