Skip to main content
Glama
Fabrica MCP Server

Fabrica MCP Server

Official
by fabrica-land

Ask Fabrica

ask_fabrica
Read-onlyIdempotent

Answer questions about how Fabrica works using its published docs and help center, returning citable passages with URLs. Suggests lookup tools for property, wallet, or listing questions.

Instructions

Answer questions about how Fabrica works from Fabrica's own published documents: docs.fabrica.land, the help center and the US trust agreement. Returns the best matching passages with their URLs, so an answer can be cited. Covers the trust structure, fees, Property checks, lending, property taxes, the onramp and offramp, the legal framework, the glossary and the MCP server itself. When the question names a specific property, wallet or listing, the result also suggests which lookup tool to call. Retrieval is lexical over a committed index, with no external call.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "question": "<question>"
    },
    "name": "ask_fabrica"
  }
}

Input Schema

NameRequiredDescriptionDefault
sourceNoRestrict to one source: 'docs', 'help' (help center), 'trust-agreement', or 'all' (default)
questionYesThe question in plain language, e.g. 'Who is the trustee of the trust that holds my property?'
maxPassagesNoHow many passages to return (1-10, default 5)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description goes further by disclosing the retrieval mechanism ('lexical over a committed index, with no external call') and the return shape ('best matching passages with their URLs, so an answer can be cited'). Minor gap: the 'suggests which lookup tool' behavior is mentioned but not detailed.

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?

Five sentences, each earning its place: sources, return format, coverage areas, the property/wallet routing rule, and the retrieval mechanism. Slightly front-loading could improve, but no significant waste.

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?

No output schema exists, so the description appropriately describes what is returned (matching passages with URLs). It covers sources, return format, scope, and cross-tool routing. The main missing piece is guidance on what the returned passages look like in detail, but for a retrieval tool this is sufficient.

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 question, source (with enum values), and maxPassages. The description adds no syntax or format detail beyond naming the sources in prose. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

States a specific verb (answer questions) and a well-defined scope: Fabrica's own published documents, explicitly enumerated (docs.fabrica.land, help center, US trust agreement). This is clearly a documentation-retrieval tool, distinct from every sibling which are all lookup/action tools (get_property, search_properties, etc.).

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

Usage Guidelines5/5

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

The description says when to use it (conceptual 'how does Fabrica work' questions) and, crucially, adds a routing rule: when the question names a specific property, wallet or listing, the result suggests which lookup tool to call. This links it to the sibling lookup tools and makes the boundary explicit.

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