Skip to main content
Glama
FamilySearch MCP Server

FamilySearch MCP Server

by G4rutti

download-document

Fetch a FamilySearch record image as a high-resolution JPG or PDF and return it inline so it can be read, then delete it from disk unless keep is set.

Instructions

Fetch a FamilySearch record image (original high-resolution JPG, or PDF through the official viewer) and return it inline so it can be read. By default the file is deleted from disk right after it is returned; pass keep: true to leave it in the download folder.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "download-document"
  }
}

Input Schema

NameRequiredDescriptionDefault
dgsNoDGS/image group number (use together with imageNumber)
keepNoKeep the file on disk after returning it (default false: deleted right away)
formatNojpg is the original high-resolution scan (default)
imageIdNoFamilySearch 3:1 image ID or its ARK URL; alternatively use dgs plus imageNumber
fileNameNoOptional file name; unsafe path characters are removed and existing files are never overwritten
imageNumberNoOne-based image number within the DGS
outputDirectoryNoSub-folder inside the download root (default root: ~/Downloads/familysearch-mcp, override with FAMILYSEARCH_DOWNLOAD_DIR); paths outside the root are rejected

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.2.0

TDQS

A3.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose the key non-obvious side effect: the file is deleted from disk immediately after being returned unless keep: true is passed. It also notes the PDF goes through the official viewer, hinting at a different retrieval path. Gaps remain on authentication/session requirements and error behavior, which matter for a FamilySearch tool given siblings like login-with-browser and set-session-cookie.

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?

Two sentences, front-loaded with purpose and output form, followed by the one behavioral caveat that changes how the tool is called. No filler or 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?

Seven parameters with zero required leaves the agent to work out that either imageId or dgs+imageNumber must be supplied, which the description never states. It also omits how to obtain an image ID or DGS number (likely from search-records or get-image). For a no-annotation, no-output-schema tool, that is a noticeable gap.

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 all seven parameters, including keep, format and path sanitization. The description only restates the keep default and the JPG default, adding no new meaning beyond what the schema provides, so the baseline of 3 applies.

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?

States a specific verb and resource ('Fetch a FamilySearch record image') plus the concrete outputs (high-resolution JPG or PDF via the official viewer) and the inline return so the agent can read it. It does not, however, distinguish itself from siblings like get-image, get-record or list-film-images, leaving ambiguity about which to pick.

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 usage ('return it inline so it can be read') but gives no explicit when-to-use or when-not-to-use guidance and never names alternatives such as get-image or list-film-images. With seven sibling tools in the image/record space, the agent must infer routing on its own.

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