Skip to main content
Glama
ianderso

familysearch-mcp

by ianderso
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

search_records

Read-only

Find historical genealogy records on FamilySearch by name, relatives, dates, places, record type, or collection. Relationship criteria help locate people when their own name was misindexed.

Instructions

Search historical records by name, events, relatives, type or collection.

Relationship criteria find a man by his wife's or father's name when his own was misindexed. Scoping to a record type or one collection searches one register instead of the whole archive.

Every criterion filters, loosely: a record lacking that field still matches, names match variants, years match within 5, places widen. With exact, each must be on the record and match. The result's filters says which criteria were applied exactly, relaxed or ignored, and how: read it before calling a nil result a negative.

Pass at least one name. Requires an access token.

Input Schema

NameRequiredDescriptionDefault
countNoMaximum results to return (1-100).
exactNoRequire every criterion to be on the record and to match: names as spelled, years exactly, places within the county or state named where FamilySearch's place filter can find it. Off by default, because spellings and dates vary. Turn it on to bound a negative or cut noise.
givenNoGiven name(s) of the person sought.
looseNoRank by similarity instead of requiring every criterion to match. Off by default: FamilySearch treats a search term as a scoring hint unless told otherwise, so a filter that does not filter is the surprising behaviour.
offsetNoResults to skip, for paging. Past about 1,000 FamilySearch often stops paging; that is reported, not answered with page one.
surnameNoSurname of the person sought.
birth_yearNoApproximate birth year.
death_yearNoApproximate death year.
birth_placeNoBirth place, free text.
death_placeNoDeath place, free text.
record_typeNoRestrict to one kind of record: birth, marriage, death, census, immigration, military, probate or other.
father_givenNoFather's given name(s).
mother_givenNoMother's given name(s).
spouse_givenNoSpouse's given name(s).
collection_idNoRestrict to one collection, by the id search_collections returns. Scoping to a collection is how you search a specific register rather than the whole archive.
marriage_yearNoApproximate marriage year.
father_surnameNoFather's surname.
marriage_placeNoMarriage place, free text.
mother_surnameNoMother's surname, usually her maiden name.
spouse_surnameNoSpouse's surname.
residence_placeNoA place the person is known to have lived.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.3.0
    • changedInput schema / properties / exact / description
      Previous value: -"Require names and places to match exactly. Off by default, because indexed spellings vary and fuzzy matching is usually what you want. Turn it on when a common name returns noise."New value: +"Require every criterion to be on the record and to match: names as spelled, years exactly, places within the county or state named where FamilySearch's place filter can find it. Off by default, because spellings and dates vary. Turn it on to bound a negative or cut noise."
    • changedInput schema / properties / offset / description
      Previous value: -"Results to skip, for paging."New value: +"Results to skip, for paging. Past about 1,000 FamilySearch often stops paging; that is reported, not answered with page one."
  2. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations cover only readOnlyHint and openWorldHint, and the description adds substantial non-obvious behavior: default filters are loose (missing fields still match, name variants match, years match within 5, places widen), exact flips that to strict conjunctive matching, and the result's `filters` field reports exactly/relaxed/ignored — with an explicit warning not to treat a nil result as a negative. It also states the access-token requirement, which no annotation conveys.

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?

Front-loaded with purpose, then structured into relationship/scoping guidance and a filtering-semantics paragraph. Nearly every sentence carries information, though the middle prose is dense enough that it reads more like documentation than a terse tool blurb.

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

Completeness5/5

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

For a 21-parameter, no-output-schema, mutation-free search tool with thin annotations, the description covers what matters most: the implicit name requirement, the token prerequisite, the loose-by-default filtering model, and where to inspect applied criteria in the response. Nothing an agent needs to call it correctly is missing.

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?

Schema coverage is already 100%, so the baseline is 3, but the description adds cross-parameter meaning the schema lacks: the relationship-criteria use case, the archive-vs-register effect of record_type/collection_id, and the precise matching semantics of `exact` versus default loose filtering. It also states the at-least-one-name requirement that the schema (0 required params) does not enforce.

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?

Opens with a specific verb and resource plus the five facets it searches (name, events, relatives, type, collection). This distinguishes it cleanly from siblings such as fulltext_search, get_record, and search_collections without the agent needing to open any schema.

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?

Gives concrete when-to-use cases: relationship criteria recover a man misindexed under his wife's or father's name, and scoping to a type or collection narrows the archive to one register. It also explains when to turn on exact ('to bound a negative or cut noise'). It stops short of naming sibling alternatives like fulltext_search for text-heavy queries, so routing is implied rather than explicit.

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

Deploy Server

Other Tools