Skip to main content
Glama
mcp-geneanet

mcp-geneanet

by mgcrea

Geneanet: Get Family Tree Around a Person

geneanet_get_tree
Read-only

Retrieve a person's ancestors, descendants, and siblings in one call, with relationships resolved and names with life years included; fetch person details separately for places and sources.

Instructions

Ancestors and descendants of one person in a single call, with each relationship already resolved: ancestors carry generation (1 = parents) and fatherIndex/motherIndex; descendants carry relation (child or spouse) with parentIndexes and/or spouseOfIndexes (a cousin marriage has both); siblings are listed too. Names and life years only; use geneanet_get_person on an index for places, sources and notes. One request whatever the depth, but 10 generations can be over a thousand people, so start small.

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": "geneanet_get_tree"
  }
}

Input Schema

NameRequiredDescriptionDefault
nNoSurname key, lower case without accents, as in a profile URL's `n=` (e.g. "louvignes"). Use with `p` instead of `index`, typically straight from a geneanet_search_records hit.
pNoFirst-names key, lower case without accents, as in a profile URL's `p=` (e.g. "marie germaine"; spaces, not +).
ocNoOccurrence number telling apart homonyms in one tree, the URL's `oc=`. Defaults to 0, which is right unless the URL has an oc.
treeNoThe family tree to read: its owner's Geneanet username, the first path segment of a tree URL (gw.geneanet.org/maudrenel1 → "maudrenel1"). Every geneanet_search_records family_tree hit carries it as `tree`. Defaults to GENEANET_TREE when that is set.
indexNoThe person's internal index in THIS tree, the `index` that every other geneanet_* tree tool returns (e.g. 27). Indexes are per tree: the same ancestor has a different index in every tree.
ancestorsNoGenerations of ancestors beyond the person (0-10): 1 = parents, 3 = up to great-grandparents. Defaults to 3.
descendantsNoGenerations of descendants (0-5): 1 = spouses and children. Defaults to 1.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds real value by disclosing that a single request serves any depth, that the payload is limited to names and life years, and that deep requests can explode in size. Auth is not mentioned, though the tree parameter's GENEANET_TREE default is documented in the schema.

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?

Three sentences, each front-loaded with the useful fact: what is returned and how relationships are resolved, what is omitted and where to get it, and the size caveat. No filler wording.

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?

With no output schema, the description carries the burden of describing the return shape and does so well (generation, fatherIndex/motherIndex, relation, parentIndexes, spouseOfIndexes, siblings, names and life years). Minor gaps remain about the overall response envelope, but nothing needed for correct invocation is missing.

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 explains n, p, oc, tree, index, ancestors and descendants. The description reinforces depth semantics ('1 = parents', generation indexes) but adds little beyond what the schema states, making the baseline 3 appropriate.

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 and resource (fetch ancestors and descendants of one person in a single call) and immediately differentiates from the sibling by naming geneanet_get_person for places, sources and notes. An agent can tell which tool to open for tree structure versus person detail.

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?

Explicitly routes detail lookups to geneanet_get_person and warns to 'start small' because 10 generations can exceed a thousand people. It does not spell out when to prefer geneanet_search_tree or search_records, but the alternative and the sizing caution give clear operating context.

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