Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@WikiTree MCP server find the ancestors and descendants of Skłodowska-2"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This project provides an MCP server that integrates with the WikiTree API and exposes it as a set of tools.
Disclaimer: This code (and readme) was fully vibe-coded and I am not planning to continue developing it. I have tested it in Gemini CLI. Maybe it could also work in other apps that support the MCP protocol. Feel free to take the code and use it any way you like.
This entire project was implemented by the Gemini CLI itself. Starting with a single prompt, Gemini was asked to create a tool server for the WikiTree API. It wrote the server code, defined the tools, and handled the integration with the Model Context Protocol (MCP) server. This README (the majority of it), and the entire interaction history, serves as a testament to its capabilities.
Related MCP server: WikiJS MCP Server
First, install the necessary dependencies:
npm installThe server is written in TypeScript. Compile it to JavaScript:
npm run buildStart the MCP tool server:
npm start -- --sse --port=3000Add the following settings to ~/.gemini/settings.json:
"mcpServers": {
"wikitree": {
"url": "http://localhost:3000/sse"
}
}You can now run Gemini CLI and questions related to WikiTree.
Here are the example interactions that were used to generate the information about Maria Skłodowska-Curie and her family.
Question:
get parents of Skłodowska-2
Answer:
The parents of Maria Salomea (Skłodowska) Curie (Skłodowska-2) are:
Father: Władysław Skłodowski (Skłodowski-1), born in 1832 and died in 1902.
Mother: Bronisława Marianna (Boguska) Skłodowska (Boguska-1), born in 1835 and died in 1878.
Question:
wWhat are the names of grandparents of Maria Skłodowska?
Answer:
The grandparents of Maria Salomea (Skłodowska) Curie are:
Paternal Grandparents (Parents of Władysław Skłodowski):
Grandfather: Józef Skłodowski (Skłodowski-4), 1804–1882.
Grandmother: Salomea (Sagtyńska) Skłodowska (Sagtyńska-1), 1802–1882.
Maternal Grandparents (Parents of Bronisława Marianna Boguska):
Grandfather: Feliks Boguski (Boguski-1), 1799–1872.
Grandmother: Marianna Zaruska (Zaruska-1).
Question:
short bio of Maria
Answer:
Maria Salomea (Skłodowska) Curie (1867–1934) was a pioneering Polish-French physicist and chemist. She is best known for her groundbreaking research on radioactivity, a term she coined.
Key Achievements:
Nobel Prizes: She was the first woman to win a Nobel Prize and remains the only person to win Nobel Prizes in two different scientific fields (Physics in 1903 and Chemistry in 1911).
Element Discovery: Along with her husband Pierre Curie, she discovered the elements polonium (named after her native Poland) and radium.
Educational Pioneer: She was the first female professor at the University of Paris (Sorbonne).
War Effort: During World War I, she developed mobile X-ray units ("Little Curies") to assist battlefield surgeons.
Personal Life: Born in Warsaw, Poland, she moved to Paris in 1891 to study. She married Pierre Curie in 1895, and they had two daughters, Irène (also a Nobel laureate) and Ève. She died in 1934 from leukemia, caused by her long-term exposure to radiation. She is buried in the Panthéon in Paris.
Question:
Are her ancestors known for something?
Answer:
Maria Skłodowska-Curie's ancestors were largely part of the Polish intelligentsia and minor nobility (szlachta), many of whom were dedicated educators and patriots.
Parents:
Father: Władysław Skłodowski (1832–1902) was a well-known teacher of mathematics and physics and the director of two gymnasiums (secondary schools) for boys in Warsaw.
Mother: Bronisława Boguska (1835–1878) was also an educator. She was the director of a prestigious Warsaw boarding school for girls until she contracted tuberculosis.
Grandparents:
Paternal Grandfather: Józef Skłodowski (1804–1882) was a prominent educator, librarian, and school principal. He was also a participant in the November Uprising (1830–1831), a Polish insurrection against the Russian Empire.
Family Heritage:
Both the Skłodowski and Boguski families belonged to the Polish nobility, though they had lost most of their property and focused their efforts on intellectual pursuits.
Question:
What about her descendants?
Answer:
Maria Skłodowska-Curie had two daughters, both of whom were highly accomplished:
Daughters:
Irène Joliot-Curie (1897–1956): A Nobel Prize-winning scientist. She and her husband, Frédéric Joliot-Curie, were awarded the Nobel Prize in Chemistry in 1935 for their discovery of artificial radioactivity.
Ève Curie (1904–2007): A successful writer, journalist, and concert pianist, famous for writing her mother's biography, Madame Curie. She later worked extensively with UNICEF.
Grandchildren (Children of Irène):
Hélène Langevin-Joliot (born 1927): A distinguished nuclear physicist.
Pierre Joliot (born 1932): A renowned biologist and researcher.
Maria's descendants have continued her legacy of scientific and humanitarian excellence.
Call any WikiTree API endpoint directly
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | WikiTree API action (e.g., 'searchPerson') | |
| params | No | Parameters for the action |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool calls API endpoints 'directly' but doesn't explain authentication requirements, rate limits, error handling, or what 'directly' implies (e.g., raw HTTP calls, response format). This is a significant gap for a generic API tool with potential side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero waste. It's front-loaded and appropriately sized for the tool's purpose, making it easy for an agent to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a generic API tool with no annotations and no output schema, the description is incomplete. It lacks details on authentication, error responses, rate limits, and how to interpret results, which are critical for correct invocation. The presence of sibling tools adds context but isn't addressed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 both parameters (action and params). The description adds no additional meaning beyond what the schema provides (e.g., examples of actions, structure of params). Baseline 3 is appropriate as the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Call any WikiTree API endpoint directly' specifies the verb ('call') and resource ('WikiTree API endpoint'). It distinguishes from siblings like 'get_person' by being a generic API caller rather than a specific data retrieval function. However, it doesn't specify what 'directly' means operationally, keeping it from a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus the sibling tools (get_ancestors, get_descendants, get_person, get_relatives). It doesn't mention alternatives, prerequisites, or exclusions, leaving the agent to infer usage based on the generic nature of the tool versus specialized siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve ancestors for a given person ID
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | WikiTree ID | |
| depth | No | Number of generations to retrieve | |
| bioFormat | No | ||
| fields | No | ||
| resolveRedirect | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions retrieval but lacks details on permissions, rate limits, error handling, or output format. For a tool with 5 parameters and no output schema, this leaves significant behavioral gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, direct sentence with zero wasted words, making it highly concise and front-loaded. It efficiently conveys the core purpose without unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (5 parameters, no annotations, no output schema), the description is inadequate. It doesn't explain return values, behavioral traits, or parameter usage, leaving the agent with insufficient context to use the tool effectively beyond basic purpose.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is low at 40%, with only 'key' and 'depth' described in the schema. The description adds no parameter semantics beyond implying 'person ID' relates to 'key', failing to compensate for the coverage gap or explain parameters like 'bioFormat', 'fields', or 'resolveRedirect'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Retrieve') and target ('ancestors for a given person ID'), making the purpose understandable. However, it doesn't differentiate from sibling tools like 'get_descendants' or 'get_relatives' which likely retrieve similar family data, missing explicit sibling distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'get_descendants' or 'get_relatives', nor does it mention prerequisites or context for usage. It merely states what the tool does without indicating appropriate scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve descendants for a given person ID
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | WikiTree ID | |
| depth | No | Number of generations to retrieve | |
| bioFormat | No | ||
| fields | No | ||
| resolveRedirect | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions retrieval but doesn't cover aspects like rate limits, authentication needs, error handling, or what the output looks like (e.g., format, structure). This leaves significant gaps for a tool with 5 parameters.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no wasted words. It's front-loaded with the core purpose, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (5 parameters, no annotations, no output schema), the description is incomplete. It lacks details on behavior, parameter usage, and output, leaving the agent with insufficient information to use the tool effectively beyond basic invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is low at 40%, with only 'key' and 'depth' having descriptions. The tool description adds no parameter details beyond the schema, failing to compensate for the coverage gap. For example, it doesn't explain what 'bioFormat' or 'fields' entail.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Retrieve') and resource ('descendants for a given person ID'), making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'get_ancestors' or 'get_relatives', which would be needed for a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like 'get_ancestors' or 'get_relatives'. The description only states what it does, without context about appropriate scenarios or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve a single person record from WikiTree
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | WikiTree ID (e.g., 'Smith-1') | |
| bioFormat | No | Format of the biography | |
| fields | No | Fields to retrieve | |
| resolveRedirect | No | Whether to resolve redirects |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. While 'Retrieve' implies a read-only operation, it doesn't clarify authentication requirements, rate limits, error handling, or what happens with invalid keys. For a tool with no annotation coverage, this leaves significant gaps in understanding its behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence that efficiently communicates the core purpose without unnecessary words. It's appropriately sized for a simple retrieval tool and front-loads the essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (4 parameters, no output schema, no annotations), the description is minimally adequate but incomplete. It covers the basic purpose but lacks behavioral details, usage context, and output expectations, which are important for a tool interacting with an external API like WikiTree.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no parameter-specific information beyond what's already documented in the input schema (which has 100% coverage). It doesn't explain the significance of the 'key' parameter (e.g., that it's a unique identifier) or provide examples for 'fields' or 'bioFormat'. With high schema coverage, the baseline is 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Retrieve') and resource ('a single person record from WikiTree'), making the purpose immediately understandable. However, it doesn't explicitly differentiate this tool from sibling tools like get_ancestors or get_descendants, which also retrieve person-related data but with different scopes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like get_ancestors (for lineage) or get_relatives (for family connections), nor does it specify prerequisites or typical use cases for retrieving a single person record.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve relatives for a given person ID or list of IDs
| Name | Required | Description | Default |
|---|---|---|---|
| keys | Yes | WikiTree IDs | |
| getParents | No | ||
| getChildren | No | ||
| getSpouses | No | ||
| getSiblings | No | ||
| bioFormat | No | ||
| fields | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden but only states the basic action. It doesn't disclose behavioral traits such as permissions needed, rate limits, error handling, or what 'retrieve' entails (e.g., format, pagination). This is inadequate for a tool with 7 parameters and no output schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero waste. It's front-loaded and appropriately sized, making it easy to parse without unnecessary details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (7 parameters, low schema coverage, no annotations, no output schema), the description is incomplete. It doesn't explain the tool's behavior, output format, or parameter meanings, leaving significant gaps for an AI agent to understand and invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is low at 14%, with only 'keys' parameter documented. The description adds minimal value by mentioning 'person ID or list of IDs', which loosely relates to 'keys', but doesn't explain the other 6 parameters (e.g., boolean flags for family types, 'bioFormat', 'fields'). It fails to compensate for the coverage gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Retrieve') and resource ('relatives'), specifying it works for 'a given person ID or list of IDs'. It distinguishes from siblings like 'get_ancestors' and 'get_descendants' by focusing on immediate family relations, though it doesn't explicitly contrast them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like 'get_ancestors' or 'get_descendants' is provided. The description implies usage for retrieving relatives but lacks context on prerequisites, exclusions, or comparisons to sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0call_apiget_ancestorsget_descendantsget_personget_relativesScored across 5 tools
Most tools have distinct purposes: get_person retrieves a single record, while get_ancestors, get_descendants, and get_relatives focus on different relationship types. However, get_relatives could be ambiguous with the more specific ancestor/descendant tools, as it might overlap in scope depending on what 'relatives' includes.
Four tools follow a consistent 'get_' prefix pattern (get_ancestors, get_descendants, get_person, get_relatives), which is clear and predictable. The outlier is call_api, which uses a different verb style, but this minor deviation doesn't significantly hinder readability or consistency.
With 5 tools, this is well-scoped for a genealogy-focused server. Each tool serves a distinct purpose in retrieving person data and relationships, and the count is neither too sparse nor overwhelming, fitting typical MCP server ranges.
The toolset covers core read operations for person data and relationships (get, ancestors, descendants, relatives), but lacks update, create, or delete capabilities, which might be expected for a full CRUD lifecycle in a genealogy context. The call_api tool provides flexibility but doesn't fill all gaps directly.
Read-only A2Me family context tools for AI assistants (members, dates, activity, relationships)
Human Lineage MCP server — search and query the public genealogical graph of all humanity
Live Wikipedia edit feed, page summaries, trending pages, and Wikidata search.
Machine-readable entity discovery with provenance, trust and verified source evidence.
