Learning Resources
typeza.ai
Provides tools for exploring Typeza personality types, socionics relationship types, and starting a 41-question personality test.
ENDPOINT 1
https://api.typeza.ai/mcp
MCP server metadata
- Name
- typeza
- Version
- 1.0.0
Typeza is a socionics personality test with plain-language profiles of the 16 personality types and the 16 relationship types between them. Use these tools to describe a type, to explain how two types relate (for example the person and their partner, friend or colleague), or to let the person take the Typeza test right here and get their type. - Every output names types and relations by their Typeza names (Analyst, Craftsman, Duality). Use those names; inputs also accept codes and slugs. - Duality is the relation for partners and friends. When the question is about work, describe the pair as business relations. - Typeza describes typical patterns between types, not what anyone should do. Do not turn a relation into advice or a prediction for a real relationship, and pass on the disclaimer that relationship outputs carry. - Share the typeza.ai links the outputs give, so the person can read more.
Known tools 10
list_personality_typesList the 16 Typeza personality types: name, subtitle, quadra and the typeza.
Inferred read-onlyget_personality_typeDescribe one personality type: name, subtitle, quadra, key traits, a short profile in markdown and its typeza.
Inferred read-onlylist_relationship_typesList the 16 socionics relationship types: name, one-line tagline, category (comfortable, neutral or tense) and the typeza.
Inferred read-onlyget_relationship_betweenExplain the relationship between two personality types: the relation's name, tagline and category, a sentence saying which side each type is on, the opening of Typeza's article on it, the relation page (relationship_url), the full article for this pair (pair_url) and a disclaimer.
Inferred read-onlystart_testStart the Typeza personality test in this conversation: 41 short questions, no account needed.
Inferred read-onlyanswer_testSend the person's answers for one batch of a Typeza test begun with start_test, using its draft_id and key.
Potential side effectschoose_test_typeRecord the type the person picks for their finished Typeza test: after answer_test returns status choose_type, the candidate that describes them best, or any type they say fits them better than their result.
Inferred read-onlyget_my_typeGet the signed-in person's own Typeza personality type: name, subtitle, quadra and its typeza.
Inferred read-onlyget_my_invite_linkGet the signed-in person's personal Typeza invite link (https://typeza.
Inferred read-onlylist_my_peopleList the people in the signed-in person's Typeza circle, newest first.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.typeza]
url = "https://api.typeza.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"typeza": {
"type": "http",
"url": "https://api.typeza.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: typeza
Remote MCP URL: https://api.typeza.ai/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"typeza": {
"url": "https://api.typeza.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"typeza": {
"type": "http",
"url": "https://api.typeza.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "typeza",
"transport": "streamable-http",
"url": "https://api.typeza.ai/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for typeza.ai was fetched 2026-11-17T20:27:40.217Z.
typeza.ai is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.