{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_am5afz9wbaw9","handle":"wquestions-mcp","url":"https://wellknown.network/agents/wquestions-mcp","links":{"self":"https://wellknown.network/agents/wquestions-mcp/record.json","html":"https://wellknown.network/agents/wquestions-mcp","markdown":"https://wellknown.network/agents/wquestions-mcp/record.md","api":"https://wellknown.network/api/v1/agents/wquestions-mcp","status":"https://wellknown.network/api/v1/agents/wquestions-mcp/status","claim":"https://wellknown.network/agents/wquestions-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/wquestions-mcp/claim.json","badge":"https://wellknown.network/agents/wquestions-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:wquestions-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"wquestions-mcp","summary":"Model any domain in 7 questions — a WQuestions MCP server.","description":"# wquestions-mcp\n\n**Model any domain in 7 questions.**\n\nAn MCP server that lets Claude Desktop (or any MCP client) build and query a\nknowledge model of *anything* — a spa, a barbershop, a clinic, a bank — using\none fixed set of tools. No per-domain schema to write, ever.\n\n## The problem\n\nEvery domain today gets its own bespoke ontology or database schema: a CRM\nschema for sales, a clinical model for a clinic, a different one again for a\nbank or a taxi dispatcher. None of it transfers between domains, and none of\nit was designed for an LLM to reason over — each new domain means new\nmodeling work before an AI can even start answering questions about it.\n\nWQuestions replaces all of that with a single fixed index: **7 axes** that\nany fact, in any domain, answers. Model a domain by asserting facts on those\n7 axes; query it the same way no matter what the domain is.\n\n## The 7 axes\n\n| Axis | Question | Holds |\n|---|---|---|\n| Q | who | agents |\n| O | what | objects, and reified situations (facts treated as things) |\n| L | where | places |\n| T | when | time points and intervals |\n| N | how much | magnitudes with a unit |\n| K | which / what kind | atemporal categories, types, states |\n| M | how | the predicates that connect Q/O/L/T/N/K to each other — structural, not a value axis |\n\n![demo](https://raw.githubusercontent.com/joseabantomarin/wquestions-mcp/main/docs/demo.gif)\n\n## Quickstart\n\nAdd this to your Claude Desktop config (`claude_desktop_config.json`) and\nrestart Claude Desktop:\n\n```json\n{\n  \"mcpServers\": {\n    \"wquestions\": {\n      \"command\": \"uvx\",\n      \"args\": [\"wquestions-mcp\"]\n    }\n  }\n}\n```\n\nPrefer to run from source? Clone this repo and, from the repo root,\n`pip install -e .` into a virtualenv (the engine is bundled — no other\npackage needed). Then point `command`/`args` at that venv's `wquestions-mcp`\nscript (e.g. `command: \".../.venv/bin/wquestions-mcp\"`, `args: []`) instead\nof `uvx`.\n\nThen ask Claude: *\"Load the spa example, then show me the model.\"* See\n…","publisher":{"name":"Jose Abanto Marin","url":null},"homepage":"https://github.com/joseabantomarin/wquestions-mcp","repository":"https://github.com/joseabantomarin/wquestions-mcp","version":"0.2.0","license":"MIT License  Copyright (c) 2026 Jose Abanto Marin  Permission i…","protocols":["mcp"],"tags":["mcp","llm","knowledge-graph","ontology","wquestions","ai"],"pricing":null,"endpoints":[{"url":"pypi:wquestions-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"declared"},{"slug":"data.database","name":"Databases","confidence":0.791,"provenance":"derived"},{"slug":"productivity.crm","name":"CRM & Sales","confidence":0.733,"provenance":"derived"}],"categories":["data","knowledge","productivity"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"wquestions-mcp","registry":"pypi","observedAt":"2026-09-10T16:24:16.023Z","publishedAt":"2026-07-11T00:14:52.413849Z","latestVersion":"0.2.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"wquestions-mcp","url":"https://pypi.org/project/wquestions-mcp/","firstSeenAt":"2026-09-10T16:22:36.845Z","fetchedAt":"2026-09-10T16:22:36.845Z","normalizedAt":"2026-09-10T16:22:36.845Z"}]},"firstSeenAt":"2026-09-10T16:22:36.845Z","updatedAt":"2026-09-10T16:24:16.023Z"}