{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_cvdsaztght57","handle":"webify-mcp","url":"https://wellknown.network/agents/webify-mcp","links":{"self":"https://wellknown.network/agents/webify-mcp/record.json","html":"https://wellknown.network/agents/webify-mcp","markdown":"https://wellknown.network/agents/webify-mcp/record.md","api":"https://wellknown.network/api/v1/agents/webify-mcp","status":"https://wellknown.network/api/v1/agents/webify-mcp/status","claim":"https://wellknown.network/agents/webify-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/webify-mcp/claim.json","badge":"https://wellknown.network/agents/webify-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:webify-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"webify-mcp","summary":"Adaptive web research for AI coding agents — 91% of Deep Research quality at 5% cost","description":"# Webify\n\nAdaptive web research for AI coding agents. Search the web, build semantic graphs, get synthesized answers — at 5% the cost of deep research tools.\n\nA skill by [GrapeRoot](https://graperoot.dev)\n\n**Docs:** [中文](docs/README.zh-CN.md) | [日本語](docs/README.ja.md) | [한국어](docs/README.ko.md) | [Español](docs/README.es.md) | [हिन्दी](docs/README.hi.md) | [Français](docs/README.fr.md) | [Deutsch](docs/README.de.md) | [Português](docs/README.pt-BR.md) | [Русский](docs/README.ru.md)\n\n## What it does\n\n| Tool | Purpose | Cost |\n|------|---------|------|\n| `web_find(query)` | Multi-source web search + synthesis | ~$0.003/query |\n| `web_lookup(url, query)` | Single-page graph retrieval | ~$0.0005/query |\n\n**web_find** searches DuckDuckGo, builds semantic graphs from multiple sources in parallel, extracts relevant content via BM25, and synthesizes with Haiku. It adapts depth based on query complexity — simple factual queries hit 3 sources, multi-dimensional research queries scale to 6+ sources with multi-aspect retrieval.\n\n**web_lookup** fetches a single page, builds a heading-hierarchy graph, and returns only the relevant nodes (~250-750 tokens instead of 5,000-50,000).\n\n## Benchmarks\n\nBlind A/B evaluation against Claude's Deep Research on 15 unseen queries (5 tech, 5 non-tech, 5 mixed). Judge: Sonnet, scoring accuracy + completeness + specificity (1-5 each, max 15/query).\n\n| Metric | Webify | Deep Research |\n|--------|--------|--------------|\n| Quality score | **68/75** (90.7%) | 73/75 (97.3%) |\n| Cost per query | **~$0.003** | ~$0.05+ |\n| Latency | **30-90s** | 80-280s |\n| Cost efficiency | **18× better** | baseline |\n\nWebify achieves 91% of Deep Research quality at 5% of the cost. The gap is always on completeness/specificity, never accuracy — Webify finds correct information but Deep Research finds more of it.\n\n<details>\n<summary>Per-query breakdown (unseen validation set)</summary>\n\n| Query | Webify | Deep Research | Winner |\n|-------|--------|--------------|-----…","publisher":null,"homepage":"https://github.com/kunal12203/webify-mcp","repository":"https://github.com/kunal12203/webify-mcp","version":"0.0.2","license":null,"protocols":["mcp"],"tags":["ai","claude","graph","mcp","research","retrieval","search","semantic","web"],"pricing":null,"endpoints":[{"url":"pypi:webify-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"ai.evaluation","name":"Evaluation & Benchmarks","confidence":1,"provenance":"derived"},{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"declared"},{"slug":"research.web","name":"Deep Web Research","confidence":1,"provenance":"declared"},{"slug":"data.web-search","name":"Web Search","confidence":0.894,"provenance":"derived"}],"categories":["ai","data","knowledge","research"],"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":"webify-mcp","registry":"pypi","observedAt":"2026-09-10T15:25:25.618Z","publishedAt":"2026-07-08T22:03:22.004091Z","latestVersion":"0.0.2"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"webify-mcp","url":"https://pypi.org/project/webify-mcp/","firstSeenAt":"2026-09-10T15:24:23.385Z","fetchedAt":"2026-09-10T15:24:23.385Z","normalizedAt":"2026-09-10T15:24:23.385Z"}]},"firstSeenAt":"2026-09-10T15:24:23.385Z","updatedAt":"2026-09-10T15:25:25.618Z"}