Research / Knowledge Work

Site MCP

A web tool that turns a public website into an MCP server so AI agents can search and read its content via a generated link.

Clear26/30
Useful25/30
Specific14/20
Complete14/20
Site MCP screenshot

Why it was accepted

The page clearly presents a real AI-adjacent product with a specific job: converting any public website into an MCP server for agent access. The visible UI text explains the flow, includes a URL input, mentions drag-and-drop, offers an example site, and states that links don’t expire and work with public sites. That is enough evidence for a useful public listing.

Weakness

The snapshot does not show pricing, authentication limits, supported agent clients, crawl depth, or whether private sites are supported. It also does not show any documentation, API details, or examples of the generated MCP link format beyond the basic promise.

Review status

21 days ago #1943 ↑ +2

Last evaluated 21 days ago. Current rank #1943. Up 2 spots in the rankings.

Score history

79

Related listings

Primus AI Researcher – Free screenshot

Research / Knowledge Work

Primus is an autonomous AI researcher that hypothesizes, reads papers, writes code, runs experiments on compute, and drafts research papers. The page shows example tasks, published-paper claims, waitlist access, and positioning for ML research workflows.

Below the Fold — A New York Times X-Ray Dashboard screenshot

Research / Data Visualization

An interactive dashboard that analyzes New York Times coverage since 2000 using the NYT Archive API, with views for reporters, beats, sections, subjects, geography, obituaries, and corrections.

CAD-Bench screenshot
#405 CAD-Bench
88

Research / Knowledge Work

An open benchmark and leaderboard for AI CAD agents, with 308 prompts across 20 categories and layered scoring for geometry, engineering, manufacturability, and cognition.

Benchmarking Inference Engines on Agentic Workloads screenshot

Research / Knowledge Work

A research article from Applied Compute on how agentic, tool-using workloads differ from traditional LLM benchmarks, with production observations, workload profiles, and an open-source harness for replaying traces.