PreClick scans links for threats and confirms intent match with high accuracy before agents click.
AI & Agentsv0.3.6streamable-httppreclick.ai repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 904ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo ai.preclick/preclick-mcp@0.3.6 |
| tooling | 35 / 35 | tools/list OK: 6 tools e.g. "url_scanner_async_scan"; 6/6 described, 6/6 fully-typed schemas, median description 324 chars |
| latency | 7 / 10 | initialize round-trip 904ms |
| provenance | 15 / 15 | description present; repository linked; version 0.3.6; namespace ai.preclick matches endpoint/repo |
Score 97/100 · latency 904ms · 6 tools · auth: open
Claude Code:
claude mcp add --transport http preclick-mcp https://preclick.ai/mcp
Generic MCP client config:
{ "mcpServers": { "preclick-mcp": { "type": "http", "url": "https://preclick.ai/mcp" } } }
MCP Queen is a graded index, not a middleman — your agent connects directly to the server above. Check the grade and evidence first; that's the point.
Share this server: permalink https://mcpqueen.com/s/ai.preclick/preclick-mcp · referral link https://mcpqueen.com/go/ai.preclick/preclick-mcp (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/ai.preclick/preclick-mcp)
Think the grade is wrong? Fix the finding the evidence shows, then the next probe cycle picks it up automatically (full cycle ≈ 3 days) — or open a dispute via the MCP endpoint.
Email alerts when the grade changes or the endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.
| When (UTC) | Grade | Score | Latency |
|---|---|---|---|
| 2026-07-12 15:16 | A | 97 | 904ms |