Screenshots, PDFs and Markdown from any URL or HTML for AI agents, via the SnapForge API
AI & Agentsv1.3.0streamable-httpsnapforge.org repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 80ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo snapforge@1.3.0 |
| tooling | 35 / 35 | tools/list OK: 4 tools e.g. "snapforge_screenshot"; 4/4 described, 4/4 fully-typed schemas, median description 212 chars |
| latency | 10 / 10 | initialize round-trip 80ms |
| provenance | 15 / 15 | description present; repository linked; version 1.3.0; namespace org.snapforge matches endpoint/repo |
Score 100/100 · latency 80ms · 4 tools · protocol access: open ⓘ
Security, data integrity, citation quality, and advertised claims are measured separately from protocol uptime. Missing evidence is marked unverified, never converted into a pass.
| Dimension | Metric | Status | Evidence | Source |
|---|---|---|---|---|
| security | authentication_boundary | observed | Live protocol probe observed auth_state=open. This describes discovery/access behavior; it is not by itself a vulnerability finding. Observed value: open | live_probe |
Machine-readable receipt: /api/trust/org.snapforge/snapforge.json
Claude Code:
claude mcp add --transport http snapforge https://snapforge.org/mcp
Generic MCP client config:
{ "mcpServers": { "snapforge": { "type": "http", "url": "https://snapforge.org/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/org.snapforge/snapforge · referral link https://mcpqueen.com/go/org.snapforge/snapforge (counts as “routed via the queen”).
Live operational-grade badge, re-probed continuously — not a security or data-quality certification. Put it in your README and link to the complete receipt:
[](https://mcpqueen.com/s/org.snapforge/snapforge)
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 |
|---|---|---|---|
| 2026-07-21 03:30 | A | 100 | 80ms |