MCP QUEEN
online.sasame/research A
No-key MCP: audit/certify MCPs, signed trust history; join Gold Rush Town & build with your LLM.
AI & Agentsv0.8.1streamable-httplive-vps.sasame.online repository
Grade evidence — probed 2026-07-16 18:59 UTC
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 377ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo sasame-mcp-observatory@2.1.0 |
| tooling | 35 / 35 | tools/list OK: 103 tools e.g. "start_here"; 103/103 described, 101/103 fully-typed schemas, median description 291 chars |
| latency | 10 / 10 | initialize round-trip 377ms |
| provenance | 15 / 15 | description present; repository linked; version 0.8.1; namespace online.sasame matches endpoint/repo |
Score 100/100 · latency 377ms · 103 tools · protocol access: open ⓘ
Trust receipt
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 |
|---|---|---|---|---|
| citation_quality | identifier_resolvability:pubmed_lookup | not_testable | No PMID or DOI was exposed, so citation validity could not be tested. Observed value: 0/0 Sample: n=5 | response_benchmark |
| citation_quality | citation_identifier_presence:pubmed_lookup | concern | 0 of 5 benchmark queries exposed at least one machine-resolvable PMID or DOI; 0 identifiers observed. Observed value: 0/5 Sample: n=5 | response_benchmark |
| security | tool_access_boundary:pubmed_lookup | observed | Observed HTTP status distribution across 5 actual tool calls: 200×5. Open initialize/tools-list does not imply open data-tool access. Observed value: {"200":5} Sample: n=5 | response_benchmark |
| data_integrity | response_success_rate:pubmed_lookup | concern | 2 of 5 controlled read-only calls returned a non-error MCP tool result. Observed value: 2/5 Sample: n=5 | response_benchmark |
| citation_quality | citation_capability_advertised | unverified | Metadata/tool descriptions advertise citation or evidence capability: rt output, runtime health where available, tool-surface readability where available, receipt/replay references where available, the stage label, and known limitations | pubmed_lookup FREE preview: real PubMed (NCBI) search | engage_sasame Open an evidence-backed External Call Activation engagement for a public MCP. No response-level citation benchmark has verified this claim yet. | live_probe |
| security | sensitive_capabilities_declared | concern | 6 discovered tool(s) advertise potentially state-changing or privileged capabilities. Tool names: resolve_and_run, capability_profile, capability_landscape, escrow_attest, receipt_status_set, town_claim_confirm. Classification is description-based and does not prove exploitability. Observed value: resolve_and_run, capability_profile, capability_landscape, escrow_attest, receipt_status_set, town_claim_confirm Sample: n=6 | live_probe |
| 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/online.sasame/research.json
Connect your agent
Claude Code:
claude mcp add --transport http research https://live-vps.sasame.online/public-mcp
Generic MCP client config:
{ "mcpServers": { "research": { "type": "http", "url": "https://live-vps.sasame.online/public-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/online.sasame/research · referral link https://mcpqueen.com/go/online.sasame/research (counts as “routed via the queen”).
Own this server? Embed your grade badge
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/online.sasame/research)
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.
Queen Watch
Email alerts when the grade changes or the endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.
Probe history
| When (UTC) | Grade | Score | Latency |
|---|---|---|---|
| 2026-07-16 18:59 | A | 100 | 377ms |
| 2026-07-15 03:15 | A | 100 | 45ms |