MCP QUEEN
ai.scite/mcp A
Ground answers in scientific literature. Search full text, evaluate trust, access full-text articles
Web & Searchv1.0.0streamable-httpapi.scite.ai 👑 routed via the queen ×3
Server identity and mutable locations
| Registry identity | ai.scite/mcp |
| Stable evidence key | https://mcpqueen.com/s/ai.scite/mcp |
| Declared repository | No repository declared Mutable Registry metadata; not proof of current ownership or availability. Mapping synchronized . |
| Operational endpoint | https://api.scite.ai/mcpProbed separately from repository state. |
Repositories can be renamed, transferred, archived, privatized, or deleted. MCP Queen keeps this evidence page and badge keyed to the Registry name. Moved this repository? Follow the maintainer guide.
Research this MCP server inside your agent
Connect MCP Queen to ChatGPT, Claude, or your own agent to retrieve this server's operational evidence, Trust Receipt, caveats, and reviewed field reports without leaving the conversation.
Grade evidence — probed 2026-08-25 20:30 UTC
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 506ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo scite-api-mcp@1.0.0 |
| tooling | 35 / 35 | tools/list OK: 25 tools e.g. "search_literature"; 25/25 described, 25/25 fully-typed schemas, median description 855 chars |
| latency | 7 / 10 | initialize round-trip 506ms |
| provenance | 12 / 15 | description present; no repository URL; version 1.0.0; namespace ai.scite matches endpoint/repo |
Score 94/100 · latency 506ms · 25 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 |
|---|---|---|---|---|
| claim_verification | advertised_corpus_scale | unverified | Advertised corpus-size expression(s) found in public metadata/tool descriptions: 210M+ paper. Black-box discovery does not establish corpus coverage; a manifest or sampled benchmark is required. Observed value: 210M+ paper | live_probe |
| citation_quality | citation_capability_advertised | unverified | Metadata/tool descriptions advertise citation or evidence capability: Large limits with full citations and excerpts produce very large payloads that consume significant LLM context | Returns patent families with titles, abstracts, inventors, assignees, filing status, and citation counts | ions: - _relevance: relevance score (sortDir ignored) - forwardCitationCount: number of forward citations - fa search_clinical_trials Search clinical trials from the scite clinical trials database (ClinicalTrials. No response-level citation benchmark has verified this claim yet. | live_probe |
| security | sensitive_capabilities_declared | concern | 2 discovered tool(s) advertise potentially state-changing or privileged capabilities. Tool names: delete_collection, remove_dois_from_collection. Classification is description-based and does not prove exploitability. Observed value: delete_collection, remove_dois_from_collection Sample: n=2 | 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/ai.scite/mcp.json
Connect your agent
Claude Code:
claude mcp add --transport http mcp https://api.scite.ai/mcp
Generic MCP client config:
{ "mcpServers": { "mcp": { "type": "http", "url": "https://api.scite.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.scite/mcp · referral link https://mcpqueen.com/go/ai.scite/mcp (safe HTTPS redirect; GET does not write state).
Own this server? Embed your grade badge
Live operational-grade badge, re-probed continuously — not a security or data-quality certification. Copy the ready-made Markdown into your README:
[](https://mcpqueen.com/s/ai.scite/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.
Queen Watch
Email alerts when the grade changes or the endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta. Need recommendations and change review across several servers? Try the Scout + Guard pilot.
Probe history
| When (UTC) | Grade | Score | Latency |
|---|---|---|---|
| 2026-08-25 20:30 | A | 94 | 506ms |
| 2026-08-20 23:00 | A | 97 | 446ms |
| 2026-08-16 07:00 | A | 97 | 192ms |
| 2026-08-12 05:00 | A | 97 | 230ms |
| 2026-08-08 11:15 | A | 97 | 206ms |
| 2026-08-04 15:01 | A | 97 | 232ms |
| 2026-07-31 22:16 | A | 94 | 516ms |
| 2026-07-28 08:31 | A | 97 | 180ms |
| 2026-07-24 22:30 | A | 94 | 698ms |
| 2026-07-21 16:15 | A | 97 | 454ms |