Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

三域医研 · 科研算法引擎 (SanYu Research Engine)

REMOTE · SANYU.WENTANGKEJI.COM

147 tools: deterministic compute + 39 AI writers; each response self-labels data_source + verified.

0 this week 71 Trust /100

Last scanned (21 hours ago)

Scores higher than 56% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Health and Science

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security80
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability70
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 21921 tokens (~146/item across 150 items; 150 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Tools include usage examples.Pass
Stability & Change Management0
  • Stability check failed: schema churn in the 15 days we've observed: 106 tool removals, 0 breaking changes, 0 auth/transport breaks, 149 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 150 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 151 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 16 Nov 26 0
    • “cell_assay_calc” reworded the description of “params” cosmetic

    1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.

  • 13 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
  • 12 Nov 26 0
    • A breaking change shipped without a version bump: still 1.3.0 ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • “qpcr_bayesian_design” added a required parameter “ctrl_ct”, so existing callers break ▼ functional
    • “qpcr_bayesian_design” added a required parameter “treat_ct”, so existing callers break ▼ functional
    • New tool “act_crf_suggest_coding” functional
    • New tool “idea_ignite” functional
    • “qpcr_bayesian_design” reworded the description of “target” cosmetic
    • “qpcr_bayesian_design” made “target” optional cosmetic
  • 11 Nov 26 0
    • A breaking change shipped without a version bump: still 1.3.0 ▼ security
    • Tool “clinical_basic_bridge” was removed ▼ security
    • Tool “design_next_step” was removed ▼ security
    • Tool “idea_ignite” was removed ▼ security
    • Tool “paper_draft_one_click” was removed ▼ security
    • Tool “protocol_export” was removed ▼ security
    • Tool “protocol_export_check” was removed ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “design_protocol_generate” rewrote its description, which is the text the model reads security
    • Tool “differential_expression” rewrote its description, which is the text the model reads security
    • “arrive_checklist” added a required parameter “E1”, so existing callers break ▼ functional
    • “crf_sdtm_validate” added a required parameter “fields”, so existing callers break ▼ functional
    • “design_protocol_generate” added a required parameter “tool_name”, so existing callers break ▼ functional
    • “experiment_plan_generate” added a required parameter “research_question”, so existing callers break ▼ functional
    • “literature_review_outline” added a required parameter “topic”, so existing callers break ▼ functional
    • “nuclei_count” added a required parameter “image_base64”, so existing callers break ▼ functional
    • “sample_size_calculator” added a required parameter “effect_size”, so existing callers break ▼ functional
    • “acceptance_probability” made “journal_id” required, so existing callers break ▼ functional
    • “acceptance_probability” made “paper” required, so existing callers break ▼ functional
    • “consort_flowchart” made “randomized” required, so existing callers break ▼ functional
    • “consort_flowchart” made “screened” required, so existing callers break ▼ functional
    • “dataframe_parse” made “csv_data” required, so existing callers break ▼ functional
    • “differential_expression” made “group_a” required, so existing callers break ▼ functional
    • “differential_expression” made “group_b” required, so existing callers break ▼ functional
    • “fibrosis_staging” made “stage” required, so existing callers break ▼ functional
    • “flow_cluster” made “events” required, so existing callers break ▼ functional
    • “flow_gate” made “events” required, so existing callers break ▼ functional
    • “mif_phenotype” made “cd3_pos” required, so existing callers break ▼ functional
    • “nomogram” made “csv_data” required, so existing callers break ▼ functional
    • “organ_coefficient” made “body_weights” required, so existing callers break ▼ functional
    • “organ_coefficient” made “organ_weights” required, so existing callers break ▼ functional
    • “pcr_primer_design” made “sequence” required, so existing callers break ▼ functional
    • “prisma_flowchart” made “records_identified” required, so existing callers break ▼ functional
    • “propensity_score_matching” made “covariates” required, so existing callers break ▼ functional
    • “propensity_score_matching” made “treatment” required, so existing callers break ▼ functional
    • “shap_explain” made “csv_data” required, so existing callers break ▼ functional
    • “stats_toolbox” made “payload” required, so existing callers break ▼ functional
    • “toxicology_assess” made “hERG_IC50_nM” required, so existing callers break ▼ functional
    • “tumor_microenvironment” made “cancer_type” required, so existing callers break ▼ functional
    • “tumor_volume_curve” made “days” required, so existing callers break ▼ functional
    • “tumor_volume_curve” made “lengths” required, so existing callers break ▼ functional
    • “tumor_volume_curve” made “widths” required, so existing callers break ▼ functional
    • “design_protocol_generate” dropped the required parameter “prompt” ▼ functional
    • “experiment_plan_generate” dropped the required parameter “prompt” ▼ functional
    • “differential_expression” changed the type of “group_a”: string → array ▼ functional
    • “differential_expression” changed the type of “group_b”: string → array ▼ functional
    • “nuclei_count” changed the type of “cell_density”: number → string ▼ functional
    • “ppi_network” changed the type of “species”: string → integer ▼ functional
    • New tool “compare_manuscript_versions” functional
    • New tool “deidentify_phi” functional
    • New tool “distribution_fit” functional
    • New tool “list_my_data_files” functional
    • New tool “omics_methods_draft” functional
    • New tool “proteomics_methods_draft” functional
    • New tool “wetlab_protocol_generate” functional
    • “arrive_checklist” added an optional parameter “E10” cosmetic
    • “arrive_checklist” added an optional parameter “E2” cosmetic
    • “arrive_checklist” added an optional parameter “E3” cosmetic
    • “arrive_checklist” added an optional parameter “E4” cosmetic
    • “arrive_checklist” added an optional parameter “E5” cosmetic
    • “arrive_checklist” added an optional parameter “E6” cosmetic
    • “arrive_checklist” added an optional parameter “E7” cosmetic
    • “arrive_checklist” added an optional parameter “E8” cosmetic
    • “arrive_checklist” added an optional parameter “E9” cosmetic
    • “design_protocol_generate” added an optional parameter “alpha” cosmetic
    • “design_protocol_generate” added an optional parameter “comparison” cosmetic
    • “design_protocol_generate” added an optional parameter “completed_steps” cosmetic
    • “design_protocol_generate” added an optional parameter “design” cosmetic
    • “design_protocol_generate” added an optional parameter “dropout_rate” cosmetic
    • “design_protocol_generate” added an optional parameter “duration_months” cosmetic
    • “design_protocol_generate” added an optional parameter “effect_size” cosmetic
    • “design_protocol_generate” added an optional parameter “event_rate” cosmetic
    • “design_protocol_generate” added an optional parameter “hazard_ratio” cosmetic
    • “design_protocol_generate” added an optional parameter “intervention” cosmetic
    • “design_protocol_generate” added an optional parameter “n_centers” cosmetic
    • “design_protocol_generate” added an optional parameter “n_groups” cosmetic
    • “design_protocol_generate” added an optional parameter “n_subjects” cosmetic
    • “design_protocol_generate” added an optional parameter “outcome” cosmetic
    • “design_protocol_generate” added an optional parameter “outcome_type” cosmetic
    • “design_protocol_generate” added an optional parameter “p1” cosmetic
    • “design_protocol_generate” added an optional parameter “p2” cosmetic
    • “design_protocol_generate” added an optional parameter “population” cosmetic
    • “design_protocol_generate” added an optional parameter “power” cosmetic
    • “design_protocol_generate” added an optional parameter “primary_timepoint” cosmetic
    • “design_protocol_generate” added an optional parameter “secondary_outcomes” cosmetic
    • “design_protocol_generate” added an optional parameter “topic” cosmetic
    • “experiment_plan_generate” added an optional parameter “budget_level” cosmetic
    • “experiment_plan_generate” added an optional parameter “experiment_types” cosmetic
    • “experiment_plan_generate” added an optional parameter “field” cosmetic
    • “experiment_plan_generate” added an optional parameter “involves_gene_editing” cosmetic
    • “experiment_plan_generate” added an optional parameter “involves_infectious_agents” cosmetic
    • “experiment_plan_generate” added an optional parameter “model_organism” cosmetic
    • “experiment_plan_generate” added an optional parameter “time_months” cosmetic
    • “experiment_plan_generate” added an optional parameter “uses_animals” cosmetic
    • “experiment_plan_generate” added an optional parameter “uses_humans” cosmetic
    • “literature_digest_card” added an optional parameter “journal” cosmetic
    • “literature_digest_card” added an optional parameter “year” cosmetic
    • “results_paragraph_writer” added an optional parameter “params” cosmetic
    • “results_paragraph_writer” added an optional parameter “polish_level” cosmetic
    • “sample_size_calculator” added an optional parameter “dropout_rate” cosmetic
    • “sample_size_calculator” added an optional parameter “n_groups” cosmetic
    • “sample_size_calculator” added an optional parameter “outcome_type” cosmetic
    • “systematic_review_assist” added an optional parameter “comparison” cosmetic
    • “systematic_review_assist” added an optional parameter “exclusion” cosmetic
    • “systematic_review_assist” added an optional parameter “inclusion” cosmetic
    • “systematic_review_assist” added an optional parameter “intervention” cosmetic
    • “systematic_review_assist” added an optional parameter “outcome” cosmetic
    • “systematic_review_assist” added an optional parameter “population” cosmetic
    • “systematic_review_assist” added an optional parameter “query” cosmetic
    • “academic_polish” reworded the description of “lang” cosmetic
    • “academic_polish” reworded the description of “level” cosmetic
    • “acceptance_probability” reworded the description of “journal_id” cosmetic
    • “acceptance_probability” reworded the description of “paper” cosmetic
    • “consort_flowchart” reworded the description of “randomized” cosmetic
    • “consort_flowchart” reworded the description of “screened” cosmetic
    • “differential_expression” reworded the description of “gene_names” cosmetic
    • “differential_expression” reworded the description of “group_a” cosmetic
    • “differential_expression” reworded the description of “group_b” cosmetic
    • “differential_expression” reworded the description of “log2fc_threshold” cosmetic
    • “fibrosis_staging” reworded the description of “method” cosmetic
    • “fibrosis_staging” reworded the description of “stage” cosmetic
    • “literature_digest_card” reworded the description of “abstract” cosmetic
    • “literature_digest_card” reworded the description of “external_id” cosmetic
    • “literature_digest_card” reworded the description of “source” cosmetic
    • “literature_digest_card” reworded the description of “title” cosmetic
    • “mif_phenotype” reworded the description of “cd3_pos” cosmetic
    • “nuclei_count” reworded the description of “cell_density” cosmetic
    • “nuclei_count” reworded the description of “positive_rate” cosmetic
    • “nuclei_count” reworded the description of “stain_type” cosmetic
    • “ppi_network” reworded the description of “species” cosmetic
    • “prisma_flowchart” reworded the description of “records_identified” cosmetic
    • “results_paragraph_writer” reworded the description of “design_type” cosmetic
    • “results_paragraph_writer” reworded the description of “lang” cosmetic
    • “results_paragraph_writer” reworded the description of “model_type” cosmetic
    • “stats_toolbox” reworded the description of “payload” cosmetic
    • “toxicology_assess” reworded the description of “hERG_IC50_nM” cosmetic
    • “crf_sdtm_validate” dropped the optional parameter “form_id” cosmetic
    • “design_protocol_generate” dropped the optional parameter “title” cosmetic
    • “design_protocol_generate” dropped the optional parameter “type” cosmetic
    • “differential_expression” dropped the optional parameter “pval_threshold” cosmetic
    • “experiment_plan_generate” dropped the optional parameter “experiment_type” cosmetic
    • “sample_size_calculator” dropped the optional parameter “dropout” cosmetic
    • “sample_size_calculator” dropped the optional parameter “effect” cosmetic
    • “sample_size_calculator” dropped the optional parameter “sample_type” cosmetic
    • “sample_size_calculator” dropped the optional parameter “sd” cosmetic
    • “results_paragraph_writer” made “design_type” optional cosmetic
    • Tool “design_protocol_generate” changed its title: Full research protocol generation / 生成研究方案 → Full research protocol generation / 完整研究方案 / 方案设计工具 cosmetic
  • 10 Nov 26 0

    We did not load change detail this far back for this component, so this day may have recorded more than is shown.

    • Tool “academic_polish” was removed ▼ security
    • Schema quality: 19676 → 15452 ▲ functional
    • Server version: 1.2.2 → 1.3.0 functional
    • Server version: 1.1.0 → 1.2.2 functional
    • New tool “academic_polish” functional
    • New tool “acceptance_probability” functional
    • New tool “cover_letter” functional
    • New tool “decision_arbitration” functional
    • New tool “deep_peer_review” functional
    • New tool “design_next_step” functional
    • New tool “design_protocol_generate” functional
    • New tool “design_type_decision” functional
    • New tool “experiment_plan_generate” functional
    • New tool “idea_ignite” functional
    • New tool “literature_compare” functional
    • New tool “literature_digest_card” functional
    • New tool “literature_review_outline” functional
    • New tool “local_literature_compare” functional
    • New tool “mermaid_diagram” functional
    • New tool “nsfc_grant_analysis” functional
    • New tool “paper_draft_one_click” functional
    • New tool “paper_outline” functional
    • New tool “paper_six_agent_review” functional
    • New tool “pdf_text_pico” functional
    • New tool “pico_structure” functional
    • New tool “pre_submission_review” functional
    • New tool “proposal_review” functional
    • New tool “protocol_export” functional
    • New tool “protocol_export_check” functional
    • New tool “results_paragraph_writer” functional
    • New tool “revision_response” functional
    • New tool “section_writer” functional
    • New tool “systematic_review_assist” functional
    • New tool “technical_roadmap” functional
    • New tool “top_journal_mining” functional
    • New tool “topic_feasibility” functional
    • New tool “topic_gaps” functional
    • New tool “topic_generate” functional
    • New tool “topic_lit_review” functional
    • New tool “topic_novelty” functional
    • New tool “topic_ppt” functional
    • New tool “topic_prominence” functional
    • New tool “topic_research_plan” functional
  • 7 Nov 26 +2

    We did not load change detail this far back for this component, so this day may have recorded more than is shown.

  • 6 Nov 26 69

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://sanyu.wentangkeji.com/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=sanyu.wentangkeji.com CN=YE1,O=Let's Encrypt,C=US 14 Oct 2026 12 Jan 2027 ECDSA 256 ECDSA-SHA384 65db438cd0e71915afa22908968cf764a43
SANs: sanyu.wentangkeji.com
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of sanyu.wentangkeji.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
wentangkeji.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains
content-security-policy default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval' https://cdn.jsdelivr.net; style-src 'self' 'unsafe-inline' https://fonts.googleapis.com; font-src 'self' data: https://fonts.gstatic.com; img-src 'self' data: blob: https:; connect-src 'self' wss://sanyu.wentangkeji.com https://api.openalex.org; worker-src 'self' blob:; frame-src 'self' blob: about:; object-src 'self' blob:; base-uri 'self'; form-action 'self'; frame-ancestors 'self'; upgrade-insecure-requests
x-content-type-options nosniff
x-frame-options SAMEORIGIN
referrer-policy strict-origin-when-cross-origin
permissions-policy geolocation=(), microphone=(), camera=(), usb=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://sanyu.wentangkeji.com/api/mcp Verified 200
http (plaintext) http://sanyu.wentangkeji.com/api/mcp HTTPS enforced 301 https://sanyu.wentangkeji.com/api/mcp
MCP tools · 150 exposed · ~20,964 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
gleason_grade_group ~112

Gleason grade group / Gleason 分级分组 | USE WHEN: Gleason score → Grade Group and risk stratum (prostate cancer) | ALIASES: Gleason, 前列腺癌分级, Grade Group, 格里森评分, 前列腺病理 | RETURNS: Grade Group 与风险分层

NameTypeReqDescription
primary_gradeintegeryes主要分级 1-5
secondary_gradeintegeryes次要分级 1-5

No output schema declared.

No examples provided.

go_kegg_enrichment ~130

GO / KEGG enrichment / 通路富集(GO/KEGG) | USE WHEN: pathway enrichment for a gene list (GO biological process, KEGG) | ALIASES: 富集分析, GO, KEGG, 通路富集, enrichment, 通路, 功能注释 | RETURNS: 富集通路与 P 值

NameTypeReqDescription
db_filterstring–数据库:GO_BP/GO_CC/GO_MF/KEGG
gene_listarrayyes基因列表
project_idinteger–项目 id

No output schema declared.

{"db_filter":"KEGG","gene_list":["TP53","EGFR","MYC","KRAS","BRCA1"]}
ic50_fit ~141

IC50 curve fitting / IC50 曲线拟合 | USE WHEN: fit a dose-response curve and report IC50 with 95% CI | ALIASES: IC50, 半数抑制浓度, 剂量效应曲线, dose response, 抑制率拟合, GI50 | RETURNS: IC50 值与 95%CI

NameTypeReqDescription
concentrationsarrayyes浓度序列
directionstring–inhibition 或 activation
modelstring–拟合模型:4PL/3PL
responsesarrayyes响应/抑制率

No output schema declared.

{"concentrations":[0.01,0.1,1,10,100],"direction":"inhibition","model":"4PL","responses":[5,12,38,72,91]}
idea_ignite ~154

Idea ignition / 想法点燃 | USE WHEN: the user gives one vague word or a hunch and wants it expanded into researchable directions | ALIASES: 想法, 一个词, 不知道研究啥, 灵感, 发散一下, idea, hunch, expand this idea | RETURNS: 扩展研究方向

NameTypeReqDescription
include_sectionsboolean–是否返回文献正文节段(introduction/methods/results/discussion;默认 false,每段上限 800 字符)
max_papersinteger–返回文献条数上限(默认 5,硬上限 25)
topicstringyes初始想法或关键词

No output schema declared.

No examples provided.

ihc_hscore ~179

IHC scoring (H-score / Allred) / IHC 免疫组化评分 | USE WHEN: immunohistochemistry scoring from staining intensity percentages (H-score, Allred, positive rate) | ALIASES: 免疫组化评分, H-score, Allred, IHC, 阳性率, 染色评分, ER PR HER2 | RETURNS: H-score / Allred / 阳性率

NameTypeReqDescription
intensity_0_pctnumber–0 级占比(%)
intensity_1_pctnumber–1+ 占比(%)
intensity_2_pctnumber–2+ 占比(%)
intensity_3_pctnumber–3+ 占比(%)
stain_typestringyes染色类型

No output schema declared.

No examples provided.

iptw_weighting ~109

IPTW inverse probability weighting / IPTW 逆概率加权 | USE WHEN: propensity-score weighting (ATE/ATT) for observational comparisons | ALIASES: IPTW, 逆概率加权, 倾向评分加权, propensity weighting, 加权后效应, ATE | RETURNS: 权重与加权后效应

NameTypeReqDescription
propensity_scoresarrayyes倾向评分
treatmentarrayyes处理分组 0/1

No output schema declared.

No examples provided.

journal_recommend ~146

Journal recommendation / 智能选刊 V3 | USE WHEN: recommend target journals from title/abstract, in reach / match / safe tiers | ALIASES: 选刊, 投哪个期刊, 期刊推荐, journal, submission target, 冲稳保, 投稿建议 | RETURNS: 候选期刊与三档策略

NameTypeReqDescription
abstractstring–摘要
designstring–研究设计
keywordsarray–关键词
sample_sizeinteger–样本量
target_tierstring–目标档次
titlestringyes论文标题

No output schema declared.

No examples provided.

kaplan_meier ~112

Kaplan-Meier curve / Kaplan-Meier 曲线 | USE WHEN: KM curve and median survival only (no multivariable model) | ALIASES: KM曲线, Kaplan-Meier, 中位生存, 生存曲线, 生存率, log-rank | RETURNS: KM 曲线与中位生存

NameTypeReqDescription
eventsarrayyes事件 0/1
groupsarray–分组
timesarrayyes随访时间

No output schema declared.

{"events":[1,1,0,1,1,0],"times":[5,12,18,24,30,42]}
linear_mixed_model ~495

Linear mixed model (repeated measures) / 线性混合模型(纵向/重复测量,公式模式) | USE WHEN: same subject measured repeatedly (pre/post, multiple follow-ups): compare trajectories over time, group×time interaction; modern replacement for repeated-measures ANOVA (handles missing, no sphericity assumption) | ALIASES: 混合模型, 重复测量, 纵向数据, LMM, mixed model, 交互作用, 多次随访, 每人测多次, repeated measures | RETURNS: 固定效应系数/SE/Wald z/P/95%CI(按真实变量名,不是 X1/X2)、各项整体检验 omnibus、交互项检验、primary_test、ICC、方差成分、n_subjects/n_obs、组间例数、缺失与收敛告警

NameTypeReqDescription
categoricalarray–显式声明哪些列按分类处理(如 ["分组"]);数值编码的 0/1 分组必须声明,否则会被当连续变量
dataarrayyes长格式数据:每行一次观测 [{受试者ID, 分组, 时点, 结局}, ...];也接受列式 {列名: [值, ...]}。注意必须是**长表**(每行一次测量),不是每人一行多列
formulastringyesR 风格公式,如 '收缩压 ~ 分组 * 时点'(组×时间交互);左端=结局
re_formulastring–随机效应,默认 '1'(随机截距);随机斜率用 '1 + 时点'
referenceobject–参照水平,如 {"分组": "对照组"} —— 报告表里「与对照组相比」必须是它
remlboolean–默认 true(REML)
subjectstringyes受试者/病案号列名(随机截距的分组依据)
time_valuesobject–把字符串时点映射成数值以估线性趋势,如 {"时点": {"基线":0,"4周":1,"12周":2}}

No output schema declared.

No examples provided.

list_my_data_files ~97

List the caller's uploaded data files / 列出我的数据文件 | USE WHEN: the user asks what data files they have uploaded / available in the workspace | ALIASES: 我的数据, 已上传文件, 数据文件列表, my data, list files | RETURNS: 数据文件列表(含 file_id/文件名/行数)

NameTypeReqDescription
project_idinteger–限定项目 id(可不填)

No output schema declared.

No examples provided.

literature_compare ~91

Compare with published literature / 与已有文献对比 | USE WHEN: the user wants to know how their findings differ from what is already published | ALIASES: 和文献比, 新在哪, 对比已有研究, literature compare, how is this different | RETURNS: 对比结论

NameTypeReqDescription
main_findingsstring–主要发现
titlestringyes标题

No output schema declared.

No examples provided.

literature_digest_card ~152

Literature digest card / 文献摘要卡生成 | USE WHEN: the user gives a paper and wants a structured digest card out of it | ALIASES: 摘要卡, 文献卡片, 精读卡, digest, literature card | RETURNS: 摘要卡

NameTypeReqDescription
abstractstring–论文摘要(没有则留空,导读质量会下降)
external_idstring–外部 id(PMID/PMCID/DOI 等)
journalstring–期刊名
sourcestring–来源,默认 pmc
titlestringyes论文标题
yearstring–发表年份

No output schema declared.

No examples provided.

literature_review_outline ~84

Review outline from reading list / 文献综述提纲 | USE WHEN: the user wants a review outline built from the papers already digested | ALIASES: 综述提纲, review outline, 按精读文献出提纲 | RETURNS: 综述提纲

NameTypeReqDescription
topicstringyes综述主题(必填)

No output schema declared.

No examples provided.

literature_search_pmc ~129

Literature search (1.53M PMC full texts) / 文献检索(站内 153 万篇 PMC) | USE WHEN: search the in-house PMC corpus for literature / evidence / state of the art | ALIASES: 找文献, 文献检索, 检索文献, literature search, PMC, 证据, 研究现状, PubMed替代 | RETURNS: 文献列表(含 PMCID)

NameTypeReqDescription
limitinteger–返回条数
qstringyes检索词(英文效果更好)

No output schema declared.

No examples provided.

local_literature_compare ~93

Local literature comparison / 本地文献对比 | USE WHEN: the user gives a topic and wants a cross-comparison table of the in-house literature | ALIASES: 本地文献对比, 横向对比, 文献对比表, local literature compare | RETURNS: 对比表

NameTypeReqDescription
keywordsarray–关键词
topicstringyes主题

No output schema declared.

No examples provided.

mermaid_diagram ~107

Mermaid diagram generation / 生成流程图(Mermaid) | USE WHEN: the user wants a flow chart, sequence diagram or mind map expressed as Mermaid code | ALIASES: 流程图, Mermaid, 时序图, 思维导图, 画流程, diagram, flowchart | RETURNS: Mermaid 代码

NameTypeReqDescription
diagram_typestring–图类型:flowchart/sequence/mindmap
promptstringyes图的内容描述

No output schema declared.

No examples provided.

metabolite_heatmap ~182

Metabolite heatmap / 代谢组热图 | USE WHEN: clustered heatmap of metabolites | ALIASES: 代谢热图, 聚类热图, heatmap, metabolite heatmap | RETURNS: 聚类热图

NameTypeReqDescription
data_jsonobjectyes必填。数据对象(不是字符串)。矩阵形式:{"matrix": [[行1各列数值...], [行2...]], "rows": ["基因/特征名"], "cols": ["样本名"]};组学结果另可带 {"groups": ["组A","组A","组B"...]}(与 cols 一一对应)、{"p_values": [...], "log2fc": [...]}(若已有差异结果)。实测缺此字段会被…

No output schema declared.

No examples provided.

metabolite_pathway ~103

Metabolite pathway enrichment / 代谢物通路富集 | USE WHEN: pathway enrichment for differential metabolites | ALIASES: 代谢物通路, 代谢富集, metabolite pathway, KEGG代谢, 差异代谢物 | RETURNS: 代谢通路富集

NameTypeReqDescription
fdr_thresholdnumber–FDR 阈值
metabolitesarrayyes代谢物列表

No output schema declared.

No examples provided.

metabolite_pca ~103

Metabolite PCA / 代谢组 PCA | USE WHEN: sample separation / outliers in metabolomics (unsupervised) | ALIASES: 代谢组PCA, PCA, 样本分组趋势, 离群, unsupervised, 得分图 | RETURNS: PCA 得分与解释度

NameTypeReqDescription
data_jsonobjectyes代谢物矩阵
groupsarray–分组标签

No output schema declared.

No examples provided.

metabolite_plsda ~101

Metabolite PLS-DA / 代谢组 PLS-DA | USE WHEN: supervised discrimination and VIP for differential metabolites | ALIASES: PLS-DA, 有监督判别, VIP, 代谢组判别, 判别分析 | RETURNS: PLS-DA 模型与 VIP

NameTypeReqDescription
data_jsonobjectyes代谢物矩阵
groupsarray–分组标签

No output schema declared.

No examples provided.

metabolite_volcano ~182

Metabolite volcano plot / 代谢组火山图 | USE WHEN: volcano plot of differential metabolites | ALIASES: 代谢火山图, volcano, 差异代谢物火山图 | RETURNS: 火山图

NameTypeReqDescription
data_jsonobjectyes必填。数据对象(不是字符串)。矩阵形式:{"matrix": [[行1各列数值...], [行2...]], "rows": ["基因/特征名"], "cols": ["样本名"]};组学结果另可带 {"groups": ["组A","组A","组B"...]}(与 cols 一一对应)、{"p_values": [...], "log2fc": [...]}(若已有差异结果)。实测缺此字段会被…

No output schema declared.

No examples provided.

mif_phenotype ~151

Multiplex IF phenotyping / 多重免疫荧光表型 | USE WHEN: assign cell phenotypes and proportions from multiplex immunofluorescence markers | ALIASES: 多重免疫荧光, mIF, 细胞表型, phenotype, marker组合, 亚群比例 | RETURNS: 细胞亚群表型与比例

NameTypeReqDescription
cd3_posnumberyesCD3+ 细胞数(核心输入,必填)
cd8_posnumber–CD8+ 数
foxp3_posnumber–FoxP3+ 数
pd_l1_posnumber–PD-L1+ 数

No output schema declared.

No examples provided.

multi_omics_integrate ~130

Multi-omics integration / 多组学整合 | USE WHEN: integrate mRNA / protein / metabolite layers and find cross-layer associations | ALIASES: 多组学, 整合分析, multi-omics, 转录组蛋白组代谢组, cross-omics | RETURNS: 多组学关联结果

NameTypeReqDescription
metabolitearray–代谢物列表
mrnaarray–mRNA 列表
pathway_mapstring–通路映射方式
proteinarray–蛋白列表

No output schema declared.

No examples provided.

nomogram ~79

Nomogram / 列线图 Nomogram | USE WHEN: turn a logistic or Cox model into a nomogram figure for clinical use | ALIASES: 列线图, Nomogram, 评分图, nomogram, 风险评分图 | RETURNS: 列线图 SVG

NameTypeReqDescription
csv_datastringyesCSV 文本

No output schema declared.

No examples provided.

nsfc_grant_analysis ~98

NSFC grant fit analysis / 国自然申报分析 | USE WHEN: the user asks whether a topic fits NSFC / provincial funding, which category, and the odds | ALIASES: 国自然, NSFC, 基金申报, 省自然, 命中率, 报什么口子, grant fit | RETURNS: 国自然分析

NameTypeReqDescription
diseasestringyes疾病/研究方向

No output schema declared.

No examples provided.

nuclei_count ~181

Nuclei segmentation & counting / 细胞核分割与计数 | USE WHEN: cell density / positive rate from a tissue section (nuclei segmentation) | ALIASES: 细胞核分割, 细胞计数, 密度, nuclei count, segmentation, 阳性细胞率 | RETURNS: 分割统计结果

NameTypeReqDescription
cell_densitystring–细胞密度:low/moderate/high/very_high,默认 moderate
image_base64stringyes病理图像 base64(必填;无图时端点走演示模式,属假结果,开放层不接受)
positive_ratenumber–预估阳性率,默认 0.3
stain_typestring–染色类型,默认 Ki67

No output schema declared.

No examples provided.

omics_methods_draft ~83

Multi-omics methods section draft / 多组学论文段落 | USE WHEN: the user wants a methods section for a multi-omics paper, assembled only from the analyses they actually ran | ALIASES: 多组学方法, 方法学段落, RNA-seq 方法, methods section, omics methods | RETURNS: 论文段落

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

orf_find ~78

ORF prediction / ORF 预测 | USE WHEN: find open reading frames in a nucleotide sequence | ALIASES: ORF, 开放阅读框, 找编码区, open reading frame, 翻译起始 | RETURNS: ORF 列表与位置

NameTypeReqDescription
sequencestringyes核酸序列

No output schema declared.

No examples provided.

organ_coefficient ~112

Organ coefficient / 脏器系数 | USE WHEN: organ weight / body weight ratio (脏器系数) | ALIASES: 脏器系数, 器官系数, organ coefficient, organ index, 脏器重量比 | RETURNS: 脏器系数

NameTypeReqDescription
body_weightsarrayyes体重
labelstring–脏器名
organ_weightsarrayyes脏器重

No output schema declared.

No examples provided.

paper_outline ~101

Manuscript outline / 生成论文提纲 | USE WHEN: the user wants the outline / chapter structure before the full text is written | ALIASES: 提纲, 目录, 章节结构, 论文框架, outline, chapter structure | RETURNS: 章节提纲

NameTypeReqDescription
design_typestring–研究设计类型
project_idinteger–项目 id
titlestringyes论文题目

No output schema declared.

No examples provided.

paper_six_agent_review ~120

Six-agent manuscript review / 论文预审(六智能体) | USE WHEN: the user wants a pre-submission review to find the reasons a paper would be rejected | ALIASES: 预审, 六智能体, 审稿意见, 投稿前审, manuscript review, six agent review | RETURNS: 审稿意见与评分

NameTypeReqDescription
abstractstring–摘要
methodsstring–方法
resultsstring–结果
titlestringyes标题

No output schema declared.

No examples provided.

pcr_primer_design ~113

PCR primer design / PCR 引物设计 | USE WHEN: design PCR primer pairs from a DNA sequence or gene (Tm, GC, product size) | ALIASES: 引物设计, PCR引物, primer, 设计引物, 扩增引物, primer pair | RETURNS: 候选引物对与 Tm/GC

NameTypeReqDescription
genestring–基因名(无序列时用)
sequencestringyes模板 DNA 序列

No output schema declared.

No examples provided.

pdf_text_pico ~86

PICO from pasted text / 从文本抽取 PICO | USE WHEN: the user pastes an abstract or paragraph and wants PICO extracted from it | ALIASES: 抽取PICO, 从摘要提PICO, 文献PICO, extract pico from text | RETURNS: 结构化 PICO

NameTypeReqDescription
textstringyes文献文本

No output schema declared.

No examples provided.

permutation_test ~118

Permutation test / 置换检验 | USE WHEN: exact/permutation test when t-test assumptions fail or n is tiny | ALIASES: 置换检验, 随机化检验, permutation, 精确检验, 小样本非参数, resampling | RETURNS: 置换 P 值

NameTypeReqDescription
group1arrayyes第一组数值
group2arrayyes第二组数值
n_perminteger–置换次数,默认 10000

No output schema declared.

{"group1":[12.1,13.4,11.8,12.9],"group2":[15.2,14.8,16.1,15.5]}
pico_refine ~126

PICO refinement / PICO 精炼 | USE WHEN: turn a vague clinical question into a structured PICO (Population / Intervention / Comparator / Outcome) | ALIASES: PICO, 把问题拆开, 研究问题怎么提, refine question, 结构化问题, PICO拆解 | RETURNS: 结构化 PICO

NameTypeReqDescription
picoobjectyes结构化 PICO,如 {"P":"ICU 脓毒症患者","I":"乳酸清除率","C":"常规","O":"28天病死率"}

No output schema declared.

No examples provided.

pico_structure ~137

PICO structuring (design flow) / PICO 结构化精炼 | USE WHEN: the user says refine my PICO / turn this sentence into PICO / how to split PICO; only structures what the user said and reports missing elements instead of inventing them | ALIASES: 精修PICO, PICO拆解, 做成PICO, 结构化PICO, pico refine, structure pico | RETURNS: PICO 四要素结构化结果 + 提示缺哪些要素

NameTypeReqDescription
picoobjectyesPICO 四要素:{population, intervention, comparison, outcome, topic}

No output schema declared.

No examples provided.

pk_nca ~157

Non-compartmental PK (NCA) / NCA 非房室药代分析 | USE WHEN: non-compartmental analysis of concentration-time data: AUC, Cmax, Tmax, t1/2, CL, Vd | ALIASES: NCA, 非房室分析, 药代参数, AUC Cmax T1/2, PK parameters, 血药浓度 | RETURNS: AUC/Cmax/Tmax/T1/2/CL/Vd

NameTypeReqDescription
concentrationsarrayyes浓度
dosenumber–给药剂量
dose_unitstring–剂量单位,如 mg/kg
time_pointsarrayyes时间点

No output schema declared.

No examples provided.

pk_pd_assess ~101

PK/PD assessment / PK/PD 评估 | USE WHEN: pharmacokinetic/pharmacodynamic assessment and dose projection | ALIASES: PK/PD评估, 药代药效, 剂量推算, pkpd assess, 暴露量 | RETURNS: PK/PD 评估结果

NameTypeReqDescription
drug_namestringyes药物名称
pk_paramsobject–药代参数

No output schema declared.

No examples provided.

pkpd_simulate ~107

PK/PD simulation / PK/PD 模拟 | USE WHEN: simulate concentration-effect time course for a dosing regimen | ALIASES: PK/PD模拟, 给药方案模拟, 浓度时间曲线, simulation, 剂量方案 | RETURNS: 模拟曲线与参数

NameTypeReqDescription
drug_namestringyes药物名
pd_paramsobject–药效参数
pk_paramsobject–药代参数

No output schema declared.

No examples provided.

plasmid_map ~87

Plasmid map / 质粒图谱 | USE WHEN: draw/describe a plasmid map from a sequence (features, orientation) | ALIASES: 质粒图谱, 载体结构, plasmid map, vector, 质粒构建图 | RETURNS: 质粒图谱

NameTypeReqDescription
sequencestringyes质粒序列

No output schema declared.

No examples provided.

ppi_network ~142

Protein-protein interaction network / 蛋白互作网络 | USE WHEN: PPI network from a protein list, hub identification (STRING) | ALIASES: 蛋白互作, PPI, STRING, hub基因, 互作网络, network | RETURNS: 互作网络与 hub 蛋白

NameTypeReqDescription
confidence_thresholdnumber–置信度阈值
protein_listarrayyes蛋白/基因列表
speciesinteger–物种 NCBI taxonomy id:9606=人,10090=小鼠(默认 9606)

No output schema declared.

No examples provided.

pre_submission_review ~108

Pre-submission review / 投稿前预审 | USE WHEN: the user wants a pre-submission check to find likely rejection points | ALIASES: 投稿前预审, 会被拒吗, 投稿检查, pre review, desk reject risk | RETURNS: 预审意见

NameTypeReqDescription
abstractstring–摘要
designstring–研究设计
sample_sizeinteger–样本量
titlestringyes标题

No output schema declared.

No examples provided.

primer_tm ~96

Primer Tm & dimers / 引物 Tm 计算 | USE WHEN: Tm, GC% and self/cross dimer check for given primer sequences | ALIASES: Tm, 引物Tm, 退火温度, GC含量, 二聚体, primer dimer, melting temperature | RETURNS: Tm、GC、二聚体

NameTypeReqDescription
sequencestringyes引物序列

No output schema declared.

{"sequence":"ATGGCCATTGTAATGGGCCGC"}
prisma_flowchart ~147

PRISMA flow diagram / PRISMA 流程图 | USE WHEN: PRISMA literature screening flow for systematic reviews / meta-analyses | ALIASES: PRISMA, 文献筛选流程, 系统评价流程图, flow diagram, 检索流程图 | RETURNS: PRISMA 流程图

NameTypeReqDescription
records_identifiedintegeryes检索记录数(PRISMA 流程图起点,必填)
records_screenedinteger–筛读记录数
studies_includedinteger–最终纳入研究数
titlestring–研究题目

No output schema declared.

No examples provided.

propensity_score_matching ~259

Propensity score matching (PSM) / 倾向性评分匹配 PSM | USE WHEN: match treated and control subjects on baseline covariates (1:1 nearest neighbour within caliper), then report SMD balance | ALIASES: PSM, 倾向性评分, 倾向评分匹配, propensity score, 1:1匹配, 基线可比, 混杂控制, 匹配后均衡 | RETURNS: 匹配后样本与均衡性

NameTypeReqDescription
covariatesarrayyes协变量列名数组,如 ["age","sex"](传 data 时)或二维数值矩阵
dataarray–样本表:每行一个受试者的字典,如 [{"treat":1,"age":62,"sex":0}, …](也可改用 treatment/covariates 直接传数组)
rationumber–匹配比例,默认 1
treatmentstringyes处理变量(1=处理组,0=对照组)。传 data 时填列名 "treat";也可直接传 0/1 数组

No output schema declared.

{"caliper":0.2,"covariates":["age","sex"],"data":[{"age":62,"sex":0,"treat":1},{"age":58,"sex":1,"treat":0},{"age":65,"sex":0,"treat":1},{"age":61,"sex":1,"treat":0},{"age":70,"sex":0,"treat":1},{"age":55,"sex":0,"treat":0}],"treatment":"treat"}
proposal_review ~100

Proposal / grant review / 标书评审 | USE WHEN: the user pastes a proposal or protocol and wants scoring, weaknesses and revision advice | ALIASES: 标书评审, 方案打分, 本子, 评审意见, proposal review, grant review, 专家怎么挑毛病 | RETURNS: 五维评分与修改建议

NameTypeReqDescription
proposal_textstringyes标书正文全文(平台要求 ≥100 字)

No output schema declared.

No examples provided.

protein_digest ~113

In-silico protein digestion / 蛋白酶解模拟 | USE WHEN: choose protease and list peptides for mass-spec sample prep | ALIASES: 蛋白酶解, 质谱前处理, 酶解肽段, digest, trypsin, 肽段清单 | RETURNS: 肽段清单

NameTypeReqDescription
enzymesarray–酶:Trypsin/Lys-C
sequencestringyes蛋白序列

No output schema declared.

No examples provided.

protein_enrichment ~105

Protein enrichment / 蛋白富集分析 | USE WHEN: GO/KEGG enrichment for a protein list | ALIASES: 蛋白富集, protein enrichment, 蛋白GO, 蛋白通路 | RETURNS: 富集通路

NameTypeReqDescription
enrichment_typestring–GO/KEGG/Reactome
protein_listarrayyes蛋白列表
speciesstring–物种

No output schema declared.

No examples provided.

protein_physchem ~118

Protein physicochemical properties / 蛋白理化性质 | USE WHEN: molecular weight, pI, GRAVY, instability index etc. from a protein sequence | ALIASES: 蛋白理化性质, 分子量, 等电点, pI, GRAVY, 疏水性, MW, protein properties | RETURNS: MW/pI/GRAVY 等

NameTypeReqDescription
protein_namestring–蛋白名
sequencestringyes蛋白序列

No output schema declared.

No examples provided.

protein_ptm ~113

Post-translational modification prediction / 翻译后修饰分析 | USE WHEN: predict phosphorylation / glycosylation and other PTM sites | ALIASES: 翻译后修饰, 磷酸化位点, 糖基化, PTM, phosphorylation, modification sites | RETURNS: 修饰位点预测

NameTypeReqDescription
modificationsarray–修饰类型:phosphorylation/glycosylation
sequencestringyes蛋白序列

No output schema declared.

No examples provided.

Install

How do I install the 三域医研 · 科研算法引擎 (SanYu Research Engine) MCP server?

三域医研 · 科研算法引擎 (SanYu Research Engine) is a hosted endpoint at https://sanyu.wentangkeji.com/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · sanyu.wentangkeji.com

# add to Claude Code
claude mcp add --transport http kfx2026-sanyu-research 'https://sanyu.wentangkeji.com/api/mcp'
Common questions

What is the 三域医研 · 科研算法引擎 (SanYu Research Engine) MCP server?

三域医研 · 科研算法引擎 (SanYu Research Engine) is an MCP server listed in the public MCP registry as io.github.kfx2026/sanyu-research. 147 tools: deterministic compute + 39 AI writers; each response self-labels data_source + verified. This page covers its hosted endpoint (https://sanyu.wentangkeji.com/api/mcp).

Is the 三域医研 · 科研算法引擎 (SanYu Research Engine) MCP server safe to use?

三域医研 · 科研算法引擎 (SanYu Research Engine) scores 71 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the 三域医研 · 科研算法引擎 (SanYu Research Engine) MCP server expose?

三域医研 · 科研算法引擎 (SanYu Research Engine) exposes 150 tools: academic_polish, acceptance_probability, act_crf_suggest_coding, animal_dose_volume, animal_randomization, and 145 more. Their descriptions and schemas cost roughly 20,964 tokens of context every time the server is loaded.

Does the 三域医研 · 科研算法引擎 (SanYu Research Engine) MCP server require authentication?

No. We connected to 三域医研 · 科研算法引擎 (SanYu Research Engine) without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the 三域医研 · 科研算法引擎 (SanYu Research Engine) MCP server still maintained?

三域医研 · 科研算法引擎 (SanYu Research Engine) is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the 三域医研 · 科研算法引擎 (SanYu Research Engine) MCP server?

VerifyMCP ran 13 checks on 三域医研 · 科研算法引擎 (SanYu Research Engine), covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.