search_inactive_compounds
Search inactive compounds
Inactive small-molecule compound-target pairs.
輸入參數
tierlimitoffsettargetoutcomecompound
Nullary
ai.nullary由 nullary.ai 發布官方發布者v1.0.1更新於 Oct 27, 2026
Negative results intelligence for drug discovery — query measured failures via MCP.
概覽
AI 產生的概覽
針對藥物研發陰性結果的遠端 MCP 伺服器，可查詢化合物、生物藥、標的與適應症的實測失敗資料。
- 可以做什麼
- 依模態搜尋陰性結果：小分子、抗體、胜肽、PROTAC、寡核苷酸、疫苗、ADC 與雙特異性抗體
- 查詢某個標的、適應症或病原體橫跨所有模態的失敗歷史
- 檢視化合物的結構、名稱、最高臨床階段與完整陰性檔案
- 依 id 取得單一發現的完整來源與細節
- 依基因符號或 UniProt 編號瀏覽標的「墓地」排名與標的消耗指數
- 檢視失活評分模型卡、模型登錄概況與各模態覆蓋統計
- 適用情境
- 適合在評估藥物研發風險時使用：確認某標的、機制或模態是否已經失敗，在立項前回顧既有陰性結果，或查證某化合物或類別為何被中止。
- 執行需求
- 遠端 streamable HTTP 端點 mcp.nullary.ai；未宣告任何套件、環境變數或標頭，也未宣告身分驗證。
安裝前請注意
服務本身為唯讀查詢，但查詢內容會向第三方伺服器揭露你正在研究的標的、化合物或適應症。覆蓋範圍自稱僅為第一階段資料，可能不完整；依賴結論前應透過來源查詢工具核實。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Nullary，將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
交給代理程式安裝
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/ai.nullary%2Fnullary/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。其他 MCP 客戶端
把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"nullary": {
"type": "http",
"url": "https://mcp.nullary.ai/mcp"
}
}
}README
該儲存庫沒有 README。
工具
35search_failed_selectivity
Search failed selectivity
Small molecules that failed selectivity.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_admet_failures
Search admet failures
Small-molecule ADMET failures.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_failed_guides
Search failed guides
Failed/ineffective CRISPR guides.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_failed_essentiality_screens
Search failed essentiality screens
Non-dependency / failed essentiality screens.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_ancestry_specific_failures
Search ancestry specific failures
Ancestry-specific CRISPR failures.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_developability_failures
Search developability failures
Antibody developability failures.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_failed_clinical_antibodies
Search failed clinical antibodies
Discontinued/terminated clinical antibodies.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_failed_peptide_therapeutics
Search failed peptide therapeutics
Failed peptide therapeutics.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_peptide_stability_issues
Search peptide stability issues
Peptide stability/half-life failures.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_failed_protacs
Search failed protacs
PROTACs that failed degradation/ternary/permeability.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_protac_e3_issues
Search protac e3 issues
PROTAC E3-ligase recruitment / ternary failures.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_failed_oligonucleotides
Search failed oligonucleotides
ASOs/siRNAs that failed engagement/developability.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_oligo_delivery_failures
Search oligo delivery failures
Oligonucleotide delivery failures.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_failed_vaccines
Search failed vaccines
Failed/terminated vaccines (by pathogen/indication).
輸入參數
tierlimitoffsettargetoutcomeindicationsearch_vaccine_immunogenicity_failures
Search vaccine immunogenicity failures
Failed vaccine immunogen designs.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_failed_adcs
Search failed adcs
ADCs that failed at any stage.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_adc_linker_failures
Search adc linker failures
ADC failures attributed to linker chemistry.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_failed_bispecifics
Search failed bispecifics
Bispecifics that failed at any stage.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_bispecific_format_failures
Search bispecific format failures
Bispecific format/engineering failures.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_admet_failures_all_modalities
Search admet failures all modalities
ADMET failures across ALL modalities.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_drug_drug_interaction_failures
Search drug drug interaction failures
Drug-drug interaction failures.
輸入參數
tierlimitoffsetoutcomecompoundsearch_mechanism_failures
Search mechanism failures
Approaches that failed for a mechanism (by target).
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_failed_replications
Search failed replications
Findings that failed to replicate.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_safety_failures
Search safety failures
Clinical/preclinical safety failures across modalities.
輸入參數
tierlimitoffsettargetoutcomecompoundsearch_target_history
Search target history
ALL failed approaches against a target across every modality.
輸入參數
tierlimitoffsettarget必填search_indication_history
Search indication history
ALL failed approaches for an indication across every modality.
輸入參數
tierlimitoffsetindication必填search_pathogen_history
Search pathogen history
Vaccine + antimicrobial + antibody failures for a pathogen.
輸入參數
tierlimitoffsetpathogen必填get_compound
Get compound
A compound (structure, name, max clinical phase) + its full negative profile across modalities/sources.
輸入參數
tierlimitoffsetchembl_idinchi_keypubchem_cidget_finding_provenance
Get finding provenance
Full provenance + detail for a single finding by id.
輸入參數
id必填get_target_landscape
Get target landscape
Target 'graveyard' / exhaustion index: how many distinct compounds/agents have been tried against a target and failed, broken down by modality and outcome. Answers 'how picked-over is this target?'. Accepts a gene symbol (e.g. EGFR) or a UniProt accession (e.g. P00533).
輸入參數
target必填list_top_targets
List top targets
Coverage browse: the most heavily-pursued ('graveyard') targets, ranked by recorded negative findings. Optional family filter (kinase, gpcr, protease, nuclear_receptor, ion_channel, transporter, phosphatase, other).
輸入參數
limitfamilylist_models
List models
Summary of the Layer-1 inactivity-scoring model registry: how many per-target models, split by family, and median scaffold-split ROC-AUC.
無需輸入參數。
get_model_card
Get model card
Per-target Layer-1 model card: training counts and held-out scaffold-split metrics (ROC-AUC, PR-AUC, Brier, calibration). Accepts a gene symbol (e.g. EGFR) or UniProt accession (e.g. P00533).
輸入參數
target必填get_coverage
Get coverage
Per-modality and per-source coverage stats (honest Phase-1 numbers).
無需輸入參數。
版本歷史
1- v1.0.1最新Sep 16, 2026
評分
已滿足適用檢查項的 75%
該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。
- 近 30 天內可連通必需25 分
- 已宣告認證方式必需10 分
- 已列出工具必需15 分
- 描述必需15 分
- 圖示10 分
- 文件15 分
請宣告包含 README 的 GitHub 儲存庫，或在 OAuth 受保護資源後設資料中提供 resource_documentation。
- 授權條款10 分
請在儲存庫或註冊中心條目中宣告授權條款。