autosearch
PRISMA 2020 systematic reviews as MCP tools - verified citations, IMRAD papers
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"autosearch": {
"url": "https://exatoshi.uk/mcp"
}
}
}遠端端點
https://exatoshi.uk/mcpstreamable-http它能做什麼
工具清單
工具（6）
🟢autosearch_run_research(prompt, depth)
Launch an AI scientific research run. Returns run_id immediately. Use get_run_status to poll.
輸入結構描述
{
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "Research question or topic"
},
"depth": {
"type": "string",
"enum": [
"quick-scan",
"standard-review",
"deep-review"
],
"default": "standard-review"
}
},
"required": [
"prompt"
]
}🟢autosearch_get_run_status(run_id)
Get the current status of a research run. Returns status, frontier_score, n_experiments, summary.
輸入結構描述
{
"type": "object",
"properties": {
"run_id": {
"type": "string"
}
},
"required": [
"run_id"
]
}🟢autosearch_get_run_paper(run_id, format)
Get the generated paper for a completed run. Returns markdown, JSON metadata, or PDF download URL.
輸入結構描述
{
"type": "object",
"properties": {
"run_id": {
"type": "string"
},
"format": {
"type": "string",
"enum": [
"markdown",
"json",
"pdf_url"
],
"default": "markdown"
}
},
"required": [
"run_id"
]
}⚪autosearch_verify_doi(doi)
Verify a DOI via Crossref. Returns validity, title, authors, year, journal.
輸入結構描述
{
"type": "object",
"properties": {
"doi": {
"type": "string",
"description": "DOI string with or without https://doi.org/ prefix"
}
},
"required": [
"doi"
]
}🟢autosearch_search_evidence(query, sources, limit)
Search peer-reviewed evidence across academic sources without launching a full research run. Returns top N papers with metadata.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"sources": {
"type": "array",
"items": {
"type": "string",
"enum": [
"arxiv",
"clinicaltrials",
"crossref",
"dblp",
"doaj",
"openalex",
"pubmed",
"semantic-scholar"
]
},
"default": [
"openalex",
"crossref",
"pubmed",
"semantic-scholar"
]
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 50
}
},
"required": [
"query"
]
}🟢autosearch_list_my_runs(limit)
List the authenticated user latest research runs with status and frontier score.
輸入結構描述
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 20,
"maximum": 100
}
}
}建議的提示詞
autosearch_run_researchautosearch_run_researchautosearch_get_run_statusautosearch_get_run_statusautosearch_list_my_runs社群
證據