YaCy peer-to-peer search

io.github.pad01g由 GitHub 账号 pad01g 发布v1.0.0更新于 Oct 24, 2026

Web search, crawling and ranking evaluation on your own YaCy peer: no API key, no central service.

概览

AI 生成的概览

把助手连接到自建的 YaCy 节点,用于网页搜索、抓取、排序设置与搜索质量评估,无需搜索 API 密钥。

可以做什么
  • 在节点索引中搜索,可选同时查询点对点网络并等待各节点返回结果
  • 启动、暂停、恢复和停止站点抓取,并列出抓取任务及其句柄
  • 查看索引状态、已连接节点与信任委派信息
  • 读取并修改排序与过滤设置,再用精确率、召回率和 R 精确率评估排序质量
  • 从节点自有索引中删除单个页面
适用场景
适合自己运行 YaCy 节点、希望助手在其中搜索、把站点抓取进索引、调整排序设置并衡量搜索质量的场景,无需依赖商业搜索 API。
运行要求
需要一个可通过 HTTP 访问的运行中 YaCy 节点,由 YACY_URL 指定。服务器以本地 stdio 进程运行,通常是和节点同一网络的 Docker 容器,或从源码运行时使用 Node 24。管理操作需要 YACY_ADMIN_USER 和 YACY_ADMIN_PASSWORD;可选 YACY_CRAWL_ALLOW_PRIVATE、YACY_ALLOW_TRUST_SETTINGS 和 YACY_TIMEOUT_MS。
安装前请注意
YACY_ADMIN_PASSWORD 是通过环境变量传入的机密,拥有抓取、设置和删除权限。抓取、抓取控制、删除文档和修改排序被标记为破坏性操作,会改变节点索引或配置。YACY_CRAWL_ALLOW_PRIVATE=1 会让抓取访问回环和私有地址。标题和摘要来自网页作者和其他节点,应视为数据而非指令。

安装

在 SourceWeft 中

  1. 打开 控制台中的 YaCy peer-to-peer search,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

yacy-search MCP server

An MCP server for one YaCy peer: web search without a search API or API key, crawling, ranking settings and search quality evaluation. It runs next to the agent (stdio) and talks to the agent's own peer over HTTP. There is no central service: the peer is yours, and it searches the peer-to-peer network it belongs to. Registry name: io.github.pad01g/yacy-search.

It is written for the improved-search fork (results carry author signature verdicts and tags). Search, crawl, status and settings also work with upstream YaCy.

Run

Start a peer and the MCP server on one Docker network:

sh
docker network create yacy 2>/dev/null || truedocker run -d --name yacy --network yacy -p 127.0.0.1:8090:8090 \  -v yacy_data:/opt/yacy_search_server/DATA ghcr.io/pad01g/yacy-improved-search:latest
# Claude Codeclaude mcp add yacy -- docker run -i --rm --network yacy \  -e YACY_URL=http://yacy:8090 -e YACY_ADMIN_PASSWORD='<your password>' ghcr.io/pad01g/yacy-search-mcp:1.0.0

The fork's image starts with the administrator account admin / yacy: change the password at http://127.0.0.1:8090/ConfigAccounts_p.html before connecting the MCP server, and pass the new one.

Other clients (mcp.json style):

json
{  "mcpServers": {    "yacy": {      "command": "docker",      "args": ["run", "-i", "--rm", "--network", "yacy", "-e", "YACY_URL=http://yacy:8090", "-e", "YACY_ADMIN_PASSWORD=<your password>", "ghcr.io/pad01g/yacy-search-mcp:1.0.0"]    }  }}

For a peer outside Docker use -e YACY_URL=http://host.docker.internal:8090 (Linux: add --add-host=host.docker.internal:host-gateway). Without Docker: npm ci && node src/server.ts in this directory (Node 24).

VariableDefaultMeaning
YACY_URLhttp://localhost:8090base URL of the peer
YACY_ADMIN_USERadminadministrator account (crawl, status counts, settings)
YACY_ADMIN_PASSWORDunsetadministrator password; without it crawl_site, control_crawl, delete_document and set_ranking_setting are refused (even if the peer accepts local requests without a password), and the reading admin tools work only where the peer allows them without one
YACY_CRAWL_ALLOW_PRIVATEunset1: crawl_site may reach loopback and private addresses (an intranet). Otherwise only http(s) URLs of public hosts. This checks the start URL only; the links and redirects YaCy follows are limited by YaCy's own network.unit.domain (global on public peers refuses local addresses)
YACY_TIMEOUT_MS30000timeout of one request to the peer
YACY_ALLOW_TRUST_SETTINGSunset1: set_ranking_setting may also change trust.search.acceptUnverified and trust.policy.excludeTags

On the improved-search fork, the vector search (short questions find pages without the exact words) is used only for searches of the peer's administrator or from its host. When the MCP server runs in another container, set search.vector.public=true on the peer (it then embeds every new query of its search page).

Tools

ToolWhat it does
search_webfull-text search; resource: "global" also asks connected peers and waits waitMs before ranking all answers
crawl_sitestart a crawl (url, depth, range: domain / subpath / wide, maxPages per host, default 200)
get_index_statusindexed documents, crawl queues, peer type and connections; explains a paused crawler (load average) and a peer without a public address
list_peersconnected peers: signed seed, reach (direct / relay), tags
get_ranking_settingsthe ranking and filtering settings with their meaning
set_ranking_settingchange one of them (allow-list only: minimum match, coverage and thin page weights, title phrase boost, wait time; unverified results and excluded tags only with YACY_ALLOW_TRUST_SETTINGS=1)
evaluate_rankingqueries with known relevant URLs: precision@k, recall@k, R-precision, the rank of each relevant URL; finishes within about 50 s (queries that do not fit are reported as skipped)
get_trust_statusthe signed delegations and peer lists the peer holds
list_crawlsthe crawls started on the peer, with the handle control_crawl needs
control_crawlpause or resume the local crawler, or stop one crawl (indexed pages stay)
delete_documentremove one page from the peer's own index (stop a running crawl of that site first)

1.0.0 renamed the tools to a consistent verb_noun form (no aliases): search → search_web, crawl → crawl_site, crawls → list_crawls, crawl_control → control_crawl, index_status → get_index_status, peers → list_peers, trust_status → get_trust_status. Clients that call tools by name need the new names.

A typical loop for improving results: evaluate_ranking → set_ranking_setting → evaluate_ranking.

Titles and snippets come from page authors and other peers: the tool descriptions tell the model to treat them as data, not instructions. crawl_site, control_crawl, delete_document and set_ranking_setting are marked destructive so that clients ask before calling them. Values of settings are checked per key, and a value YaCy stores differently is rolled back.

Test

sh
npm ci && npm run typecheck && npm test                      # unit testsYACY_URL=http://localhost:8090 YACY_ADMIN_PASSWORD=yacy npm test   # also calls every tool on a live peer

License

This directory (the MCP server) is under the MIT license. It talks to YaCy only over HTTP and contains no YaCy code; the rest of this repository, YaCy itself, stays under the GPL.

来源:mcp/README.md,提交 2fa4cc2

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

5
  1. v1.0.0最新Oct 1, 2026
  2. v0.3.0Oct 1, 2026
  3. v0.2.1Sep 30, 2026
  4. v0.2.0Sep 29, 2026
  5. v0.1.0Sep 28, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分