Hashgrid DNA

ai.hashgrid由 hashgrid.ai 发布官方发布者v1.2.0更新于 Nov 7, 2026

A search engine that learns from your grades. Store text, records, images or embeddings.

已验证Streamable HTTP可网页运行数据库知识与记忆

概览

AI 生成的概览

一个远程存储文本、记录、图片和嵌入的检索服务,结果会随评分不断改进,并以网格、条目、查询和评分工具提供给助手。

可以做什么
  • 创建、查看和删除网格,即由密钥限定的存储空间
  • 按路径式键写入、读取、列出和删除条目,内容可为文本、JSON 记录、图片或嵌入
  • 创建、读取和删除已保存的查询
  • 获取查询的排序结果,可按键前缀限定范围
  • 记录、读取、列出和删除 -1 到 1 的评分,用于训练排序
适用场景
适合需要一个小型持久语料库、能进行语义检索并通过给结果打分逐步调优的场景,而不是固定索引。适用于原型以及重视反馈驱动排序的个人或团队知识库。
运行要求
远程 streamable HTTP 端点,无需本地安装。需要 API 密钥,通过 Authorization 头以 Bearer hg-… 形式发送,或作为各工具的 api_key 参数传入;可用 create_grid 创建密钥。需要能访问服务商端点。
安装前请注意
API 密钥属于机密,create_grid 只返回一次,须立即保存。工具会写入、替换和删除条目、查询与评分,delete_grid 会清空整个网格并使其密钥失效。通过工具创建的网格上限为 1024 个条目(含查询),每个地址只能创建少量网格。存储内容由第三方服务保管。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Hashgrid DNA,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。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/ai.hashgrid%2Fdna/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "hashgrid-dna": {
      "type": "http",
      "url": "https://dna.hashgrid.ai/mcp"
    }
  }
}

工具

15

create_grid

POST /: create a grid, your own store of items; no API key needed. Returns its `api_key`, shown only now: pass it as `api_key` to every other tool, or send it as the header `Authorization: Bearer hg-…`. It holds up to `max_items` items, queries included. Each address may create only a few grids a day.

输入参数name

get_grid

GET /: the grid the API key opens: its name and its limit on items, `max_items` (queries included; null: no limit).

输入参数api_key

delete_grid

DELETE /: delete the grid and everything in it, items, queries and grades; its key stops working.

输入参数api_key

put_item

PUT /items/key: write the item at `key` (e.g. "42", no leading /), creating it or replacing its content. Text is a string and a record a JSON object, each up to 8 KB; an image its bytes as base64, kept as a WebP of at most 512 px (its width and height come back); an emb a list of floats from the grid's model. DNA embeds the rest itself and keeps it only to embed it again; results and listings never return it. `type` is one of text/plain, application/json, image/png, image/jpeg, image/webp, image/gif, application/vnd.hashgrid.emb+json; leave it out for text, a record or an emb, which DNA tells apart, not for an image. Group items under a prefix (e.g. "tools/42") to search groups apart. Returns the item: its key, type, size, etag, ctime and mtime.

输入参数key必填typeapi_keycontent必填

get_item

GET /items/key: the item at `key`, with its `content` as put_item takes it.

输入参数key必填api_key

delete_item

DELETE /items/key: delete the item at `key`, and every grade of it.

输入参数key必填api_key

list_items

GET /items?prefix=: `items`, those whose keys start with `prefix` (e.g. "tools/"; all by default), in key order, without their content (get_item reads one), at most `limit` (1 to 100, 32 by default). `next`: for the next page, pass it as `after` (null: this was the last).

输入参数afterlimitprefixapi_key

create_query

POST /queries: store a question to ask of the items, its content as put_item takes it. Returns its `id`, which the other query tools take. Its results are ready at once; ask again with the same `id` rather than creating the same query twice, so its grades add up.

输入参数typeapi_keycontent必填

get_query

GET /queries/id: the query `id`, with its `content` as create_query takes it.

输入参数id必填api_key

delete_query

DELETE /queries/id: delete the query `id` and its grades.

输入参数id必填api_key

get_results

GET /queries/id/results: `results`, the query's best items under any of `prefixes` (e.g. ["tools/"]; all items by default), best first, each with its `score`, DNA's estimate of the grade you would give it (on the grades' scale once the grid has some; before, only the order means anything), as list_items shows it, without content. `ungraded`: leave out the items you already graded for this query. Grade what you judged with put_grade: the results learn from it within a few seconds.

输入参数id必填limitapi_keyprefixesungraded

put_grade

PUT /queries/id/grades/key: grade the item at `key` (as get_results returns it, e.g. "42") for the query `id`. `score` is from -1 (wrong) to 1 (right), anything between for partly right; it trains DNA and replaces the grade before. Grade the results you judged, typically the first few.

输入参数id必填key必填score必填api_key

get_grade

GET /queries/id/grades/key: the query's grade of the item at `key`.

输入参数id必填key必填api_key

delete_grade

DELETE /queries/id/grades/key: forget the query's grade of the item at `key`.

输入参数id必填key必填api_key

list_grades

GET /queries/id/grades: `grades`, the query's grades, {"key", "score"}, in path order.

输入参数id必填api_key

版本历史

2
  1. v1.2.0最新Nov 7, 2026
  2. v1.1.0Oct 19, 2026

评分

已满足适用检查项的 83%

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 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分

    请声明包含 README 的 GitHub 仓库,或在 OAuth 受保护资源元数据中提供 resource_documentation。

  • 许可证不适用

    托管服务按其提供方的条款使用,因此这里不要求许可证。此检查项不计入百分比。

其他 Hashgrid 集成