Carbon Forge

io.github.100monkeys-ai由 GitHub 账号 100monkeys-ai 发布v1.0.0更新于 Oct 24, 2026

One record of code, files and pages that people and agents read and write, with lanes and git.

发布方自己的服务:Carbon Fyi

已验证Streamable HTTP可网页运行网页搜索与抓取知识与记忆开发者工具

概览

AI 生成的概览

让助手读取、搜索和浏览由页面、原子与代码树组成的工作区,并查看修订、评论和交叉链接。

可以做什么
它把页面和原子以 Markdown 形式暴露出来,提供按路径或 UUID 列出和读取的工具,也可只返回某个标题小节。搜索既有全文加向量的混合检索,也有精确子串匹配。此外还能列出并比较修订、读取评论和媒体元数据、跟踪交叉链接与语义近邻、浏览代码树和工作区文件树,并报告实例与工作区的定位信息。
适用场景
当助手需要查阅或维护由人和智能体共同编辑的文档、笔记或代码记录时适用。适合在已知工作区内做检索、查看修订历史或评论、以及浏览代码树和文件结构。不太适合一次性的公开网页查询。
运行要求
需要访问位于 carbonforge.dev 的远程 streamable HTTP 端点,无需本地安装。可选的 Authorization 请求头携带来自设置或 API 令牌的 bearer 令牌,用于写入或读取私有内容;不提供时端点仅以只读方式提供公开工作区。需要能访问该端点的网络。
安装前请注意
Authorization 请求头是 bearer 令牌;没有它时端点只提供公开工作区的只读访问,写入或读取私有内容需要令牌。令牌可能带有对工作区内容的写入权限,应视为机密并尽量使用受限范围的令牌。部分工具会按查看者身份过滤,但列出工作区只是成员目录,并不代表该令牌具备相应权限。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Carbon Forge,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/io.github.100monkeys-ai%2Fcarbon-forge/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": {
    "carbon-forge": {
      "type": "http",
      "url": "https://carbonforge.dev/api/mcp"
    }
  }
}

工具

22

pages.list

List pages in a workspace. `path_prefix` narrows by leading segment; `body_contains` keeps pages whose Markdown holds a literal substring; `metadata` keeps pages whose top-level metadata contains the given scalar keys; `sort` (path | updated_at | created_at) and `direction` order the set; `include_metadata` adds each page's metadata. Details: https://carbonforge.dev/docs/p/api/mcp-tools-catalog

输入参数sortlimitcursorinstancemetadatadirectionworkspacepath_prefixbody_containsinclude_metadata

pages.read

Read a page by path or UUID. Returns the Markdown body plus the page metadata object. Pass `section` with a heading's plain text to get back only that heading and the blocks under it, down to the next heading at the same or shallower level; the result then also carries `section: { heading, level, matches }`. Details: https://carbonforge.dev/docs/p/api/mcp-tools-catalog

输入参数lanesectioninstancepathOrId必填workspace

atoms.list

List atoms in the current workspace. The `path_prefix`, `body_contains`, `metadata`, `sort`, `direction` and `include_metadata` arguments mirror the same arguments on pages.list.

输入参数sortlimitcursorinstancemetadatadirectionworkspacepath_prefixbody_containsinclude_metadata

atoms.read

Read an atom by path or UUID with usage_pages projection. Returns metadata. Pass `section` with a heading's plain text to get back only that heading and the blocks under it, down to the next heading at the same or shallower level; the result then also carries `section: { heading, level, matches }`, and everything else on it is the atom's own, so a section can be read and written straight back.

输入参数lanesectioninstancepathOrId必填workspace

search.global

Hybrid FTS + pgvector + RRF search. Returns Markdown excerpts.

输入参数q必填limitscopecursorinstanceworkspaceperspective

search.literal

Exact-substring search over the Markdown projection of pages and atoms — deterministic, unlike hybrid `search.global`. A needle shorter than 3 characters is rejected. Returns one envelope per matched entity, up to 5 hits each as `{ line, col, snippet }`. `case_sensitive` defaults to false; `scope` is workspace | all_mine | all_public. Details: https://carbonforge.dev/docs/p/api/mcp-tools-catalog

输入参数q必填kindslimitscopecursorinstanceworkspacecontext_linescase_sensitive

discovery.list_entities

Browse pages or atoms inside a workspace with faceted filters (tag, author, date range, visibility, metadata containment) and sort by alphabetical, recency, or star count. Viewer-aware: members see everything, anonymous callers see only public entities in public workspaces. 50 items per page, cursor-based. Details: https://carbonforge.dev/docs/p/api/mcp-tools-catalog

输入参数qkind必填sortlimitcursorfiltersinstanceworkspaceworkspace_idworkspace_slug

revisions.list

List revisions for a page or atom (cursor-paginated).

输入参数kind必填limitcursorinstancepathOrId必填workspace

revisions.get

Fetch a specific revision (returns Markdown body).

输入参数kind必填instancepathOrId必填workspacerevision_id必填

revisions.compare

Markdown-level diff between two revisions of the same page or atom. Returns segments (op: equal | insert | delete) plus both Markdown projections.

输入参数kind必填instancepathOrId必填workspacerevision_a_id必填revision_b_id必填

media.read

Fetch metadata for a single media item.

输入参数instancemedia_id必填workspace

comments.list

List the comment thread for a page or atom.

输入参数instanceworkspacetarget_kind必填target_pathOrId必填

cortex.ground

Orientation surface: instance metadata, both grounding documents, identity and capabilities, reachable workspaces, sidecar health. Pass `workspace` to ground a named workspace without moving the per-token pointer. Pass a `known_grounding_at` / `known_workspace_grounding_at` you hold and an unchanged document is acknowledged, not resent. Details: https://carbonforge.dev/docs/p/api/mcp-tools-catalog

输入参数instanceworkspaceknown_grounding_atknown_workspace_grounding_at

workspaces.list

List every workspace the calling user is a member of. This is a membership catalogue and not a capability: it is not narrowed by the token, so a listed workspace may still be outside this token's reach. Call cortex.ground for what this token can actually resolve.

无需输入参数。

workspaces.resolve_slug

Resolve a workspace slug to its id, role, and archived state. 404 when the caller isn't a member (no enumeration).

输入参数slug必填instance

discovery.list_instances

List instances. Filter: all (default) | public | my | my_admin. public lists an instance that has public reading on, is listed in Discover, is not frozen, and has a workspace that is not private holding a page that is not private. my and my_admin list the caller's own instances (member; admin) with no such gate; all is public plus my. Without a token every filter is public.

输入参数limitqueryfilter

discovery.list_workspaces

List workspaces across one or all instances, with the same filters. public lists a workspace when its instance has public reading on, the workspace is not private, its instance is listed in Discover and not frozen, and it holds a page that is not private. my and my_admin list the caller's own workspaces with no such gate; all is public plus my. Without a token every filter is public.

输入参数limitqueryfilterinstance_id

trees.get

Read a code tree's revision (the current one by default), its metadata and surface, and a page of its entries in path order: path, git mode, size and blob SHA-256, optionally under `path_prefix`. A symlink's blob is its target; a submodule link has no blob and gives its `commit`. With `lane`, `metadata` is the lane's bag if it sets one. Anonymous callers read a public code tree's current one.

输入参数lanelimitoffsetinstanceworkspacepath_or_id必填path_prefixrevision_idsnapshot_id

files.list

Browse the workspace as a file tree, one level at a time: directories, pages, atoms, code trees (expanded at their paths) and library entries. Each node names its kind, entity, current revision and digest; `at` holds the entities exactly at `path`. `surface` keeps that surface only. History: files.history. Anonymous callers see public pages and atoms, and code trees of surface code.

输入参数lanepathlimitoffsetsurfaceinstanceworkspaceperspective

版本历史

1
  1. v1.0.0最新Oct 24, 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 Carbon 集成