doco

Doco is an open-source collaborative document workspace where humans and AI agents write together.

CommunityOnlineNo sign-inGlobalFreeCan modify data

What it can do

  • Doco Whoami: 自检身份：当前 Token 对应的用户与权限 scope
  • Doco List Knowledge Bases: 列出当前用户可见的全部知识库
  • Doco Get Tree: 获取一个知识库的完整目录树（文件夹 + 文档）

What data it sees

Do you need an account

No: the server works without sign-in

Doco is an open-source collaborative document workspace where humans and AI agents write together. It provides stable block IDs, optimistic concurrency, Markdown round-trip, and a 29-tool MCP server for safe knowledge-base operations.

How to connect

How to connect doco to Claude

The server address to paste into Claude settings:

https://doco--songofhawk.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect doco to ChatGPT

The server address to paste into ChatGPT settings:

https://doco--songofhawk.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect doco to Cursor

The server address to paste into Cursor settings:

https://doco--songofhawk.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (29)

Raw names from tools/list. Only developers need these.

doco_whoami自检身份：当前 Token 对应的用户与权限 scope
doco_list_knowledge_bases列出当前用户可见的全部知识库
doco_get_tree获取一个知识库的完整目录树（文件夹 + 文档）
doco_list_documents按知识库 / 文件夹 / 关键词搜索文档列表（分页）
doco_search按标题和正文全文搜索文档。正文命中返回稳定 block_id 与摘要，适合先定位再用块 API 精确读取或修改。
doco_search_v2带查询级完整性证明的全文搜索。返回目录路径、标题路径、前后文、分数解释、source/indexed 水位；exhaustive 模式可用 cursor 完整遍历。projection.complete=false 时结果不完整，不能据此断言“知识不存在”。
doco_translations读取一个具体文档的 Document Set、源语言、可用语言版本和每种语言的新鲜度。
doco_translation_units读取目标语言的块级翻译单元、稳定块映射、source_version 和 missing/current/conflict 等状态。
doco_review_translation_unit在具体目标语言文档上确认当前译文或忽略单元；不接受机器结果直接覆盖，遇到 409 必须重读目标版本。
doco_get_document读取整篇文档正文。format: markdown（读懂语义，附带 warnings 降级提示）/ tiptap-json（无损，精确编辑用）/ html。返回含 version（后续写入需携带）。annotate=anchors 时 markdown 每个顶层块带 <!--@block=<id>--> 锚点，改完整篇写回（PUT content format=markdown）可按锚点保留未改动块的 ID。
doco_changes建立或增量读取文档的块级变更水位。首次不传 after 返回 manifest 与 cursor；后续传 cursor 获取 added/removed/modified/moved。sync_required=true 时必须重新读取正文并建立新基线。
doco_outline读取文档结构大纲：每个标题以稳定 block_id、heading_path 和顶层块区间表达，适合先规划再局部读取。
doco_read按 token 预算局部读取文档。可用 around 锚定任意嵌套 block_id，或用 next_cursor 续读；游标绑定正文版本，read_cursor_stale 时必须重新规划。
doco_traverse沿显式关系遍历文档。返回正向/反向关系、注册谓词、来源块与来源版本；status=dangling_* 时目标已失效，evidence_freshness=stale 时应重新确认证据，projection_freshness=stale 时不得当作完整关系图。
doco_create_relation从稳定来源块创建一条显式、可审计的类型关系。target_uri 使用 doco://doc/{id}#block={block_id}；创建前服务端校验两端权限与块存在性。
doco_concepts统一读取概念层：列出/获取显式概念、沿概念关系遍历，或列出待审核候选。候选与显式概念严格分离。
doco_edit_concepts统一写入显式概念：创建、更新、补来源/关系、合并，以及接受/拒绝候选。客户端自动读取 ETag、发送 If-Match，并为每次写入生成幂等键。
doco_refresh_concept_candidates触发概念候选抽取/刷新。只生成待审核候选，不会直接污染显式概念层；写入自动带幂等键。
doco_summary读取章节、文档、文件夹或知识库摘要，或查询异步生成任务。结果带来源块、来源版本、覆盖率、freshness 与 fallback 语义；模型关闭时仍始终可用。
doco_save_summary人工编辑并可钉住摘要。客户端会先读取当前 summary/source 双版本后带保护写入；pinned 只防自动覆盖，来源变化后仍会显示 stale。
doco_rebuild_summary重建摘要。deterministic 同步返回可追溯 fallback；model 只创建异步任务，必须随后用 doco_summary(job_id) 查询，来源变化或摘要被钉住时结果会 obsolete 而不会覆盖。
doco_update_document整篇写回文档正文。markdown 写回凭 <!--@block=<id>--> 锚点保留未改动块 ID（配合 doco_get_document 的 annotate=anchors）；tiptap-json 为整篇无损替换。强烈建议带 base_version，409 时重读合并重试。
doco_get_blocks按块读取文档：返回顶层（或 recursive=true 时全部）块及其稳定 block_id 与 version
doco_patch_block更新单个块：提供完整 node 替换，或用 attrs/content 局部修改。带 base_version 做乐观并发校验；不带则自动读取最新版本。409 时请重读合并重试。
doco_insert_blocks在指定位置插入一个或多个块。position 六选一：after_block_id / before_block_id / parent_block_id(+child_index) / document_start / document_end / after_heading（按标题文本定位，服务端匹配）
doco_delete_block删除单个块
doco_batch_edit单事务批量编辑（1–100 个操作，全有或全无）：operations 为 {op: insert|replace|delete, ...} 数组。base_version 必填语义由服务端强制（不填自动读取）。
doco_create_document新建文档，可同时灌入初始正文（content: {format: markdown|tiptap-json|html, content|document}）
doco_upload_attachment上传附件（图片/PDF/文本/Word），返回 attachment_id 与 URL；在文档块中用 image 节点 attrs.attachmentId 引用