> ## Documentation Index > Fetch the complete documentation index at: https://docs.danubeai.com/llms.txt > Use this file to discover all available pages before exploring further. # Context > What every agent should know before it works for your team: organization and personal markdown, read at the start of a session Context is a set of markdown documents that agents read before they work for you, the way Claude Code reads a `CLAUDE.md` file. It comes in two layers: | Layer | Written by | Read by | | ---------------- | ------------------------------------------------------------- | ----------------------------------------------------------- | | **Organization** | The organization's owners and admins, in the dashboard | Every member's agent, whenever it acts for the organization | | **Personal** | You, in the dashboard, or your agent through `update_context` | Only your own agents | Good organization context says what the company does, its products and customers, the terms people use, and the conventions and policies an agent should follow. Good personal context says your role, what you are working on and how you like things done. ## Edit context Open [Dashboard > Context](https://danubeai.com/dashboard/context) with the organization selected in the workspace switcher. The tab named after the organization holds its documents (in **Personal** there is no such tab, and no organization context reaches your agent); owners and admins can add, edit, reorder and delete them, and everyone else can read them. The **Personal** tab holds yours. A layer holds up to 10 documents of up to 32,000 characters each. Agents never write organization context. The organization endpoints answer `403` to any API key, an admin's included, so a prompt injected into one agent can't change what every member's agent reads. Every organization edit is recorded in the [audit log](/organizations/audit-log) (`context.create`, `context.update`, `context.delete`, `context.restore`). ## Share a document with your organization A personal document you want the whole team's agents to read can be shared with the organization. **Share with \** on the document (in the **Personal** tab) copies its text into the organization's context; your own document stays where it is and stays yours. * **Owners and admins** add it at once. When the organization already has a document with that name, the dashboard asks before replacing it; the old text stays in that document's history. * **Members** send it to the organization's owners and admins as a proposal. Sharing the same name again updates the pending proposal. * **Agents only propose.** A share made with an API key, an admin's included, always becomes a proposal, so no agent writes what every member's agent reads. Owners and admins review proposals under **Proposals** on the organization's tab (the tab shows how many are waiting): the proposer, the name and the text, raw or rendered, with **Approve** or **Decline**. Approving writes the document into the organization's context, with the same replace question when the name is taken. Members see their own pending proposals there and can **Withdraw** one. Every step is recorded in the [audit log](/organizations/audit-log) (`context.propose`, `context.proposal_approve`, `context.proposal_decline`). ## What the agent sees At the start of a session an agent calls `get_context` (or reads the MCP resource `context://current`, or `GET /v1/context`). It gets one merged text, broad to narrow: 1. **Organization context** for the organization the session acts for. 2. **Personal context**. 3. **Skills you can load**: your organization's [internal skills](/organizations/skills) and your private ones, by name and description. The agent loads one with `get_skill` when a task calls for it. 4. **Your timezone**, when set. Which organization applies: the one the connection acts for (the `danube-org-id` header, or an organization API key). If there is none and you belong to exactly one shared organization, that one applies. If you belong to several, no organization layer is included and the answer carries a `note` asking you to pick one, since guessing could put one company's context in front of another's work. The Danube MCP server tells clients to call `get_context` first, and `get_context` is in the `core` tool group, so it is available on every connection. Agents treat context as information about you and your organization, not as instructions that override your own request. ## How agents remember When you tell an agent something durable (your role, a preference, what you are working on), it can save it with the `update_context` MCP tool: ``` update_context(content="Prefers weekly summaries on Mondays.", document="notes.md", mode="append") ``` `mode` is `append` (a new paragraph at the end) or `replace`. The document is created when missing. `update_context` only writes the personal layer, and it is in its own tool group (`context`), so a connection limited with `?tools=core` can read context but not change it. From a script or the CLI: ```bash theme={null} danube context remember "Prefers weekly summaries on Mondays." danube context show ``` ## Revisions Every edit keeps the previous text as a revision: yours, your agent's and every organization edit. The dashboard shows who changed a document, when and how (`dashboard`, `api` or `agent`), and restores any earlier version in one click. The 50 most recent revisions of each document are kept. To avoid overwriting someone else's change, a write can carry `expected_version`; if the document changed since that version, nothing is written and the answer is `409` with the current text. ## No credentials in context Everything in context is shown to agents, so a key or token in a document would reach every agent that reads the layer. Content is scanned with the same secret scanner that redacts tool responses; a document that contains a credential is refused with `400`. Store keys and tokens as [credentials](/api-reference/endpoint/store_credential) instead. ## API | Endpoint | Purpose | | ------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [`GET /v1/context`](/api-reference/endpoint/get_context) | The merged context (`format=markdown` for the text only) | | [`POST /v1/context/personal/upsert`](/api-reference/endpoint/upsert_personal_context) | Write a personal document by name | | `GET /v1/organizations/{org_id}/context/documents` | The organization's documents (any member) | | `POST /v1/context/personal/documents/{id}/share` | Share a personal document (`org_id`, `replace`): `{"result": "published"}` for an owner or admin in the dashboard, `{"result": "proposed"}` otherwise; `409` with the `existing` document when the name is taken | | `GET /v1/organizations/{org_id}/context/proposals` | Pending proposals: all of them for owners and admins, your own for anyone else | | `POST /v1/organizations/{org_id}/context/proposals/{id}/approve` | Approve (owner or admin, dashboard; `replace` to overwrite a document of the same name) | | `POST /v1/organizations/{org_id}/context/proposals/{id}/decline` | Decline (owner or admin, dashboard) | | `POST /v1/organizations/{org_id}/context/proposals/{id}/withdraw` | Take back your own pending proposal |