MCP Tools
Context & Resources

add_context

Add a new context item to your reference library. Context items are reference materials that power AI generation — they help the AI produce more accurate, on-brand, and relevant content. You can supply the body two ways: - **`content`** — paste the markdown body directly. Best for short or hand-authored material. - **`content_url`** — pass a public URL and the backend fetches it and converts it to clean markdown server-side using a headless browser + Mozilla Readability (the same engine used for the user-website context-import flow). Use this whenever the body is large, comes from a presigned-link export (e.g. Google Doc, Composio sandbox), or you'd otherwise have to pull the page into your own conversation just to forward it. Exactly one of `content` or `content_url` is required — providing both returns a 400.

Parameters

NameTypeRequiredDefaultDescription
namestringYes—Descriptive name for the context item
contentstringNo—Markdown body. Mutually exclusive with `content_url` — provide exactly one
content_urlstringNo—Public URL — backend fetches it and extracts clean markdown server-side. Mutually exclusive with `content`
collection_idintegerNo—Collection ID to organize the item (from `list_context_collections` or `create_context_collection`)
project_idstringNo—Project ID to associate with (from `get_projects`)

Input Schema

{
  "type": "object",
  "required": [
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "description": "Descriptive name for the context item"
    },
    "content": {
      "type": "string",
      "description": "Markdown body. Mutually exclusive with content_url — provide exactly one."
    },
    "project_id": {
      "type": "string",
      "format": "uuid",
      "description": "Project ID to associate with (from get_projects)"
    },
    "content_url": {
      "type": "string",
      "description": "Public URL — backend fetches it and extracts clean markdown server-side. Mutually exclusive with content."
    },
    "collection_id": {
      "type": "integer",
      "description": "Collection ID to organize the item (from list_context_collections or create_context_collection)"
    }
  }
}

Output Schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "format": "uuid",
      "description": "Context item ID"
    },
    "name": {
      "type": "string",
      "description": "Context item name"
    },
    "content": {
      "type": "string",
      "description": "The stored reference content"
    },
    "link_url": {
      "type": "string",
      "format": "uri",
      "description": "Direct URL to view this context item in the Marcora app. Resolves to the project, collection, or reference library view depending on the item's scope."
    },
    "created_at": {
      "type": "integer",
      "description": "Unix timestamp of creation"
    },
    "project_id": {
      "type": "string",
      "format": "uuid",
      "description": "Project association (if assigned)"
    },
    "word_count": {
      "type": "integer",
      "description": "Word count of content"
    },
    "collection_id": {
      "type": "integer",
      "description": "Collection this item belongs to (if assigned)"
    }
  }
}

Instructions

Use this tool to add a new context item to your reference library.

Workflow:

  1. Provide a descriptive name.
  2. Provide either content (markdown body directly) or content_url (a public URL the backend fetches and converts to markdown server-side).
  3. Optionally assign to a collection by passing collection_id. Use list_context_collections to see existing collections and their IDs, or use create_context_collection to create a new one and get its ID.
  4. Optionally associate with a project by passing project_id. Use list_projects to see available projects and their IDs.

Use context items for: brand voice guidelines, company facts, product descriptions, audience personas, competitive intelligence.

Errors

  • 400 — Either content or content_url is required. (neither was supplied)
  • 400 — Provide either content or content_url, not both. (both were supplied)
  • 400 — Failed to extract markdown from content_url (the URL could not be fetched or parsed; check the URL is publicly reachable)

Example prompts

  • "Add our brand guidelines to Marcora"
  • "Store this competitive analysis as context"
  • "Save https://example.com/competitor-pricing as a context item called 'Acme pricing'"
  • "Add this product brief to the 'Product Launch' collection"

Examples

Add competitor research to a project

Store competitor analysis as context tied to a specific project, so content generated for that project can reference competitive positioning.

Input
{
  "name": "Q2 Competitor Analysis — Acme Corp",
  "content": "Acme Corp launched a freemium tier in March. Their messaging focuses on speed and simplicity. Key weakness: no enterprise SSO support.",
  "project_id": "f47ac10b-58cc-4372-a567-0e02b2c3d479"
}
Output
{
  "id": "b2c3d4e5-f6a7-8901-bcde-f12345678901",
  "name": "Q2 Competitor Analysis — Acme Corp",
  "content": "Acme Corp launched a freemium tier in March...",
  "word_count": 27,
  "project_id": "f47ac10b-58cc-4372-a567-0e02b2c3d479",
  "created_at": 1712678400
}
Scroll to Top