Add Searchable Knowledge to Your Board

How searchable knowledge works

The REST API gives you two explicit building blocks:

Create nodes for source records: websites, videos, PDFs, notes, and other board items.
Vectorize text that you provide with POST /documents/vectorize.

MCP can create boards, add source nodes, upload files, and vectorize text resources from Claude Code. For URLs, videos, and PDFs, provide extracted text when you want the content to be searchable.

Source nodes

Create nodes for the source material you want to organize on the board.

curl -X POST https://api.chatgrid.ai/v1/boards/{boardId}/nodes \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "type": "youtube",
    "position": {"x": 0, "y": 0},
    "data": {"url": "https://youtube.com/watch?v=your-video-id", "label": "Webhook tutorial"}
  }'

PDFs

Upload a PDF, then process it. The current REST vectorize endpoint accepts text, so pass extracted text to /documents/vectorize after processing.

# Step 1: Upload the file
curl -X POST https://api.chatgrid.ai/v1/boards/{boardId}/assets \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "file=@architecture.pdf"

# Step 2: Start document processing
curl -X POST https://api.chatgrid.ai/v1/boards/{boardId}/documents/process \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"file_url": "{assetUrl}", "node_id": "{nodeId}"}'

Use the Jobs endpoint to check the returned job status.

Web pages

Create a website node, then vectorize the text you extracted from that page.

curl -X POST https://api.chatgrid.ai/v1/boards/{boardId}/nodes \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "type": "url",
    "position": {"x": 400, "y": 0},
    "data": {"url": "https://blog.example.com/postgres-scaling-tips", "label": "Postgres scaling tips"}
  }'

Plain text

Paste in notes, decisions, meeting summaries — anything.

curl -X POST https://api.chatgrid.ai/v1/boards/{boardId}/documents/vectorize \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "content": "Decision: We chose Inngest over Temporal for job orchestration. Reasons: managed service, no infra to operate, built-in rate limiting. Temporal is the upgrade path if we outgrow Inngest.",
    "metadata": {"source": "decision-log", "date": "2026-03-04"}
  }'

Search your content

Once content is vectorized, search it semantically.

curl -X POST https://api.chatgrid.ai/v1/boards/{boardId}/documents/search \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "why did we choose Inngest?", "limit": 3}'

Returns the most relevant chunks with their source metadata:

{
  "object": "list",
  "data": [
    {
      "content": "Decision: We chose Inngest over Temporal for job orchestration...",
      "metadata": {"source": "decision-log", "date": "2026-03-04"},
      "similarity": 0.92
    }
  ]
}

In Claude Code

These same API actions are available through MCP:

> Add this YouTube video to the board: https://youtube.com/watch?v=...
> Upload architecture.pdf to the backend board
> Add these extracted architecture notes to the backend board: "..."
> Search the board for "why did we choose Inngest?"

Cookbooks

Add Searchable Knowledge to Your Board

How searchable knowledge works

Source nodes

PDFs

Web pages

Plain text

Search your content

In Claude Code

Next steps

Team Knowledge

Streaming

​How searchable knowledge works

​Source nodes

​PDFs

​Web pages

​Plain text

​Search your content

​In Claude Code

​Next steps

Team Knowledge

Streaming

How searchable knowledge works

Source nodes

PDFs

Web pages

Plain text

Search your content

In Claude Code

Next steps