Integration

PDF Redaction integration

PDF Redaction (by StabRise) finds personal data in a PDF with AI and blacks it out: names, dates, emails, phone numbers, addresses, ID, account, card and passport numbers, signatures, QR codes, faces and more, on digital and scanned PDFs (OCR in 7 languages, rotated text). Upload a stored PDF to get the redacted PDF back as a file, or to get the detected entities and their boxes without changing the document, and check the key's remaining usage balance. Redaction and detection calls are billed against the plan's monthly allowance, and the free plan allows 5 requests a minute. The base64 variants of the same operations and the custom-prompt redaction (offered with base64 input only) are not exposed, nor the routes of the vendor's own sign-in and MCP server. Authentication is an API key generated on the PDF Redaction API keys page, sent in the X-API-Key header.

Connect PDF Redaction How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in PDF Redaction.Built from the 3 PDF Redaction tools below, on the connection you add once.

What you can do with PDF Redaction

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Each badge shows the default agent permission of an endpoint (allowed: an agent calls it without asking; ask first: you are asked before an agent calls it, when the agent or chat asks permission for sensitive actions; never: no agent may call it), which every user can change endpoint by endpoint in their credential settings.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Balance, 1 operation

get_usage_balanceGet usage balanceGETAgents: ask firstReturns the API key's remaining usage balance and whether it may run redact_pdf and detect_pii_in_pdf now. Free: uses no allowance and is not rate limited. Call it again after a redaction to see the new balance.

Pdf, 1 operation

redact_pdfRedact pdfPOSTAgents: ask firstRedacts (blacks out) the personal data AI finds in a stored PDF and returns the redacted PDF as a new file. Billed against the plan's monthly allowance. Use detect_pii_in_pdf to list what would be found without changing the file.

Pii, 1 operation

detect_pii_in_pdfDetect pii in pdfPOSTAgents: ask firstFinds the personal data in a stored PDF without changing it and returns each entity found: its kind, the text itself (personal data), a confidence score and its boxes, page by page. Billed against the plan's monthly allowance.

Use PDF Redaction from Claude Code, Cursor or Codex

Connect PDF Redaction in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its PDF Redaction operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect PDF Redaction

Create your workspace
Sign up free. Nothing to install.
Connect PDF Redaction once
Add your PDF Redaction connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.