Skip to main content

🔑 ContextPortal

Give your AI agent access to authenticated web pages — without giving it your credentials.

Your AI agent can fetch any public webpage. But the moment it hits a login wall — Jira, Confluence, internal wikis, enterprise dashboards — it's stuck.

ContextPortal sits between your AI agent and the web. When the agent needs a protected page, ContextPortal uses your existing browser session to grab it, strips out all the noise, and hands back clean Markdown. The agent gets context. It never gets your cookies.

🤖 Agent: "I can't read this ticket. It's behind an SSO login wall. Please take 5 screenshots."
👤 You: "No way. Why am I doing homework for an AI?"
🔑 ContextPortal: "Say less. Log in once in your browser; your agent retrieves the page forever."

🏛️ The 4 Pillars

  • 🛑 Stop feeding your AI screenshots. Copy-paste is not an agent architecture.
  • 🔁 Authenticate once. Retrieve context continuously. Log in once; your agent reads forever.
  • 🔐 Your browser holds the session. Your agent gets the page. Zero cookies leaked.
  • 🎯 Give your agent a retrieval tool, not a browser to operate. Clean Markdown, zero DOM fragility.

Install

🔌 Connect ContextPortal to your AI

ContextPortal works through the Model Context Protocol (MCP) and configures supported AI clients automatically.

┌──────────────────────────────────────────────┐
│  Connect your agent                          │
│                                              │
│  $ contextportal setup                       │
│                                              │
│  ✓ MCP server                                │
│  ✓ Browser profile                           │
│  ✓ AI client                                 │
│                                              │
│  Ready.                                      │
└──────────────────────────────────────────────┘

Onboarding shouldn't feel like wrestling with JSON files and virtual environments.
It's three steps: Install ContextPortal → Connect your agent → Give it the URL.


Step 1: Install ContextPortal

uv tool install contextportal

🪄 Quick Setup (Auto-Config)


Configure your AI agent (Claude Desktop, Cursor, Antigravity) with a single command:

Step 2: Connect your AI agent

contextportal setup

Verify your environment anytime: That's it! ContextPortal scans your system, detects installed AI agent clients, creates a safety backup, and registers the MCP server automatically.

contextportal doctor

🩺 Run contextportal doctor anytime to audit your system health and client connections.

🔐 Log In (Once)


Log into your private sites in your local browser — your session is saved automatically:

🤖 Supported AI Clients

ContextPortal provides zero-friction automatic setup for major AI developer tools, plus a standard manual fallback:

AI Client Platform Automatic Setup Manual Config Path
Cursor Win / Mac / Linux contextportal setup --client cursor ~/.cursor/mcp.json
Google Antigravity Win / Mac / Linux contextportal setup --client antigravity ~/.gemini/antigravity/mcp_config.json
Claude Desktop Win / Mac / Linux contextportal setup --client claude %APPDATA%\Claude\ or ~/Library/Application Support/Claude/
VS Code (Cline / Roo / Copilot) Universal Built-in MCP settings .vscode/mcp.json or Extension settings
Any Custom MCP Client Universal STDIO transport Standard JSON payload

Step 3: Log into your private sites (once)

contextportal login

Test it directly: A clean browser opens. Log into your private tools — Jira, Confluence, internal wikis, GitHub enterprise, Handshake. Close the window when you're done. Your session stays locally on your machine.

contextportal fetch https://your-protected-site.com/docs

🔌 Manual MCP Configuration (Optional)

🎉 You're ready. Now just give your agent the URL.

In your AI chat (Cursor, Claude, Antigravity, etc.):

"Summarize the roadmap at https://internal.company.com/q3-roadmap"

Your agent calls ContextPortal → ContextPortal retrieves the page through your authenticated session → clean, token-optimized Markdown comes back.

No screenshots. No copy-pasting. You're done.


🛠️ Manual Configuration Fallback (Optional)

If you prefer to configure manually:

{
  "mcpServers": {
    "context-portal": {
      "command": "contextportal",
      "args": ["mcp"]
    }
  }
}

Works with Cursor, Claude Desktop, Antigravity, VS Code, and any MCP client.

Learn More

Metadata

Release files for contextportal 0.3.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for contextportal 0.3.0
File Size Uploaded
contextportal-0.3.0.tar.gz 23.1 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for contextportal 0.3.0
File Interpreter ABI Platform
contextportal-0.3.0-py3-none-any.whl Python 3 none any Details

Total release size: 41.7 kB

Release files / contextportal-0.3.0.tar.gz

Download URL contextportal-0.3.0.tar.gz
Size 23.1 kB
Tags Source
SHA-256 checksum
How to use checksums
8c0358dedacf885456ad78ea7d98800cb306825e24a3d9ca70c6a29c31b8b139
BLAKE2b-256 checksum
How to use checksums
cf11856125be4d23db239882af8931ba9d7ab6c47baad7bcd0639ed4fff2fe28
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 14, 2026.

Transparency log

Release files / contextportal-0.3.0-py3-none-any.whl

Download URL contextportal-0.3.0-py3-none-any.whl
Size 18.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
564aa09d42eef58e381ddc43b65458002ef3756bafd53232148036d7516a01fd
BLAKE2b-256 checksum
How to use checksums
7fbeeadd8c537bc56be61b3026080b5acd95108292fe573d61c3155eae07a2b1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 14, 2026.

Transparency log

Release history Release notifications | RSS feed

0.4.1

2 release files

0.4.0

2 release files

This release

0.3.0 This release

2 release files

0.2.0

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page