🔑 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 doctoranytime 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 0.4.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| contextportal-0.4.1.tar.gz | 29.6 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| contextportal-0.4.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 52.6 kB
Release files / contextportal-0.4.1.tar.gz
| Download URL | contextportal-0.4.1.tar.gz |
|---|---|
| Size | 29.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
afa49adffc4c63b093436a4d7dbdb17fe9b921574f16beee49b7a68d47705ae3
|
|
BLAKE2b-256 checksum How to use checksums |
d9cb58bd3c346a9d7df2ec60ff8c8f2993b3aa5b7d37d0a3b75adead2d92f71c
|
| 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 Oct 11, 2026.
Transparency logRelease files / contextportal-0.4.1-py3-none-any.whl
| Download URL | contextportal-0.4.1-py3-none-any.whl |
|---|---|
| Size | 23.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
71837f057fb4d52a80e8fd70cf1ba65627c30ff9aa961fa078b9c3a01e91603f
|
|
BLAKE2b-256 checksum How to use checksums |
75ad99756d52d84b8cf8f9169570c16fdebc0783a85e6fb057a3a7b3754d7517
|
| 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 Oct 11, 2026.
Transparency log