Skip to content

[IMPLEMENTING] Auth for portalJS key #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Abeelha wants to merge 12 commits into
base: main
Choose a base branch
from
Open

[IMPLEMENTING] Auth for portalJS key #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
3b6d972
[ADD] Auth URL Param for portalJS key
Abeelha Oct 7, 2025
dd5b295
added preview url config in wrangler
Abeelha Oct 7, 2025
8607a92
Revert "added preview url config in wrangler"
Abeelha Oct 7, 2025
fe087a1
Revert "[ADD] Auth URL Param for portalJS key"
Abeelha Oct 7, 2025
7796181
Implemented runtime API per chat session | Added new tool for dataset…
Abeelha Oct 7, 2025
34d9719
[IMPLEMENTED]:
Abeelha Oct 7, 2025
831bfb6
added getApiUrl() helper method
Abeelha Oct 7, 2025
1d96c63
[REMOVED]: create_organization, add_user_to_organization, remove_user…
Abeelha Oct 8, 2025
e17c656
[ADD-tools]: get_dataset_stats, preview_resource, get_related_dataset…
Abeelha Oct 8, 2025
95c8275
URL normalization and validation
Abeelha Oct 8, 2025
30695e6
Added requireAuth helper ( cleaner aproach ), added try-catch error h…
Abeelha Oct 8, 2025
37dc878
update readme
Abeelha Oct 8, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
80 changes: 75 additions & 5 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
# Building a Remote MCP Server on Cloudflare (Without Auth)

This example allows you to deploy a remote MCP server that doesn't require authentication on Cloudflare Workers.
This example allows you to deploy a remote MCP server that doesn't require authentication on Cloudflare Workers.
Copy link
Copy Markdown

@coderabbitai coderabbitai Bot Oct 8, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟠 Major

Docs contradict auth-enabled implementation; update intro and deployment references.

Text says "doesn't require authentication" and links/templates point to "remote-mcp-authless". Align with API-key auth, update title/intro, and replace authless template/URLs with this repo’s deployment path. Prefer HTTPS in examples.

🤖 Prompt for AI Agents 
In README.md around line 3, the intro claims the example "doesn't require
authentication" and points to authless templates/URLs; update the title and
first paragraph to state this deployment uses API-key (auth-enabled) instead of
authless, replace any links/templates that reference "remote-mcp-authless" with
this repository's deployment path (use the canonical repo/deploy URLs), and
ensure all example URLs use HTTPS; keep wording concise and update any related
deployment reference text to mention API-key configuration steps instead of "no
auth".


## Get started:
## Get started:

[![Deploy to Workers](https://deploy.workers.cloudflare.com/button)](https://deploy.workers.cloudflare.com/?url=https://github.com/cloudflare/ai/tree/main/demos/remote-mcp-authless)

Expand All @@ -15,7 +15,7 @@ npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/rem

## Customizing your MCP Server

To add your own [tools](https://developers.cloudflare.com/agents/model-context-protocol/tools/) to the MCP server, define each tool inside the `init()` method of `src/index.ts` using `this.server.tool(...)`.
To add your own [tools](https://developers.cloudflare.com/agents/model-context-protocol/tools/) to the MCP server, define each tool inside the `init()` method of `src/index.ts` using `this.server.tool(...)`.

## Connect to Cloudflare AI Playground

Expand All @@ -27,7 +27,7 @@ You can connect to your MCP server from the Cloudflare AI Playground, which is a

## Connect Claude Desktop to your MCP server

You can also connect to your remote MCP server from local MCP clients, by using the [mcp-remote proxy](https://www.npmjs.com/package/mcp-remote).
You can also connect to your remote MCP server from local MCP clients, by using the [mcp-remote proxy](https://www.npmjs.com/package/mcp-remote).

To connect to your MCP server from Claude Desktop, follow [Anthropic's Quickstart](https://modelcontextprotocol.io/quickstart/user) and within Claude Desktop go to Settings > Developer > Edit Config.

Expand All @@ -47,4 +47,74 @@ Update with this configuration:
}
```

Restart Claude and you should see the tools become available.
Restart Claude and you should see the tools become available.

## Available Tools

This PortalJS MCP Server provides multiple tools for working with datasets, organizations, and resources. Here's how to use them with Claude or ChatGPT:

### 🔑 Authentication

**Set your API key** (required for write operations)
- Say: "My PortalJS API key is `your_key_here`"
- This will call the `set_api_key` tool

### 🔍 Discovery Tools (No Auth Required)

**Search for datasets**
- Say: "Search for datasets about climate change"
- This will call the `search` tool

**Get detailed dataset information**
- Say: "Show me details about the dataset named 'world-happiness-2020'"
- This will call the `fetch` tool

**Get quick dataset statistics**
- Say: "What are the stats for dataset 'world-happiness-2020'?"
- This will call the `get_dataset_stats` tool (shows size, formats, resource count, etc.)

**Preview data structure**
- Say: "Preview the first 10 rows of resource ID `abc123`"
- This will call the `preview_resource` tool (shows column names, types, and sample data)

**Find related datasets**
- Say: "Find datasets related to 'world-happiness-2020'"
- This will call the `get_related_datasets` tool (discovers similar datasets by tags or organization)

**Compare multiple datasets**
- Say: "Compare these datasets: 'dataset-a', 'dataset-b', 'dataset-c'"
- This will call the `compare_datasets` tool (side-by-side metadata comparison)

**Get organization information**
- Say: "Tell me about the organization 'my-org-name'"
- This will call the `get_organization_details` tool (shows credibility info like creation date, dataset count)

### ✏️ Write Operations (Requires Authentication)

**List your organizations**
- Say: "Show me my organizations"
- This will call the `list_organizations` tool (needed to get organization IDs for creating datasets)

**Create a new dataset**
- Say: "Create a dataset called 'my-new-dataset' with title 'My Dataset' in organization `org-id`"
- This will call the `create_dataset` tool

**Add a resource to a dataset**
- Say: "Add a CSV resource from URL `https://example.com/data.csv` to dataset 'my-dataset'"
- This will call the `create_resource` tool

**Update dataset metadata**
- Say: "Update dataset 'my-dataset' with new description 'Updated info' and tags 'data, analysis'"
- This will call the `update_dataset` tool

**Update organization details**
- Say: "Update organization 'my-org' with new description 'New description'"
- This will call the `update_organization` tool

### 💡 Tips

- Most discovery tools work without authentication
- Write operations require setting your API key first
- Dataset names must be lowercase with hyphens (e.g., 'my-dataset-name')
- When creating datasets, use `list_organizations` first to get your organization ID
- All tools return JSON-formatted responses for easy parsing.
Loading