Search rare historical texts with OCR, translations & DOI citations.
Search rare historical texts with OCR, translations & DOI citations. The source mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 5 defined tools rather than through you.
Your browser does not support the video tag.
Everything the assistant can do here goes through one of these:
Endpoint — MethodApproach — Examplecurl — The curl tool exposed by this serverPostman — 1. Create a new GET request. 2. Set URL to e.g. https://sourcelibrary.org/api/embed/bph/books 3. On the Params tab add query keys: limit =Browser — The Browser tool exposed by this serverYou will need 8 environment variables: NEXTAUTH_SECRET, GOOGLE_API_KEY, VERCEL_BLOB_TOKEN, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, STRIPE_SECRET_KEY, ZENODO_TOKEN, SUPABASE_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
The server ships on npm as tsc, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
Among the browser automation options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Source's toolset — Endpoint, Approach, curl and 2 more — is a fair guide to whether it matches your workflow. It is maintained by Embassy-of-the-Free-Mind; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Source's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Endpoint | Method |
| Approach | Example |
| curl | The curl tool exposed by this server. |
| Postman | 1. Create a new **GET** request. 2. Set URL to e.g. https://sourcelibrary.org/api/embed/bph/books 3. On the **Params** tab add query keys: limit = 24, sort = title, translated = true 4. Leave **Auth** as *No Auth* for th |
| Browser | The Browser tool exposed by this server. |
{
"mcpServers": {
"source-library": {
"command": "npx",
"args": ["-y", "tsc"],
"env": {
"NEXTAUTH_SECRET": "your-value",
"GOOGLE_API_KEY": "your-value",
"VERCEL_BLOB_TOKEN": "your-value",
"AWS_ACCESS_KEY_ID": "your-value",
"AWS_SECRET_ACCESS_KEY": "your-value",
"STRIPE_SECRET_KEY": "your-value",
"ZENODO_TOKEN": "your-value",
"SUPABASE_URL": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| NEXTAUTH_SECRET | Credential the server authenticates with. | Yes |
| GOOGLE_API_KEY | Credential the server authenticates with. | Yes |
| VERCEL_BLOB_TOKEN | Credential the server authenticates with. | Yes |
| AWS_ACCESS_KEY_ID | Credential the server authenticates with. | Yes |
| AWS_SECRET_ACCESS_KEY | Credential the server authenticates with. | Yes |
| STRIPE_SECRET_KEY | Credential the server authenticates with. | Yes |
| ZENODO_TOKEN | Credential the server authenticates with. | Yes |
| SUPABASE_URL | Endpoint or connection string the server talks to. | Yes |
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.