Residential-Chrome render_page, token_verdict, multi-source research. Free tier.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Free API key — auto-provisioned by the stdio wrapper, or GET /mcp/key
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Render a JavaScript-heavy page with real headless Chrome on a residential IP and return title, meta, headings, main text and top links. Passes anti-bot walls that block datacenter scrapers.
Public http(s) URL to render
Extra settle wait after load (300-5000, default 900)
Max text chars to return (1000-80000, default 40000)
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http jarvis-tools https://jarvis-proxy.jarvis-studio.workers.dev/mcp
Headers
X-API-Key (optional, not in the config above): Free API key — auto-provisioned by the stdio wrapper, or GET /mcp/keyRender a JavaScript-heavy page with real headless Chrome on a residential IP and return title, meta, headings, main text and top links. Passes anti-bot walls that block datacenter scrapers.
| Argument | Type | Description |
|---|---|---|
| url* | string | Public http(s) URL to render |
| wait_ms | number | Extra settle wait after load (300-5000, default 900) |
| max_chars | number | Max text chars to return (1000-80000, default 40000) |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Public http(s) URL to render"
},
"wait_ms": {
"type": "number",
"description": "Extra settle wait after load (300-5000, default 900)"
},
"max_chars": {
"type": "number",
"description": "Max text chars to return (1000-80000, default 40000)"
}
}
}Multi-source web research: GitHub repos, Hacker News, Wikipedia, arXiv — merged and deduplicated with source labels.
| Argument | Type | Description |
|---|---|---|
| limit | number | Max results (default 10, max 20) |
| query* | string | Search query |
| sources | array | github|hn|wikipedia|arxiv (default all) |
{
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "number",
"description": "Max results (default 10, max 20)"
},
"query": {
"type": "string",
"description": "Search query"
},
"sources": {
"type": "array",
"items": {
"type": "string"
},
"description": "github|hn|wikipedia|arxiv (default all)"
}
}
}Deterministic security verdict for an EVM token (SAFE/CAUTION/DANGER + score 0-100) from GoPlus Security and DexScreener: honeypot, mintable, hidden owner, taxes, liquidity, top holders. Batch up to 50 addresses.
| Argument | Type | Description |
|---|---|---|
| chain | string | base|ethereum|bsc|polygon|arbitrum|optimism|avalanche (default base) |
| addresses | array | Batch mode: up to 50 addresses |
| token_address | string | 0x token contract address |
{
"type": "object",
"properties": {
"chain": {
"type": "string",
"description": "base|ethereum|bsc|polygon|arbitrum|optimism|avalanche (default base)"
},
"addresses": {
"type": "array",
"items": {
"type": "string"
},
"description": "Batch mode: up to 50 addresses"
},
"token_address": {
"type": "string",
"description": "0x token contract address"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 22, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.