AgentRender
# AgentRender MCP
<p align="center">
<img src="https://raw.githubusercontent.com/corbinvachal48/agentrender-mcp/main/assets/logo.png" alt="AgentRender" width="160" height="160" />
</p>
[](https://mcpservers.org/servers/agentrenderapi-com) [](https://glama.ai/mcp/servers/corbinvachal48/agentrender-mcp)
**URL → screenshot, PDF, or structured extract for AI agents** via [MCP](https://modelcontextprotocol.io) (stdio) + REST.
- Site: https://agentrenderapi.com
- API: https://api.agentrenderapi.com
Tools: `screenshot` · `pdf` · `extract`
## Install
```bash
pip install agentrender-mcp
# or from this repo:
pip install .
```
Requires an AgentRender API key (`akr_…`) from https://agentrenderapi.com (free waitlist path or paid Starter $17 / Growth $79 / Scale $259).
## Environment
| Variable | Default | Purpose |
|----------|---------|---------|
| `AGENTRENDER_API_KEY` | _(required)_ | Bearer API key |
| `AGENTRENDER_BASE_URL` | `https://api.agentrenderapi.com` | API base |
## Run (stdio)
```bash
export AGENTRENDER_API_KEY=akr_your_key
agentrender-mcp
# or: python -m agentrender_mcp.server
```
## Cursor / Claude Desktop
```json
{
"mcpServers": {
"agentrender": {
"command": "agentrender-mcp",
"env": {
"AGENTRENDER_API_KEY": "akr_your_key",
"AGENTRENDER_BASE_URL": "https://api.agentrenderapi.com"
}
}
}
}
```
If `agentrender-mcp` is not on `PATH`, use your Python:
```json
{
"mcpServers": {
"agentrender": {
"command": "python",
"args": ["-m", "agentrender_mcp.server"],
"env": {
"AGENTRENDER_API_KEY": "akr_your_key"
}
}
}
}
```
## Tools
| Tool | Maps to | Notes |
|------|---------|--------|
| `screenshot` | `POST /v1/screenshot` | PNG/JPEG/WebP; returns `image_base64` + receipt |
| `pdf` | `POST /v1/pdf` | Returns `pdf_base64` + receipt |
| `extract` | `POST /v1/extract` | Title, meta, canonical, text, links (non-LLM) |
## REST smoke
```bash
curl -s https://api.agentrenderapi.com/health
curl -s -X POST https://api.agentrenderapi.com/v1/extract \
-H "Authorization: Bearer $AGENTRENDER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"url":"https://example.com"}'
```
## Notes
- Hosted Streamable HTTP MCP is not shipped in this package yet; use stdio as above.
- Do not commit API keys. Rotate any key that leaks.
- Support: hello@agentrenderapi.com
## License
MIT
<!-- mcp-name: io.github.corbinvachal48/agentrender-mcp -->
TDQS
Scored across 3 tools
Each tool captures a distinct output format from a URL: PDF, image, or extracted text/metadata. There is no overlap in purpose, so an agent can easily select the correct tool without ambiguity.
All tool names are single, lowercase verbs describing the action ('pdf', 'extract', 'screenshot'). While not verb_noun, the pattern is perfectly consistent and intuitive.
With 3 tools covering URL rendering to PDF, image, and text extraction, the count is well-scoped for a focused utility server. Each tool serves a clear purpose without bloat.
The set covers the primary content-capture needs (PDF, image, text extraction). Missing minor capabilities like full HTML or raw response capture, but the core workflows for a render/capture service are complete.