opticparse
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPTICPARSE_API_KEY | Yes | Your OpticParse API key, required for authentication when using the MCP server. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| opticparse_scrapeB | Extract structured, token-optimized data from any live web page using AI Multimodal Vision. Bypasses Cloudflare Turnstile, anti-bot mechanisms, and dynamic JavaScript rendering without brittle CSS selectors. Perfect for LLM context windows and RAG pipelines. |
| phishvision_detectA | Audit and inspect any URL for real-time zero-day phishing campaigns, smart contract wallet drainers, credential harvesting kits, and brand impersonation attacks using visual layout heuristics in under 1.6 seconds. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| OpticParse & PhishVision Capabilities | Live status and supported extraction models and threat heuristics |
TDQS
Scored across 2 tools
opticparse_scrape extracts page content for LLM/RAG use, while phishvision_detect audits URLs for security threats. Their purposes, outputs, and trigger conditions are clearly distinct, so an agent should not confuse them.
Both names follow a product_verb pattern and use snake_case, but the product prefix changes from opticparse to phishvision. This breaks the expected consistency for a server named opticparse and makes the second tool feel unrelated.
Two tools is on the thin side for a server that claims to cover web scraping and phishing detection. Each tool serves a distinct high-level purpose, but the overall surface feels minimal rather than well-rounded.
The two tools cover the core stated capabilities: extracting structured page data and detecting phishing URLs. However, there are notable gaps such as no batch processing, no non-URL input support, and no way to refine or iterate on extraction results.