Extract structured JSON from any website using Edge AI. Bypasses all anti-bot protections automatically.
Scored across 2 tools
The two tools have completely distinct purposes: one for scraping web content and the other for phishing detection. There is no overlap or ambiguity in their responsibilities, making misselection unlikely.
Both tools follow a similar pattern of a product prefix followed by an action (opticparse_scrape, phishvision_detect). The naming is internally consistent, though it deviates from the conventional verb_noun pattern in favor of descriptive brand-based names.
With only 2 tools, the server feels minimal for the broad claim of 'Edge AI Scrape' plus phishing detection. The count is borderline acceptable for a niche server, but it lacks the depth typically seen in a full-featured server.
Each tool covers a core action (scraping and detection) but there are no supporting tools for scheduling, batch processing, or result management. For the stated purpose of providing AI scrapes and phishing audits, the surface is functional but notably sparse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| target_url | Yes | The fully-qualified HTTP/HTTPS URL of the webpage to scrape and extract content from. | |
| response_schema | No | Optional JSON Schema definition to enforce a strict structured output format on the extracted result. | |
| extraction_query | Yes | Natural language instructions specifying what data fields, tables, or text to extract from the webpage. |
| Name | Required | Description |
|---|---|---|
| content | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: it bypasses Cloudflare Turnstile and anti-bot mechanisms, uses AI Multimodal Vision, and is optimized for LLM context windows and RAG pipelines. This goes beyond the annotations and helps the agent understand the tool's capabilities and limitations. It doesn't mention rate limits or potential failures, but the added context is substantial.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with zero waste. It front-loads the core purpose, then adds the key differentiators (bypassing anti-bot, no CSS selectors, token-optimized). Every sentence earns its place, and the marketing-style language is efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has an output schema, so return values are covered. The description explains the input parameters well through the schema, and the behavioral context (bypassing anti-bot, using vision) is sufficient for an agent to decide whether to use it. It doesn't mention edge cases like non-JavaScript pages or paywalls, but for a scraping tool with this complexity, the description is complete enough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all three parameters. The description adds context about the extraction_query being natural language instructions and the response_schema enforcing structured output, but it doesn't add significant new meaning beyond the schema. Baseline 3 is appropriate since the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: extracting structured, token-optimized data from live web pages using AI Multimodal Vision. It names the specific resource (live web page) and the action (extract structured data), and distinguishes itself from brittle CSS selectors. The sibling tool phishvision_detect is different enough that this description makes the purpose clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use this tool: when you need to extract data from a live web page, especially one protected by anti-bot mechanisms or dynamic JavaScript rendering. It doesn't explicitly state when not to use it or name alternatives, but the context is clear. The sibling tool phishvision_detect is not mentioned, so no explicit exclusion is given, but the use case is well-defined.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The target domain or fully qualified URL to audit for security threats, drainers, and malicious vectors. |
| Name | Required | Description |
|---|---|---|
| content | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, covering the safety profile. The description adds valuable behavioral context beyond these: a performance guarantee ('under 1.6 seconds') and the underlying mechanism ('visual layout heuristics'), plus the 'real-time' nature of detection. This helps the agent set expectations without redundancy.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that front-loads the core purpose ('Audit and inspect any URL') before enumerating threat categories and constraints. It is reasonably concise and information-dense, but the long list of threats and modifiers makes it slightly run-on; still, every part earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a single parameter, high schema coverage, rich annotations, and an output schema, so the description need not explain return values. It covers purpose, threats, method, and performance, leaving no critical operational gap for an agent to call the tool correctly. It could mention output format or edge cases, but the existing structured data compensates.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage for the single parameter is 100%, so the baseline is 3. The description adds meaningful semantic detail beyond the schema by enumerating the specific attack categories the URL is checked against (phishing campaigns, smart contract wallet drainers, credential harvesting kits, brand impersonation) and the method, giving the agent a richer understanding of what the parameter is used for and what results to expect.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('audit and inspect') and the resource ('any URL'), listing specific threat categories (zero-day phishing, wallet drainers, credential harvesting kits, brand impersonation) and the method (visual layout heuristics). It is specific and actionable, though it does not explicitly distinguish itself from the sibling tool opticparse_scrape, so it misses the top score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for security auditing of URLs by its explicit threat-focused wording, but it provides no 'when to use vs. when not' guidance, no exclusions, and no reference to the sibling tool opticparse_scrape. The context makes the intended use fairly clear, but the agent is left to infer when to prefer this tool over alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
opticparse_scrape1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "content": {
+ "items": {
+ "properties": {
+ "text": {
+ "type": "string"
+ },
+ "type": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "type",
+ "text"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "content"
+ ],
+ "type": "object"
+}phishvision_detect1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "content": {
+ "items": {
+ "properties": {
+ "text": {
+ "type": "string"
+ },
+ "type": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "type",
+ "text"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "content"
+ ],
+ "type": "object"
+}opticparse_scrapephishvision_detect
Add one secure layer between your agents and this server.