Skip to main content
Glama
KasperskyLab

Kaspersky OpenTIP MCP Server

Official
by KasperskyLab

search_url

Read-only

Check URLs for security threats using Kaspersky's threat intelligence database to identify malicious websites and protect against cyber risks.

Instructions

Get threat intelligence data about a URL

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The MCP tool handler for 'search_url', including registration decorator @mcp.tool(), type signature, docstring, and core logic to query the OpenTIP API endpoint for threat intelligence on the provided URL.
    @mcp.tool(
        description="Get threat intelligence data about a URL",
        annotations=ToolAnnotations(
            title="Investigate a URL",
            readOnlyHint=True,
            openWorldHint=True,
        ),
    )
    async def search_url(url: str) -> dict[str, Any] | None:
        """Get threat intelligence data about a URL
    
        Args:
            url: the web address that you want to investigate
        """
        params = {"request": url}
        return await opentip_request(Endpoints.search_url, "get", params)
  • StrEnum defining API endpoints used by tools, specifically Endpoints.search_url = 'search/url' for the search_url tool.
    class Endpoints(StrEnum):
        search_hash = "search/hash"
        search_ip = "search/ip"
        search_domain = "search/domain"
        search_url = "search/url"
        analyze_file = "scan/file"
        get_analysis_results = "getresult/file"
  • Supporting utility function opentip_request that performs HTTP requests to the OpenTIP API, handles errors, and is called by the search_url handler.
    async def opentip_request(
        endpoint: str,
        request_type: RequestType = "get",
        params: Optional[dict[str, Any]] = None,
        content: Optional[bytes] = None,
        headers: Optional[dict[str, str]] = None,
    ) -> dict[str, Any]:
        """Make a request to the OpenTIP API with proper error handling."""
        headers = headers or {}
        headers = {
            "user-agent": "opentip-mcp-client",
            "x-api-key": OPENTIP_API_KEY,
            **headers
        }
    
        async with httpx.AsyncClient() as client:
            try:
                url = f"{OPENTIP_API_BASE}{endpoint}"
                if request_type == "get":
                    response = await client.get(
                        url, headers=headers, params=params, timeout=OPENTIP_API_TIMEOUT
                    )
                elif request_type == "post":
                    response = await client.post(
                        url, headers=headers, params=params, content=content, timeout=OPENTIP_API_TIMEOUT
                    )
                response.raise_for_status()
                return response.json()
            except httpx.HTTPStatusError as e:
                if e.response.status_code == 400:
                    return {"result": "error", "error_message": "Invalid parameters. Please check your input and try again."}
                elif e.response.status_code == 401:
                    return {"result": "error", "error_message": "Authentication failed. Please ensure that you have provided the correct credentials and try again."}
                elif e.response.status_code == 403:
                    return {"result": "error", "error_message": "Quota or request limit exceeded. Check your quota and limits and try again."}
                else:
                    return {"result": "error", "error_message": str(e)}
            except Exception as e:  # noqa
                return {"result": "error", "error_message": str(e)}
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, indicating safe, open-ended queries. The description adds minimal behavioral context beyond this, specifying the data type ('threat intelligence') but not detailing rate limits, auth needs, or response formats. It doesn't contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero waste. It's front-loaded with the core purpose, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (1 parameter), annotations covering safety and scope, and an output schema (which handles return values), the description is reasonably complete. It could improve with more param details or usage guidelines, but it's adequate for basic understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the schema provides no param details. The description mentions 'URL' but doesn't elaborate on format, constraints, or examples. It adds some meaning by linking the parameter to threat intelligence, but doesn't fully compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('Get') and resource ('threat intelligence data about a URL'). It distinguishes from siblings like search_domain or search_ip by specifying URL as the target, though it doesn't explicitly contrast them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context (investigating URLs for threats) but provides no explicit guidance on when to use this tool versus alternatives like search_domain or search_hash. It lacks prerequisites, exclusions, or comparative advice.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/KasperskyLab/threat-intelligence'

If you have feedback or need assistance with the MCP directory API, please join our Discord server