Skip to main content
Glama

Virustotal

by io.github.pipeworx-io

Lookup Url

lookup_url
Read-onlyIdempotent

Look up a URL's reputation. Returns last-analysis stats across all engines, categories (per vendor), and whether the URL has been redirected. The URL is canonicalized before lookup; no submission step is required to read existing reports.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesFull URL including scheme

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesVirusTotal URL identifier
tagsYesTags assigned to the URL
typeYesResource type (e.g., 'urls')
statsYes
vt_urlYesDirect link to VirusTotal URL report
reputationYesReputation score from community
raw_attributesYesFull attributes object from VirusTotal API
community_votesYes
last_analyzed_atYesISO 8601 timestamp of last analysis

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "url": "https://example.com/malware"
+  },
+  {
+    "url": "http://suspicious-domain.net/phishing-page"
+  }
+]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "community_votes": {
+      "properties": {
+        "harmless": {
+          "description": "Community votes for harmless",
+          "type": "integer"
+        },
+        "malicious": {
+          "description": "Community votes for malicious",
+          "type": "integer"
+        }
+      },
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "id": {
+      "description": "VirusTotal URL identifier",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "last_analyzed_at": {
+      "description": "ISO 8601 timestamp of last analysis",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "raw_attributes": {
+      "description": "Full attributes object from VirusTotal API",
+      "type": "object"
+    },
+    "reputation": {
+      "description": "Reputation score from community",
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "stats": {
+      "properties": {
+        "harmless": {
+          "description": "Number of engines detecting as harmless",
+          "type": "integer"
+        },
+        "malicious": {
+          "description": "Number of engines detecting as malicious",
+          "type": "integer"
+        },
+        "malicious_pct": {
+          "description": "Percentage of engines detecting as malicious",
+          "type": "number"
+        },
+        "suspicious": {
+          "description": "Number of engines detecting as suspicious",
+          "type": "integer"
+        },
+        "total_engines": {
+          "description": "Total engines that analyzed the URL",
+          "type": "integer"
+        },
+        "undetected": {
+          "description": "Number of engines with no detection",
+          "type": "integer"
+        }
+      },
+      "required": [
+        "malicious",
+        "suspicious",
+        "harmless",
+        "undetected",
+        "total_engines",
+        "malicious_pct"
+      ],
+      "type": "object"
+    },
+    "tags": {
+      "description": "Tags assigned to the URL",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "type": {
+      "description": "Resource type (e.g., 'urls')",
+      "type": "string"
+    },
+    "vt_url": {
+      "description": "Direct link to VirusTotal URL report",
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "type",
+    "id",
+    "stats",
+    "reputation",
+    "community_votes",
+    "tags",
+    "last_analyzed_at",
+    "raw_attributes",
+    "vt_url"
+  ],
+  "type": "object"
+}
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Adds behavioral details beyond annotations: URL is canonicalized, no submission required, returns last-analysis stats. Consistent with readOnlyHint and idempotentHint annotations. No contradictions.

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?

Three sentence description is front-loaded with purpose, no extraneous details. Every sentence adds value.

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

Completeness5/5

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

For a single-parameter lookup tool with output schema, description fully covers purpose, behavior, and user expectations. No missing context.

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

Parameters4/5

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

Schema coverage is 100% with a clear description of 'url' parameter. Description adds meaning: canonicalization implies URL normalization, which is not in schema.

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

Purpose5/5

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

Description explicitly states purpose: 'Look up a URL's reputation.' It details return values (stats, categories, redirect info) and distinguishes from siblings (e.g., lookup_domain, lookup_file) by specifying URL-specific behavior.

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

Usage Guidelines4/5

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

Clear context: this is a read-only lookup for existing reports, with no submission step. Does not explicitly exclude cases or name alternative tools, but sibling list implies other tools for different entity types.

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

All Virustotal toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation2/5

The set mixes several overlapping families: ask_pipeworx and ask_pipeworx_beta are described as currently identical, while ask_pipeworx_grounded, deep_research, bet_research, and validate_claim all route to the same underlying data sources. Polymarket tools (arbitrage, edges, edge_tracker, fill_risk, spread) also blur together; only the four lookup_* VirusTotal functions are cleanly distinct.

Naming Consistency3/5

Names are uniformly snake_case with a few consistent families (lookup_domain/file/ip/url, ask_pipeworx_*, polymarket_*), which helps. However, the set mixes imperative verbs (remember, forget, subscribe, validate_claim), noun phrases (entity_profile, deep_research, recent_alerts), and inconsistent prefixes, so no single naming convention holds across the server.

Tool Count2/5

35 tools is too many for the apparent purpose, especially for a server named Virustotal. The bulk of the tools address unrelated Pipeworx research, memory, and prediction-market functions, so the count does not reflect the server's advertised domain.

Completeness1/5

For a VirusTotal server, only four lookup tools exist and there is no way to submit a URL/file, create a scan, retrieve analysis details, or explore relationships—core VirusTotal operations are missing. Scoped broadly, the unrelated Pipeworx tools are extensive, but they do not fill the gaps in the advertised domain. The surface is severely incomplete relative to the server name.

Resources