Skip to main content
Glama

URL Safety Validator MCP

by io.github.OjasKord
OverviewDiscussionsAdmin

Server Details

AI URL safety validator: SAFE/SUSPICIOUS/DANGEROUS verdict, trust score, threat intel.

Ownership verified
Status
Healthy
Last Tested
Transport
Streamable HTTP · MCP 2024-11-05
URL
Repository
OjasKord/url-safety-validator-mcp
GitHub Stars
1
Server Listing
url-safety-validator-mcp

TDQS

A4.6/5.0

Scored across 1 tool

Disambiguation5/5

There is only one tool, so there is no possibility of misselection or overlap with a sibling tool. Its purpose — validating a URL before navigation — is stated unambiguously in the description.

Naming Consistency5/5

check_url follows the standard verb_noun snake_case convention and reads clearly. With a single tool there is no competing convention to create inconsistency.

Tool Count4/5

One tool is genuinely well-matched to a narrowly scoped validator: a single call returns a verdict, trust score, and agent action, so no additional tools are needed. It is slightly under the 3-15 range the rubric favours, but nothing here is redundant or missing at the core.

Completeness4/5

The core lifecycle — submit URL, receive machine-ready verdict plus recommended action — is fully covered, and threat categories and live Google backends are exposed. Minor gaps remain: no batch/multi-URL checking, no way to re-validate downstream redirects or record allowlist/cache decisions for a session.

Available Tools

1 tool
check_urlAInspect

Checks a URL for phishing, malware, typosquatting, and redirect threats. Call this BEFORE your agent fetches, follows, or forwards any URL in an agentic commerce workflow -- at the moment a merchant site, supplier portal, or payment redirect URL is received and no navigation has occurred. Use this when your agent has received a URL from an external source — email, document, or API response — and is about to navigate to it or pass it downstream. Checks live against Google Web Risk (webrisk.googleapis.com) and Google Safe Browsing (safebrowsing.googleapis.com). Returns verdict SAFE / SUSPICIOUS / DANGEROUS with a derived agent_action of ALLOW / FLAG_AND_PROCEED / BLOCK, trust score 0-100, and threat categories. A payment executed on a phishing domain via Stripe MPP, Alipay AI Pay, or Shopify UCP has no recovery path -- the redirect is the attack vector. A DANGEROUS verdict means halt immediately. Returns machine-ready verdict, no further analysis needed.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesThe URL to check. Full URL preferred (e.g. https://example.com/path). Bare domains also accepted.

Output Schema

ParametersJSON Schema
NameRequiredDescription
urlYes
verdictYes
hostnameYes
reasoningNo
ssl_validNo
checked_atYes
source_urlNo
_disclaimerYes
hold_reasonNoPresent only when verdict is SUSPICIOUS
retry_afterNo
trust_scoreYes
agent_actionYesDerived directly from verdict
ai_confidenceNo
analysis_typeNo
domain_age_daysNo
escalation_pathNoPresent only when verdict is SUSPICIOUS
database_signalsNo
domain_registeredNo
threat_categoriesNo
redirect_chain_detectedNo

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full transparency burden. It discloses live checks against Google Web Risk and Safe Browsing, specifies the return contract (verdict, agent_action, trust score, threat categories), and instructs halting on DANGEROUS. This is thorough and non-misleading for a read-only security check.

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

Conciseness4/5

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

The description is front-loaded with the core purpose and uses a clear progression from what → when → how → output. It is slightly verbose with overlapping 'before' usage guidance, but each sentence provides useful operational context for a security-sensitive tool.

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?

Given that an output schema exists, the description need not detail the return structure, yet it still summarizes verdicts, action, and trust score. It covers when, why, what, and the operational safety rule, making it complete for agent selection and invocation.

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?

The input schema provides 100% coverage for the single URL parameter, including preference for full URLs. The description adds no additional parameter-level semantics beyond the schema, so the baseline score of 3 is appropriate.

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?

The description opens with a specific verb 'Checks' and explicitly enumerates the threat types (phishing, malware, typosquatting, redirect threats). It clearly identifies the tool's function and is unambiguous even without sibling tool comparison.

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

Usage Guidelines5/5

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

The description gives explicit when-to-use guidance: before fetching, following, or forwarding any URL in an agentic commerce workflow, with concrete trigger contexts (email, document, API response). It also implies when not to use (after navigation) and emphasizes the urgency with a recovery-path rationale.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool update
    • Changedcheck_url1 field changed
      • changedOutput schema / (root)
        Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "_disclaimer": {
+      "type": "string"
+    },
+    "agent_action": {
+      "description": "Derived directly from verdict",
+      "enum": [
+        "ALLOW",
+        "FLAG_AND_PROCEED",
+        "BLOCK"
+      ],
+      "type": "string"
+    },
+    "ai_confidence": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "analysis_type": {
+      "type": "string"
+    },
+    "checked_at": {
+      "format": "date-time",
+      "type": "string"
+    },
+    "database_signals": {
+      "type": "object"
+    },
+    "domain_age_days": {
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "domain_registered": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "escalation_path": {
+      "description": "Present only when verdict is SUSPICIOUS",
+      "type": "string"
+    },
+    "hold_reason": {
+      "description": "Present only when verdict is SUSPICIOUS",
+      "type": "string"
+    },
+    "hostname": {
+      "type": "string"
+    },
+    "reasoning": {
+      "type": "string"
+    },
+    "redirect_chain_detected": {
+      "type": "boolean"
+    },
+    "retry_after": {
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "source_url": {
+      "type": "string"
+    },
+    "ssl_valid": {
+      "type": "boolean"
+    },
+    "threat_categories": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "trust_score": {
+      "maximum": 100,
+      "minimum": 0,
+      "type": "number"
+    },
+    "url": {
+      "type": "string"
+    },
+    "verdict": {
+      "enum": [
+        "SAFE",
+        "SUSPICIOUS",
+        "DANGEROUS"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "url",
+    "hostname",
+    "verdict",
+    "agent_action",
+    "trust_score",
+    "checked_at",
+    "_disclaimer"
+  ],
+  "type": "object"
+}

Related MCP Connectors

Related MCP Servers

  • trust-score

    Br0ski777
    A
    license
    Not graded
    quality
    B
    maintenance
    Provides AI agents with zero-cost, zero-dependency trust evaluation for domains, URLs, wallets, APIs, and IPs, returning a 0-100 score with SSL, DNS, WHOIS, security header, and content sub-scores, plus batch comparison to rank multiple targets.
    MIT

  • unphurl-mcp

    123Ergo
    A
    license
    A
    quality
    D
    maintenance
    URL intelligence for AI agents. One URL in, structured security and data quality signals out across 7 dimensions. 13 tools, risk score 0-100 with 23 configurable weights.
    16
    63 npm
    1
    MIT

  • ScamVerify

    scamverifyai
    A
    license
    A
    quality
    F
    maintenance
    AI-powered threat verification across 6 channels: phone numbers, URLs, text messages, emails, documents, and QR codes. Analyzes threats against 10M+ intelligence records from FTC, FCC, URLhaus, ThreatFox, and community reports, returning risk scores, verdicts, and detailed signals.
    10
    1
    MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources