OnlineCyberTools MCP (280+ filterable tools)

data_data_anonymizer

Read-onlyIdempotent

Detect and mask personally identifiable information (PII) like emails, phone numbers, SSNs, IBANs, and credit cards in free text. Returns masked text with per-occurrence replacements.

Instructions

PII Data Anonymizer and Redactor. Detect and mask personally identifiable information (emails, phone numbers, US SSNs, IBANs with mod-97 check, Luhn-validated credit cards, IPv4/IPv6 addresses, ISO-8601 dates) in free text. Use this to scrub or redact real PII from logs, tickets, or datasets; use data_data_faker instead when you need to generate brand-new synthetic test data rather than mask existing values. Detection is regex-based with validity checks, and longer or stricter patterns (credit card, IBAN) resolve ahead of shorter ones (phone, SSN) so values are never partially matched. Runs locally on the text you provide: read-only, non-destructive, contacts no external service, deterministic for a given input, and rate-limited (60 requests/minute for anonymous callers). Returns the masked text plus a per-occurrence replacement list and per-type match counts.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`text`	Yes	Text to scan for PII. Maximum 1000000 characters; longer input is rejected.
`mask`	No	Masking mode. token replaces each match with a bracketed type label; partial redacts the middle and keeps a few leading and trailing characters; counter substitutes per-type sequential ids such as email-1.	token
`enable`	No	Per-type detection toggles; each key defaults to true (detected) when omitted. Set a key to false to skip that PII type.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`success`	No	Whether anonymization succeeded.
`result`	No	The anonymization output.

Schema Changelog

Changes observed during successful MCP inspections.

Changed17 schema fields changedv0.5.1Jun 3, 2026

addedInput schema / additionalProperties
```
Added value: +false
```
addedInput schema / properties / enable / additionalProperties
```
Added value: +false
```

addedInput schema / properties / enable / description

Added value: +"Per-type detection toggles; each key defaults to true (detected) when omitted. Set a key to false to skip that PII type."

addedInput schema / properties / enable / properties / cc / description
```
Added value: +"Detect credit card numbers (Luhn validated)."
```
addedInput schema / properties / enable / properties / date / description
```
Added value: +"Detect ISO-8601 dates."
```
addedInput schema / properties / enable / properties / email / description
```
Added value: +"Detect email addresses."
```
addedInput schema / properties / enable / properties / iban / description
```
Added value: +"Detect IBAN account numbers (mod-97 validated)."
```
addedInput schema / properties / enable / properties / ip / description
```
Added value: +"Detect IPv4 and IPv6 addresses."
```
addedInput schema / properties / enable / properties / phone / description
```
Added value: +"Detect NANP or E.164 phone numbers."
```
addedInput schema / properties / enable / properties / ssn / description
```
Added value: +"Detect US Social Security Numbers."
```

removedInput schema / properties / enable / required

Removed value: -[
-  "email",
-  "phone",
-  "ssn",
-  "iban",
-  "cc",
-  "ip",
-  "date"
-]

addedInput schema / properties / mask / default
```
Added value: +"token"
```

addedInput schema / properties / mask / description

Added value: +"Masking mode. token replaces each match with a bracketed type label; partial redacts the middle and keeps a few leading and trailing characters; counter substitutes per-type sequential ids such as email-1."

addedInput schema / properties / mask / enum

Added value: +[
+  "token",
+  "partial",
+  "counter"
+]

addedInput schema / properties / text / description

Added value: +"Text to scan for PII. Maximum 1000000 characters; longer input is rejected."

changedInput schema / required

Previous value: -[
-  "text",
-  "mask",
-  "enable"
-]New value: +[
+  "text"
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "result": {
+      "description": "The anonymization output.",
+      "properties": {
+        "anonymized": {
+          "description": "The text with all detected PII replaced.",
+          "type": "string"
+        },
+        "counts": {
+          "description": "Count of matches per PII type.",
+          "properties": {
+            "cc": {
+              "description": "Credit card matches.",
+              "type": "integer"
+            },
+            "date": {
+              "description": "Date matches.",
+              "type": "integer"
+            },
+            "email": {
+              "description": "Email matches.",
+              "type": "integer"
+            },
+            "iban": {
+              "description": "IBAN matches.",
+              "type": "integer"
+            },
+            "ip": {
+              "description": "IP matches.",
+              "type": "integer"
+            },
+            "phone": {
+              "description": "Phone matches.",
+              "type": "integer"
+            },
+            "ssn": {
+              "description": "SSN matches.",
+              "type": "integer"
+            }
+          },
+          "type": "object"
+        },
+        "mask": {
+          "description": "The masking mode applied (token, partial, or counter).",
+          "type": "string"
+        },
+        "replacements": {
+          "description": "One entry per replaced match, in input order.",
+          "items": {
+            "properties": {
+              "offset": {
+                "description": "Zero-based start index of the match in the original text.",
+                "type": "integer"
+              },
+              "original": {
+                "description": "The matched substring before masking.",
+                "type": "string"
+              },
+              "replacement": {
+                "description": "The value it was replaced with.",
+                "type": "string"
+              },
+              "type": {
+                "description": "PII type (email, phone, ssn, iban, cc, ip, or date).",
+                "type": "string"
+              }
+            },
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "text": {
+          "description": "The original submitted text, echoed back.",
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "success": {
+      "description": "Whether anonymization succeeded.",
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

First observedv0.1.0May 31, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Beyond the annotations (readOnlyHint, destructiveHint, idempotentHint), the description discloses critical behavioral traits: regex-based detection with validity checks, a specific resolution order for longer/stricter patterns to avoid partial matches, local execution without external services, rate limits (60 req/min for anonymous), and return format (masked text, replacement list, match counts). This fully informs the agent about how the tool behaves.

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 dense yet concise, front-loading purpose and detected types, then transitioning to usage guidance and technical details. Every sentence contributes meaningful information without redundancy. It is well-structured for an AI agent to quickly parse.

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 the tool's moderate complexity (3 parameters, output schema present), the description covers all essential aspects: purpose, usage context, detection details, operational constraints, and return format. The annotations further complete the behavioral profile, making the tool fully comprehensible.

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?

The input schema has 100% coverage, so the description's parameter details are supplementary. It clearly explains each mask mode (token, partial, counter) with examples, and describes the enable object's default behavior (all types on). This adds value beyond the schema's descriptions, though the schema already provides formal definitions.

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 clearly identifies the tool as a PII Data Anonymizer and Redactor, lists specific PII types detected, and explicitly distinguishes itself from the sibling tool 'data_data_faker' which generates new synthetic data rather than masking existing values.

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 provides explicit guidance on when to use this tool ('scrub or redact real PII from logs, tickets, or datasets') and when to use the alternative ('data_data_faker' for generating synthetic test data). It also notes that the tool runs locally, is read-only, non-destructive, deterministic, and rate-limited, giving the agent clear operational context.

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

Deploy Server