OnlineCyberTools MCP (280+ filterable tools)

seo_keyword_density_checker

Read-onlyIdempotent

Analyze plain text or HTML to detect keyword stuffing and repeated phrases. Get keyword density percentages, n-gram rankings, and over-optimization warnings for SEO content audit.

Instructions

SEO Keyword Density and N-gram Checker. Analyze plain text or HTML for keyword density and repeated phrases as an SEO content audit. Tokenizes the text (Unicode-aware, optional HTML tag/entity stripping, optional stopword removal) and returns the top unigrams, bigrams, and trigrams ranked by frequency, each with a density percentage, plus document stats (word/char/sentence/paragraph counts, unique words, lexical diversity) and over-optimization warnings when any term exceeds roughly 3-5% density. Use this when you need per-keyword and per-phrase density to detect keyword stuffing; use text_word_frequency for a plain single-word frequency list with no SEO density or n-gram analysis, text_text_statistics for readability/structure metrics without keyword ranking, seo_title_description_length_checker to validate title/meta length, and seo_meta_tag_generator to author the head tags. Runs locally on the text you provide: read-only, deterministic, non-destructive, contacts no external service, and is rate-limited (3

Input Schema

TableJSON Schema

Name	Required	Description	Default
`text`	Yes	Content to analyze: UTF-8 plain text, or an HTML document when mode is html. Must not be blank. Hard cap roughly 5 MB.
`mode`	No	Input format. plain analyzes text verbatim; html strips script/style/comments/tags and decodes entities before analysis. Unrecognized values fall back to plain.	plain
`stopwords`	No	Stopword filter for the unigram ranking and (when active) n-grams. en/english uses the built-in English list; none/off/empty disables filtering; an array of strings supplies a custom case-insensitive list. Any other string defaults to the English list.	en
`minLength`	No	Minimum token character length to include in rankings; shorter tokens are dropped. Clamped to 1-10.
`topN`	No	Maximum number of entries returned in each of the unigram, bigram, and trigram tables. Clamped to 1-100.
`operation`	No	Operation to run. Only analyze is supported.	analyze

Output Schema

TableJSON Schema

Name	Required	Description
`success`	No	Whether the analysis succeeded.
`operation`	No	The operation performed (analyze).
`result`	No	The keyword density analysis.

Schema Changelog

Changes observed during successful MCP inspections.

Changed20 schema fields changedv0.5.1Jun 3, 2026

addedInput schema / additionalProperties
```
Added value: +false
```
addedInput schema / properties / minLength / default
```
Added value: +3
```

addedInput schema / properties / minLength / description

Added value: +"Minimum token character length to include in rankings; shorter tokens are dropped. Clamped to 1-10."

addedInput schema / properties / minLength / maximum
```
Added value: +10
```
addedInput schema / properties / minLength / minimum
```
Added value: +1
```
addedInput schema / properties / mode / default
```
Added value: +"plain"
```

addedInput schema / properties / mode / description

Added value: +"Input format. plain analyzes text verbatim; html strips script/style/comments/tags and decodes entities before analysis. Unrecognized values fall back to plain."

addedInput schema / properties / mode / enum
```
Added value: +[
+  "plain",
+  "html"
+]
```

addedInput schema / properties / operation

Added value: +{
+  "default": "analyze",
+  "description": "Operation to run. Only analyze is supported.",
+  "enum": [
+    "analyze"
+  ],
+  "type": "string"
+}

addedInput schema / properties / stopwords / default
```
Added value: +"en"
```

addedInput schema / properties / stopwords / description

Added value: +"Stopword filter for the unigram ranking and (when active) n-grams. en/english uses the built-in English list; none/off/empty disables filtering; an array of strings supplies a custom case-insensitive list. Any other string defaults to the English list."

addedInput schema / properties / stopwords / items
```
Added value: +{
+  "type": "string"
+}
```

changedInput schema / properties / stopwords / type

Previous value: -"string"New value: +[
+  "array",
+  "string"
+]

addedInput schema / properties / text / description

Added value: +"Content to analyze: UTF-8 plain text, or an HTML document when mode is html. Must not be blank. Hard cap roughly 5 MB."

addedInput schema / properties / topN / default
```
Added value: +20
```

addedInput schema / properties / topN / description

Added value: +"Maximum number of entries returned in each of the unigram, bigram, and trigram tables. Clamped to 1-100."

addedInput schema / properties / topN / maximum
```
Added value: +100
```
addedInput schema / properties / topN / minimum
```
Added value: +1
```

changedInput schema / required

Previous value: -[
-  "text",
-  "mode",
-  "stopwords",
-  "minLength",
-  "topN"
-]New value: +[
+  "text"
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "operation": {
+      "description": "The operation performed (analyze).",
+      "type": "string"
+    },
+    "result": {
+      "description": "The keyword density analysis.",
+      "properties": {
+        "bigrams": {
+          "description": "Top two-word phrases by frequency, up to topN. Same item shape as unigrams.",
+          "items": {
+            "properties": {
+              "count": {
+                "description": "Number of occurrences.",
+                "type": "integer"
+              },
+              "density": {
+                "description": "Occurrences as a percentage of the density base (rounded to 2 dp).",
+                "type": "number"
+              },
+              "word": {
+                "description": "The two-word phrase.",
+                "type": "string"
+              }
+            },
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "stats": {
+          "description": "Document-level statistics for the cleaned text.",
+          "properties": {
+            "avgCharsPerWord": {
+              "description": "Mean characters per token (rounded to 2 dp).",
+              "type": "number"
+            },
+            "avgWordsPerSentence": {
+              "description": "Mean tokens per sentence (rounded to 2 dp).",
+              "type": "number"
+            },
+            "charCount": {
+              "description": "Total characters in the cleaned text.",
+              "type": "integer"
+            },
+            "charCountNoSpaces": {
+              "description": "Characters excluding spaces, tabs, and newlines.",
+              "type": "integer"
+            },
+            "lexicalDiversity": {
+              "description": "Unique words divided by total words (0-1, rounded to 4 dp).",
+              "type": "number"
+            },
+            "paragraphCount": {
+              "description": "Paragraphs (split on blank lines).",
+              "type": "integer"
+            },
+            "sentenceCount": {
+              "description": "Sentences (split on terminal . ! ? punctuation).",
+              "type": "integer"
+            },
+            "uniqueWords": {
+              "description": "Count of distinct tokens.",
+              "type": "integer"
+            },
+            "wordCount": {
+              "description": "Total tokens (words) found.",
+              "type": "integer"
+            }
+          },
+          "type": "object"
+        },
+        "trigrams": {
+          "description": "Top three-word phrases by frequency, up to topN. Same item shape as unigrams.",
+          "items": {
+            "properties": {
+              "count": {
+                "description": "Number of occurrences.",
+                "type": "integer"
+              },
+              "density": {
+                "description": "Occurrences as a percentage of the density base (rounded to 2 dp).",
+                "type": "number"
+              },
+              "word": {
+                "description": "The three-word phrase.",
+                "type": "string"
+              }
+            },
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "unigrams": {
+          "description": "Top single words by frequency (after stopword/minLength filtering), up to topN.",
+          "items": {
+            "properties": {
+              "count": {
+                "description": "Number of occurrences.",
+                "type": "integer"
+              },
+              "density": {
+                "description": "Occurrences as a percentage of filtered tokens (rounded to 2 dp).",
+                "type": "number"
+              },
+              "word": {
+                "description": "The word or phrase.",
+                "type": "string"
+              }
+            },
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "warnings": {
+          "description": "Over-optimization and quality notices (e.g. density too high, text too short, repetitive phrases).",
+          "items": {
+            "properties": {
+              "message": {
+                "description": "Human-readable explanation.",
+                "type": "string"
+              },
+              "severity": {
+                "description": "Warning severity.",
+                "enum": [
+                  "critical",
+                  "high",
+                  "medium",
+                  "low",
+                  "info"
+                ],
+                "type": "string"
+              }
+            },
+            "type": "object"
+          },
+          "type": "array"
+        }
+      },
+      "type": "object"
+    },
+    "success": {
+      "description": "Whether the analysis succeeded.",
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

First observedv0.1.0May 31, 2026

TDQS

A4.6/5.0

Behavior5/5

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

The description goes beyond annotations by stating that the tool is 'read-only, deterministic, non-destructive, contacts no external service, and is rate-limited.' It also outlines the tokenization process (Unicode-aware, optional stripping/stopword removal), adding valuable behavioral context that annotations alone do not provide.

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 informative yet efficient, covering purpose, usage, behavior, and parameter hints in a structured manner. It is slightly lengthy but every sentence adds value, so it earns a 4.

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 medium complexity and the presence of a comprehensive input schema and output schema (not shown but implied), the description covers all necessary aspects: input handling, processing details, output features, constraints, and sibling tool differentiation. It is fully 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?

Schema description coverage is 100%, so the schema already documents all parameters well. The description adds minimal extra semantic value for parameters (e.g., 'stopwords can be en, none, or custom array'), but it doesn't go into depth beyond what the schema provides, resulting in a baseline score of 3.

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 states the tool's purpose: 'Analyze plain text or HTML for keyword density and repeated phrases as an SEO content audit.' It distinguishes itself from sibling tools like text_word_frequency, text_text_statistics, seo_title_description_length_checker, and seo_meta_tag_generator, leaving no ambiguity about what it does.

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 explicitly tells when to use this tool ('when you need per-keyword and per-phrase density to detect keyword stuffing') and when to use alternatives (e.g., 'use text_word_frequency for a plain single-word frequency list'). This provides clear guidance for the agent.

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

Deploy Server