OnlineCyberTools MCP (280+ filterable tools)

text_text_splitter

Read-onlyIdempotent

Split text into an array using line, word, character, delimiter, or regex methods. Optionally trim parts, drop empty entries, and limit splits.

Instructions

Text Splitter. Split one string into an array of parts using a chosen method: by lines, by words (whitespace runs), by individual characters, by a literal delimiter, or by a regular expression. Optionally trim each part, drop empty parts, and cap the number of splits. Use this to break a string apart; use text_joiner for the inverse (merging items into one string), text_statistics for whole-text metrics without splitting, and column_tool for aligning delimited tabular data. Pure local compute: read-only, non-destructive, offline, deterministic, and rate-limited (60 requests/min for anonymous callers). Returns the parts array plus original/result length statistics and the effective settings.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`text`	Yes	The text to split. Required and must be non-empty; a blank value returns a 400 error.
`splitType`	No	Split method. lines splits on newlines; words on whitespace runs; characters into single chars; delimiter on the literal delimiter value; regex on the regex pattern.	lines
`delimiter`	No	Literal delimiter used only when splitType is delimiter; an empty string returns the text unsplit.	,
`regex`	No	Pattern used only when splitType is regex; accepts a bare pattern or PHP-style /pattern/flags; an empty string returns the text unsplit.
`removeEmpty`	No	Drop empty parts after splitting (for characters mode, also drops spaces).
`trimElements`	No	Trim leading/trailing whitespace from each part (ignored for characters mode).
`maxSplits`	No	Maximum number of splits for delimiter/regex modes; 0 means no limit. Ignored for lines/words/characters.

Output Schema

TableJSON Schema

Name	Required	Description
`success`	No	Always true on success.
`result`	No	The resulting parts after splitting and applying remove-empty/trim options.
`stats`	No	Metrics for the original text and the result.
`options`	No	The effective options echoed in camelCase.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.5.1Jun 3, 2026

changedInput schema / additionalProperties
```
Previous value: -trueNew value: +false
```

addedInput schema / properties

Added value: +{
+  "delimiter": {
+    "default": ",",
+    "description": "Literal delimiter used only when splitType is delimiter; an empty string returns the text unsplit.",
+    "type": "string"
+  },
+  "maxSplits": {
+    "default": 0,
+    "description": "Maximum number of splits for delimiter/regex modes; 0 means no limit. Ignored for lines/words/characters.",
+    "minimum": 0,
+    "type": "integer"
+  },
+  "regex": {
+    "default": "",
+    "description": "Pattern used only when splitType is regex; accepts a bare pattern or PHP-style /pattern/flags; an empty string returns the text unsplit.",
+    "type": "string"
+  },
+  "removeEmpty": {
+    "default": true,
+    "description": "Drop empty parts after splitting (for characters mode, also drops spaces).",
+    "type": "boolean"
+  },
+  "splitType": {
+    "default": "lines",
+    "description": "Split method. lines splits on newlines; words on whitespace runs; characters into single chars; delimiter on the literal delimiter value; regex on the regex pattern.",
+    "enum": [
+      "lines",
+      "words",
+      "characters",
+      "delimiter",
+      "regex"
+    ],
+    "type": "string"
+  },
+  "text": {
+    "description": "The text to split. Required and must be non-empty; a blank value returns a 400 error.",
+    "type": "string"
+  },
+  "trimElements": {
+    "default": true,
+    "description": "Trim leading/trailing whitespace from each part (ignored for characters mode).",
+    "type": "boolean"
+  }
+}

addedInput schema / required
```
Added value: +[
+  "text"
+]
```

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "options": {
+      "description": "The effective options echoed in camelCase.",
+      "properties": {
+        "delimiter": {
+          "description": "Delimiter used.",
+          "type": "string"
+        },
+        "maxSplits": {
+          "description": "Split cap applied.",
+          "type": "integer"
+        },
+        "regex": {
+          "description": "Regex pattern used.",
+          "type": "string"
+        },
+        "removeEmpty": {
+          "description": "Whether empty parts were dropped.",
+          "type": "boolean"
+        },
+        "splitType": {
+          "description": "Split method used.",
+          "type": "string"
+        },
+        "trimElements": {
+          "description": "Whether parts were trimmed.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "result": {
+      "description": "The resulting parts after splitting and applying remove-empty/trim options.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "stats": {
+      "description": "Metrics for the original text and the result.",
+      "properties": {
+        "original": {
+          "description": "Metrics of the input text before splitting.",
+          "properties": {
+            "characters": {
+              "description": "Character count of the input (same as length).",
+              "type": "integer"
+            },
+            "length": {
+              "description": "Character count of the input.",
+              "type": "integer"
+            },
+            "lines": {
+              "description": "Newline-delimited line count of the input.",
+              "type": "integer"
+            },
+            "words": {
+              "description": "Count of alphabetic word runs in the input.",
+              "type": "integer"
+            }
+          },
+          "type": "object"
+        },
+        "result": {
+          "description": "Metrics of the produced parts.",
+          "properties": {
+            "avg_length": {
+              "description": "Mean part length, rounded to one decimal.",
+              "type": "number"
+            },
+            "elements": {
+              "description": "Number of parts produced.",
+              "type": "integer"
+            },
+            "max_length": {
+              "description": "Longest part length.",
+              "type": "integer"
+            },
+            "min_length": {
+              "description": "Shortest part length.",
+              "type": "integer"
+            },
+            "total_length": {
+              "description": "Sum of the character lengths of all parts.",
+              "type": "integer"
+            }
+          },
+          "type": "object"
+        },
+        "settings": {
+          "description": "The effective split settings (snake_case).",
+          "properties": {
+            "delimiter": {
+              "description": "Delimiter used.",
+              "type": "string"
+            },
+            "max_splits": {
+              "description": "Split cap applied (0 = none).",
+              "type": "integer"
+            },
+            "regex": {
+              "description": "Regex pattern used.",
+              "type": "string"
+            },
+            "remove_empty": {
+              "description": "Whether empty parts were dropped.",
+              "type": "boolean"
+            },
+            "split_type": {
+              "description": "Split method used.",
+              "type": "string"
+            },
+            "trim_elements": {
+              "description": "Whether parts were trimmed.",
+              "type": "boolean"
+            }
+          },
+          "type": "object"
+        }
+      },
+      "type": "object"
+    },
+    "success": {
+      "description": "Always true on success.",
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

First observedv0.1.0May 31, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds valuable behavioral details: rate limit (60 req/min), offline/deterministic nature, and mode-specific behavior (e.g., parameter ignore). Minor gap: does not mention error handling beyond blank text.

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?

Description is well-structured with front-loaded main idea, followed by alternatives and behavioral notes. Every sentence adds value, though length could be slightly tighter.

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 complexity (7 params, 100% schema coverage, output schema exists), the description covers all essential aspects: purpose, methods, options, alternatives, behavioral traits, and return summary. No gaps.

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%, so baseline is 3. Description adds context beyond schema: explains behavior of each splitType (e.g., 'lines splits on newlines'), clarifies parameter dependencies (delimiter/regex only for specific types), and notes return value includes statistics. Does not repeat schema descriptions.

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: splitting a string into parts using multiple methods. It specifies the resource (string) and verbs (split), and distinguishes from siblings like text_joiner, text_statistics, and column_tool.

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?

Explicitly states when to use the tool ('Use this to break a string apart') and provides alternatives for inverse operations and similar tools. Also includes behavioral constraints like rate limit and deterministic nature.

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

Deploy Server