Skip to main content
Glama
Jambozx

OnlineCyberTools MCP (280+ filterable tools)

text_extract_urls

Read-onlyIdempotent

Extract every URL from a block of text, with per-match details, filtering by scheme, deduplication, and sorting. Returns matched URLs and statistics.

Instructions

Extract URLs From Text. Scan a block of text and return every URL it contains, with per-match scheme, byte position, line number, and optional surrounding context. Filter by extraction mode (all, http, https, ftp, or a custom scheme list), deduplicate case-insensitively, and sort alphabetically. Use this for hyperlinks and protocol URIs; use text_extract_emails instead when you only want email addresses. Pure regex extraction — read-only, non-destructive, performs no network requests against the found URLs, runs locally with no auth. Rate limited to 30 requests/min per IP (text category). Returns the matched urls array plus stats (original text metrics + extraction counts and per-scheme tally) and the resolved options.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYesSource text to scan for URLs. Required and non-empty.
extractionModeNoWhich schemes to match. all = http/https/ftp plus many app schemes and bare www. links; http = http or https; https = https only; ftp = ftp or ftps; custom = use customSchemes.all
customSchemesNoComma-separated scheme list (e.g. "myapp,custom") used only when extractionMode is custom. Required and non-empty in that mode.
removeDuplicatesNoDrop case-insensitive duplicate URLs from the results.
sortResultsNoSort results alphabetically by URL.
includeContextNoInclude surrounding text around each match.
contextLengthNoCharacters of context on each side when includeContext is true. Clamped to 10-200.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
successNoTrue when extraction succeeded.
urlsNoMatched URLs, after dedupe/sort.
statsNoOriginal-text metrics and extraction summary.
optionsNoResolved options actually applied.
errorNoError message when success is false.
Behavior5/5

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

Beyond annotations (readOnlyHint, destructiveHint, idempotentHint), description adds crucial traits: pure regex extraction, read-only, non-destructive, no network requests, local with no auth, rate limited to 30 req/min. No contradiction with annotations.

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 comprehensive but slightly long. It is front-loaded with main purpose and includes all critical details. Minor verbosity in listing every feature; still efficient and well structured.

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 7 parameters with full schema description and existence of output schema, the description covers purpose, behavior, limitations, rate limit, alternatives, and output summary completely. No gaps identified.

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%; description summarizes parameters (e.g., 'Filter by extraction mode', 'deduplicate case-insensitively') but repeats some schema info. It adds value by explaining output structure (per-match fields) not in input schema, and notes constraints like 'Required and non-empty'.

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 clearly states 'Extract URLs From Text' with specific verb and resource. It details scanning text, returning per-match details, and distinguishes from sibling 'text_extract_emails' for email addresses.

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?

Provides explicit context for use: 'Use this for hyperlinks and protocol URIs; use text_extract_emails instead when you only want email addresses.' Also mentions rate limits and local execution, but does not exhaustively list when not to use.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Jambozx/onlinecybertools-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server