Librecrawl Mcp

data-ai MCP Server

The AI-native technical SEO crawler. Open-source MCP server for Claude / Cursor / Codex — 37 tools, 50+ checks, unlimited pages, WAF detection, ephemeral by design. Built on LibreCrawl. MIT.

VerifiedFresh
data-aidata-ai
2 views41 stars7 forksMIT

Why This Matters

Discovered via github-topic:mcp and last synced Today.

VerifiedFresh
Source
github-topic:mcp
Stars
41
Last synced
Today
Install
Check source

Install

Install instructions not detected yet

Check the source repository for the latest setup steps.

View source instructions
41
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (41)

Hreflang

Language variant detection for multilingual sites

librecrawl_audit

**One-call full audit** — crawl + site checks + 30+ checks + report

librecrawl_list_crawls

List all saved crawls

librecrawl_append_gsc_section

Merge GSC indexing errors into any audit report

Images

Missing alt text (per-page count + total), broken image references

librecrawl_export_results

Raw JSON export

Section

What it catches

librecrawl_internal_links_analysis

Internal authority map — top linked pages, orphans, dead ends, anchor text

librecrawl_stop_crawl

Stop running crawl

librecrawl_pagespeed

Core Web Vitals for one URL (Google PSI API)

librecrawl_start_crawl

Start async crawl, returns `crawl_id`

librecrawl_visualization_data

Site link graph (nodes + edges)

LIBRECRAWL_PORT

`5080`

Check

Screaming Frog Free

librecrawl_schema_check

Schema.org / JSON-LD for one URL — rich result mapping

librecrawl_pause_crawl

Pause a running crawl

PAGESPEED_API_KEY

unset

Unlimited

Tiered by subscription plan

librecrawl_schema_audit

Schema coverage across multiple URLs

librecrawl_resume_crawl

Resume a paused crawl

REPORTS_DIR

`~/librecrawl-reports`

Tool

What it does

librecrawl_get_settings

Show current crawler settings

Default

Purpose

librecrawl_site_check

Instant: robots.txt, sitemap, HTTPS, www — no crawl needed

librecrawl_generate_report

Re-generate report from a past crawl

librecrawl_pagespeed_audit

Batch CWV for up to 25 URLs, ranked worst-first

librecrawl_get_status

Poll crawl progress

MCP_PORT

`5081`

librecrawl_filter_issues

Exclude false-positive patterns from results

INSTALL_DIR

`~/librecrawl-mcp`

Capability

Desktop crawler (Screaming Frog SEO Spider™)<sup>1</sup>

Manual

Hidden

Partial

❌

Native

✅

File

Use

LIBRECRAWL_URL

`http://127.0.0.1:5080`

MCP_HOST

`127.0.0.1`

MCP_TRANSPORT

`http`

LIBRECRAWL_UPSTREAM_DB

`~/.librecrawl/upstream/users.db`

Guide

What's inside