Free MCP servers · page 82

IvanBBaev/x-mcp

Safety-first X (Twitter) API v2 MCP server: 41 typed tools across 12 packages, policy-gated.

senoff/xlsx-for-ai

50 spreadsheet tools for .xlsx: recalc formulas, repair broken refs, read/write, diff, audit.

jarod-vyent/xrpl-identity-mcp

MCP server for XRPL identity: DIDs, credentials, signer lists, and safe transaction workflows.

beSaif/zenpilot

Let Claude use your Zen Browser, like Claude in Chrome. No extension, only sites you allow.

ejfkdev/zread-mcp

Zread.ai MCP Server - 连接 zread.ai 文档平台的 MCP 服务器，让 AI 助手能够阅读 GitHub 仓库文档、搜索代码、与仓库 AI 对话。

AgentsKit-io/agentskit-registry

Discover open-source AI agents and get source-owned installation instructions through MCP.

globalsearchdata/enrich-mcp-plugin

Free — no API key required. Enrich by domain or name. Country, contacts, social profiles.

mcp-dir/jusbrasil-mcp

Open-source alternative to Jusbrasil for AI: find lawsuits by name, CPF, CNPJ or case number and bui

sfxmint/sfxmint-mcp

Free CC0 sound effects for apps and games: roles, sets, search; 20 keyless downloads a day; make one

unifai-network/unifai-mcp-server

Dynamically search and call tools using UnifAI Network

AgentAvow/AgentAvow

Signed, recomputable safety scores for MCP servers, packages and tools, with offline-verifiable attestations and a GitHub Action to gate CI merges.

backloghq/backlog

Persistent, cross-session task management for Claude Code with agent coordination, event-sourced storage and per-project isolation.

bit2beat/bitrix24-mcp

Connect to Bitrix24: CRM, tasks, disk, calendar, chat, business processes, telephony and product catalog.

dimpagk92/cellar

Hybrid computer-use runtime combining the accessibility tree, Chrome DevTools Protocol and vision into structured context, with offline support via Ollama.

pavelpilyak/devrecall

Local-first index of your commits, PRs, Jira/Linear tickets, Confluence docs, Slack threads and calendar events to search and cite past work.

Dissimilis/DirForge

Read-only directory listing web app: browse directories, read files, search content, inspect archives, compute hashes and check disk usage.

dmang-dev/mcp-dolphin

Control the Dolphin GameCube/Wii emulator: memory read/write, GameCube and Wii Remote input, reset, save states and frame advance, via Felk's scripting fork.

dotemacs/domain-lookup-mcp

Domain name lookup via RDAP, falling back to WHOIS.

neilberkman/editorconfig_mcp

Formats files using .editorconfig rules so AI-generated code follows project formatting standards.

r-huijts/ethics-check-mcp

Ethical analysis of AI conversations: detect bias and harmful content and provide critical-thinking assessments, with automated pattern learning.

carrasquelalex1/hipocampo

Bilingual (English/Spanish) dual-memory system on PostgreSQL, pgvector and NVIDIA NIM with progressive retrieval, deduplication, checkpoints and auto-repair.

wn01011/llm-token-tracker

Token usage and cost tracking for OpenAI and Claude APIs with real-time session tracking.

lucasmartins-ai/lookacrawler

Token-efficient local web crawler with Playwright-based stealth anti-bot bypass.

AIMLPM/markcrawl

Crawl websites into clean Markdown, search pages and extract structured data with LLMs for web research and RAG pipelines.

Adityaaery20/media-mcp

Local image and video processing: resize, convert, compress, crop, thumbnails, metadata extraction, rotate, flip, filters and ffmpeg-based video operations.

AndreLYL/memkin

Local-first personal memory that distills Feishu/Lark chats and Claude Code/Codex sessions into a private knowledge graph of people, projects and tasks.

1luvc0d3/metabase-mcp

Metabase integration: natural-language data analysis, dashboard management, SQL queries and automated insights, with SQL guardrails and audit logging.

dmang-dev/mcp-mgba

Control the mGBA Game Boy Advance emulator: memory read/write, button input, screenshots, save states and stepping.

karyaboyraz/mockit-mcp

Generate iOS UI mockups as PNG and HTML from a text prompt, using Claude and a headless Playwright renderer.

nlqueries/nlqueries

Self-hosted natural-language-to-SQL engine with validation for PostgreSQL, MySQL, Snowflake, BigQuery and DuckDB, plus document QA and semantic caching.

Synexiom-Labs/nodiom-mcp

Read and edit Markdown files by structure (headings, lists, sections) instead of regex or line numbers: read a section, write one list item, append under a heading.

VrtxOmega/omega-brain-mcp

AI execution pipeline with NAEF logic constraints, VERITAS build gates, semantic vault integration and Tri-Node Cortex validations to curb hallucination.

toan203/osv-ui

Visual CVE audit dashboard for npm, Python, Go and Rust using OSV data, with browser-based human review and fixes applied only after confirmation.

liftkkkk/owl-mcp

Work with OWL/TTL/RDF ontologies: SPARQL queries, HermiT/Pellet reasoning and CRUD operations on knowledge graphs.

EdelmarSchneider/permark

Markdown reader and editor that tells coding agents what you are reading: the open document, section and selection, unread changes, your comments to resolve, and section search across the project. Read-only, local and off until enabled per project.

fish827-08/rag-kb

Local-first agent memory and knowledge base: hybrid dense and BM25 retrieval, document and webpage ingestion and optional RAG answers via local Ollama.

taylormatematica-beep/repoguard

Fast architectural linter & guardrail engine for AI coding agents: detects layer violations, leaked secrets, and enforces .cursorrules & CLAUDE.md standards in ~12ms.

nomadop/session-watcher

Monitors coding-agent token cache using inventory theory (EOQ) and signals optimal session restart timing via a live dashboard and terminal status line.

hunglp97/tabpilot-mcp

Drive your open, logged-in Chrome with token-budgeted page reading, complex SPA form and survey handling, and headless Ubuntu support.

magna-nz/tallybook

Local cost tracking for Claude Code and Codex sessions: spend by session, sub-agent and model, week-on-week comparisons, and findings with suggested patches.

NazarKalytiuk/tarn

API testing tool with YAML tests and structured JSON failures agents can act on: run, validate, inspect, rerun failed tests and get fix plans.

HasanJahidul/terminal-history-mcp

Local full-text search over zsh, bash and fish history, with secret redaction and optional capture of cwd, exit code and duration.

mikan-atomoki/text-to-model

Turn natural language into 3D models in Fusion 360, with CAD tools for sketches, extrudes, fillets and JIS standard parts.

davidan90/time-node-mcp

Timezone-aware date and time operations: IANA timezones, timezone conversion and daylight saving time handling.

Yomiracle/trinity-lite

Local task bus for CLI AI agents such as Codex and Claude Code: route work, persist state in SQLite and collaborate through a shared server.

ShipItAndPray/mcp-turboquant

LLM quantization: convert models to GGUF, GPTQ and AWQ, recommend quantization settings, evaluate quality and push to Hugging Face Hub.

mi60dev/visionaire-engine

Design debugging in Chrome: which CSS rule wins (with file and line), its blast radius, scoped fix selectors, live fix trials and WCAG contrast audits.

zzallirog/weighted-compact

Inspectable memory for Claude Code: read-only search and session compaction over a local, signal-scored parse of its project logs, with no outbound calls.