MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
MCP server for markdown files — search, extract sections, list headings, find code blocks across your docs directory
npm MIT -
Blockend CLI — shadcn/ui-style backend blocks for TypeScript. Generate production-ready rate limiting, validation, logging, and error handling as source code into Express, Fastify, Hono, or Next.js projects. You own the code. Ships an MCP server for AI co
npm MIT -
Block explorer and network monitor for the DeFCoN (DFCN) network, the code behind deftrack.xyz
MIT -
clean-fetchgithub.com/kenta-hi/clean-fetchupdated this year
Clean, trustworthy WebFetch replacement for Claude Code. Trafilatura-based extraction + injection protection + SSRF blocking.
MIT ★ 1 -
Bidirectional blocking ping-pong MCP bridge between Antigravity and Claude Code
MIT -
webfetch-camouflage-mcpgithub.com/tianhuil/webfetch-camouflage-mcpupdated this year
Give your AI coding assistant reliable access to web pages that block standard fetch.
MIT ★ 1 -
Deterministic CI/CD gate and native MCP server to block AI coding agents from slopsquatting, breaking architecture, and bypassing linters.
MIT -
Holds a coding agent's completion report to the record: deterministic checks of a declared handback block against the repository's own metadata.
npm AGPL-3.0-only -
Tell your coding agent which dependencies changed after its training cutoff. Diffs types and changelogs, writes a short block into AGENTS.md / CLAUDE.md.
MIT ★ 109 -
todouzgithub.com/llhtoby38/todouzupdated this year
ADHD-friendly task manager with epics, sub-issues, time-blocks, and an MCP server so any Claude Code / Claude Desktop / Cursor session can read+write tasks.
MIT ★ 2 -
MCP server + skill: a task list your coding agents report into. Steps, live progress bars and blocked questions for Claude Code, Cursor, Codex.
MIT -
Junto channel plugin: surfaces shared-memory inbox messages as channel blocks in Claude Code terminals. The CTerm-side component of the Junto system.
MIT -
Install gate for AI coding agents: blocks malicious, hallucinated and typosquatted packages (npm, PyPI, crates.io, Go) before Claude Code installs them. Hook + MCP server + CLI.
MIT -
Fast local code search, source reads, and smart block-clamped context for AI coding agents. VS Code Native Language Model Tools & MCP server backed by a shared Rust trigram cache (Linux, Windows, WSL).
MIT -
Multi-model review gate for AI-written code: independent models from different providers cross-check every change, and a deterministic gate records PASS, BLOCKED or INCONCLUSIVE. CLI + MCP server. MIT.
MIT -
Local mail for coding agents: Claude Code, opencode and kiro-cli sessions message each other, ask blocking questions and wake each other up. MCP server + CLI in Rust.
Apache-2.0 -
bitcoin-cardgithub.com/zartyblartfast/bitcoin-cardupdated this year
Open-source MCP server exposing verified Bitcoin data (price, fees, block height, network stats) to AI coding assistants like Claude Code, Cursor, and Cline.
MIT ★ 1 -
Guardrails for AI coding agents (Claude Code, Cursor, Codex): impact analysis, architecture rules, blocked bad changes and a tamper-evident record. Run with npx; downloads the verified Garuda release binary.
npm Apache-2.0 -
MCP server for nana800.io: build and manage no-code workflows, blocks, run history and analytics exports from Claude, Cursor and other MCP clients
MIT -
DevNotes+ — a VS Code extension for developer notes anchored to files, lines, and git branches. Rich block editor, Claude Code MCP integration, GitHub PR/issue linking, and opt-in team sharing over git.
AGPL-3.0 ★ 1 -
MCP server that exposes Oracle Forms modules (.fmb/.mmb/.pll/.olb) — blocks, triggers, PL/SQL, object XML — to AI assistants for legacy modernization and code review.
Apache-2.0 ★ 10 -
Stop AI agents from writing SQL against tables and columns that do not exist. Schema snapshot + Claude Code hook + MCP server + CI check. 0 false blocks on 1,034 Spider queries.
MIT ★ 1 -
Mask secrets in a project with stable placeholders, encrypt the originals, and restore them byte-for-byte. Guards Claude Code, Codex, Gemini CLI, Cursor and Copilot, and blocks git commits that leak secrets. Powered by gitleaks.
MIT ★ 3 -
Small SaaS building blocks a coding agent can set up, verify and hand to a human: waitlists, feedback widgets, changelogs, deploy checks, onboarding checklists, CSV import and more. CLI and local MCP server.
npm MIT -
Lossless local memory for Claude Code. The full, unabbreviated version. Every tool call, every file edit, every thinking block — stored verbatim on your machine. Persistent memory without tokens.
MIT ★ 16 -
The open-source browser after Arc: spaces, Arc import, built-in ad blocking, and an AI agent you can also drive from Claude Code. Windows and macOS.
GPL-3.0 ★ 7 -
Stop AI coding assistants (and teammates) from silently undoing bug fixes. Lock fixed lines, check edits via MCP in Claude Code, Cursor, Copilot and Codex, and block reverting PRs until the owner approves. A product of Algotricz.
npm MIT -
Re-run the work, recompute the number, block the wrong one before it ships — a deterministic guardrail for AI-computed results. CLI · Claude Code hook · MCP.
MIT -
Causal project memory for coding agents: corrections first in every session, and a guard that blocks the edit that writes a withdrawn value back. 4 MCP tools, ~670 tokens. Claude Code · Codex · Cursor · GitHub Actions
MIT -
MCP server that turns Codex into a conductor for a multi-model coding pipeline: split plan → code with GLM → review with another model → auto-fix, all sandboxed with git commit/push blocked.
★ 1 -
mcp-piholegithub.com/aplaceforallmystuff/mcp-piholeupdated this year
MCP server for Pi-hole v6 API - control DNS blocking from Claude Code
MIT ★ 8 -
pdf-it-mcpgithub.com/mrslbt/pdf-itupdated this year
MCP server and Claude Code skill that turns markdown into designed PDFs. Cover page, table of contents, code blocks that hold across page breaks, page-numbered footer. Fonts embedded, nothing else to install.
npm MIT -
🧠 Save 70–95% tokens in Claude Code, Cursor, Windsurf & Cline. Local Tree-sitter code graph MCP server: surgical edit context instead of full-file reads, refactor safety checks, and a hook that blocks large file reads. Reduce token usage & cost, zero LLM indexing.
MIT ★ 4 -
Zero-dependency linter and gate that blocks AI-generated comment slop: multi-line narrative comments, changelog markers, step-numbered filler. Write-time plugin for OpenCode, Claude Code hooks, pre-commit, GitHub Action, GitLab CI, MCP server. RU+EN+DE+FR+ES detection.
npm MIT ★ 7 -
MCP server for markdown — search, extract sections, list headings, find code blocks
npm MIT ★ 8 -
Claude Code plugin for Synapse, a compiler for AI agent workflows: compiles a workflow to a typed graph, optimizes it, and blocks any rewrite that fails an equivalence check. Side-effecting steps are never reordered, repeated or cached. MCP server + 4 slash commands.
MIT -
@iflow-mcp/sgroy10-speclockgithub.com/sgroy10/speclockupdated this year
AI Constraint Engine by Sandeep Roy — AI Patch Firewall. Diff-native review (interface breaks, protected symbols, dependency drift, schema changes, API impact), Patch Gateway (ALLOW/WARN/BLOCK verdicts), Spec Compiler (NL→constraints), Code Graph (blast r
npm MIT -
MCP server that turns web pages into clean Markdown, keeping tables, code blocks, and images intact. Agents can fetch pages, save docs to your project or a global library, and crawl whole doc sites.
Apache-2.0 ★ 3 -
uploadcheck-mcpgithub.com/ajantoniou/uploadcheck-mcpupdated this year
MCP server for UploadCheck — pre-publish media QC for AI agents. Run 40+ quality gates on a video/audio export from Claude Code, Cursor, or Codex, get timestamped fixes, and gate your publish on a signed PASS/BLOCK receipt.
MIT -
@iflow-mcp/shen-ming-hong-singular-blocklygithub.com/shen-ming-hong/singular-blocklyupdated this year
VS Code extension for visual Arduino & MicroPython programming with Blockly. Multi-board support (Uno, Nano, Mega, ESP32, CyberBrick), WiFi/MQTT IoT blocks, AI camera integration (Pixetto, HuskyLens), MCP server for GitHub Copilot, PlatformIO integration,
npm Apache-2.0 -
Supervise an AI coding agent (Claude Code / Codex / ACP) overnight and keep control: block forbidden tool calls before they run, gate 'done' on real tests, checkpoint work to git, cap spend, and get a morning report where every line is sourced. Local-first, no telemetry. Rust daemon + Tauri app + Claude Code plugin.
MIT ★ 1 -
BlockHand: MCP server for Minecraft Education Edition over the official /connect (/wsserver) WebSocket. No add-on or behavior pack needed. 44 tools: control the Agent robot, build 24 shapes merged into minimal /fill commands, read blocks, compare regions, subscribe to game events. For Claude Code, Codex, Gemini CLI, Grok.
npm MIT ★ 5 -
Agent runtime guard — full-stack runtime interception for AI agents (Agent 运行时全栈拦截). A zero-dependency MCP server that blocks destructive commands, credential theft, SSRF and injection in real time, with Ed25519 evidence receipts. Works with Claude Code,
npm Elastic-2.0 -
MCP integration for Blockbench: a Claude Code-launched stdio MCP adapter plus a Blockbench desktop plugin for AI-assisted Minecraft Java block/item model editing.
npm MIT -
Prompt-injection defenses for Claude Code. A PreToolUse Bash hook blocks compositional credential-exfiltration shapes (secret read plus network, env dump to network, remote script to shell, reverse shells). A sanitizing MCP server wraps untrusted URLs and files in sentinels, strips invisible unicode, flags jailbreaks.
MIT ★ 4 -
Release gate for public GitHub repositories. Give it a repo URL and it returns a ship-or-block verdict with file-and-line evidence, the fixes that clear the gate, and the deployment plan and launch copy you ship with. HTTP + MCP. Static analysis only; no code execution.
MIT ★ 4 -
@wensity/mcpactive
Wensity MCP server: lets AI coding agents search Wensity UI components and blocks, check Free and Pro access, plan an installation, and install it into your project.
npm MIT -
pdf2md-aigithub.com/tu-usuario/pdf-to-markdown-mcpupdated this year
AI-powered PDF to Markdown converter that preserves complete context: images, tables, and code blocks. Uses Gemini and LlamaParse. MCP server for Claude Desktop, Cursor, and Windsurf.
npm MIT -
Typed decisions for AI agents as an MCP tool: yes/no probability (noul), choice, and score about JSON state in one fast request, with a fallback envelope that never blocks. Backed by the TypeSafe System One model; shared by pi, Claude Code, and goose.
npm Apache-2.0 -
Ask your AI coding agent, in natural language, to search production logs or inspect a database — safely. Two drop-in MCP servers (MySQL, SSH logs) keep safety red lines in code: read-only by default, dangerous SQL/shell blocked, production disabled, no stored credentials. A recommended Skill layer teaches the model when and how to use them.
MIT ★ 3 -
Read-only MCP server for PostgreSQL, MySQL & SQLite. Lets AI assistants (Claude, Cursor, VS Code) explore schemas, run safe SELECT queries, read EXPLAIN plans, get index suggestions, and review migrations. Writes are blocked by design.
MIT ★ 8 -
fetchrgithub.com/thesatellite-ai/fetchrupdated this year
An open-source HTTP client with browser TLS fingerprinting (JA3/JA4, HTTP/2, QUIC) — a CLI, an MCP server that gives Claude Desktop & Claude Code real HTTP access, and an importable Go package. Requests look like Chrome or Firefox, passing anti-bot detection that blocks curl.
Apache-2.0 ★ 1 -
Textile Designer AIno update data
Run the Textile Designer AI design tools on image files on your computer: print-ready upscaling, seamless repeats (block, half brick, half drop, mirror, step), Super Scaler, background and watermark removal, Dress to Design, Colourways, Colour and Object Layering, Channeling screen separation, Vectorizer, 3D and Embroidery effects, Sketch to Design and more. Results are saved next to your input image. Needs a Textile Designer AI account with credits or a plan: https://www.textile-designer.ai. Sign in with the `login` tool (browser device code). Privacy: https://www.textile-designer.ai/privacy. Source and docs: https://github.com/ScientiaAI/textile-designer-ai-claude
smithery -
AYLENTO · 艾伦兔no update data
# AYLENTO · 艾伦兔 Connect Agents across AI clients using independent identities, private messages, group chats, attachments, follows and block lists. 艾伦兔为不同 AI 客户端中的 Agent 提供独立身份和通信能力,共 36 个 MCP 工具。 Client 0.13.0-beta.4 public beta; MCP runtime 0.13.0-beta.1. 本包为公测版,普通用户注册无需邀请码。 ## Install / 安装 This is a **local stdio MCP bundle**, not a hosted HTTP endpoint. Import the `.mcpb` file into a compatible client. The client must supply **Node.js 24.15.0 or newer**; the bundle includes the JavaScript server and its dependencies, but does not include Node itself. Older bundled Node runtimes cannot run it. No npm installation or API key is required for this bundle. 在支持 MCPB 的客户端导入安装包,并确保它实际使用 Node.js 24.15.0 或更新版本。包内含完整 JS 客户端和依赖,不含 Node 运行环境。安装时为当前客户端选择独立的本地配置名称(默认 `smithery-local`)。 For clients without MCPB import, extract this archive to a permanent directory and configure a local MCP server with command `node`, argument `/absolute/path/to/extracted/bin/aylento.mjs`, and environment `AYLENTO_BASE_URL=https://aylento.com`, `AYLENTO_PROFILE=your-unique-host-profile`. Windows uses an absolute Windows path. Each host's JSON structure differs; see the [official installation guide](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/README.md). Do not enable duplicate native-plugin and manual-MCP installations for the same identity. ## Pair and use / 配对与使用 1. Register at [aylento.com](https://aylento.com) and create a separate Agent Chat for this host. 2. Ask: “查看我的艾伦兔连接状态,未连接才开始配对。” The Agent should call `aylento_connection_status` first and `aylento_connect` only when disconnected. 3. Personally approve the returned pairing page and code in your browser. Never paste passwords, session tokens or private pairing links into public listings or issues. 4. Ask the Agent to call `aylento_finish_connection` once after approval. Pending means wait for the person, not continuous polling. 5. Ask “查看我的艾伦兔新消息” or “查看当前身份的黑名单”. To send, specify the recipient's exact rabbit ID and the message; verify the recipient before sending. Use both a separate profile **and a separate Agent Chat** per host. A profile only isolates local storage; it does not create a server identity. Pairing an existing identity elsewhere replaces its prior external session. Keep the same profile during an upgrade to retain local authorization and history. The included `skills/aylento/SKILL.md` contains model-facing instructions. MCPB hosts do not necessarily load skills automatically; follow the host's instructions to load it if supported. Codex, Claude Code and Gemini CLI also have [native installation options](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/README.md). ## Data and behavior / 数据与行为 Messages are sent through the AYLENTO service. Incoming message history and attachments are saved to local SQLite before delivery acknowledgment; histories do not automatically synchronize between devices. Tool results may enter the selected host/model's context and logs. Read `PRIVACY.md` for destinations and retention details. Before mutual following or the first reply, only one unsolicited private message is permitted. Once the recipient replies, both parties may continue; blocking and rate limits still apply. `REPLY_REQUIRED` means the message was not sent. Reception is not permission to auto-reply, and receiving messages does not guarantee the host wakes a model. Local reception stops when the process or device stops. If a send has an unknown outcome, inspect messages before attempting again. Disconnecting revokes external authorization but retains local history. Uninstalling the bundle does not erase that history. Do not share actual state directories, credentials, messages or attachments in bug reports. The bundle is checked with isolated MCP startup and a 36-tool inventory. This is not a claim of completed real-model messaging tests in every host or on every operating system. Refer to [host verification scope](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/HOSTS.md). ## Copyright and updates / 版权与更新 Copyright (c) 2026 AYLENTO copyright holders. All rights reserved. **AYLENTO Client Use License v1.0** applies; see `LICENSE.txt`. This is not MIT or another open-source license. Personal and organizational internal installation and use are allowed; additional program modification, repackaging, external redistribution, resale and sublicensing require separate written permission. Third-party licenses, statutory rights and rights already granted by official platform terms remain unaffected. Keep `THIRD_PARTY_NOTICES.md` with the bundle. Download updates only from official AYLENTO channels, preserve the profile and local data, and install a newer bundle through your host. Merely pushing Git does not update an installed bundle or publish a Smithery release; the distribution build and authenticated publication must also run. [Website](https://aylento.com) · [Official repository](https://github.com/popularzb/aylento-plugins) · [Release downloads](https://github.com/popularzb/aylento-plugins/releases) · [Public support](https://github.com/popularzb/aylento-plugins/issues)
smithery -
BlockWerk plugin for Claude: build, run and analyse block-diagram simulations via MCP
MIT -
Block-explorer-style site and read-only MCP server for Papertrade wallets, positions and leaderboards on HyperEVM.
Apache-2.0 ★ 6 -
VS Code extension and MCP server for Airtable, formula editor, schema tools, and 60+ automation utilities for bases, views, and fields.
npm MIT ★ 32 -
MCP server for terminal operations and file editing
npm MIT -
ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.
npm MIT ★ 31 -
MCP server and Agent Skill for TakeSix. TakeSix is an open format and libraries that let an AI agent answer with a diagram you can click into instead of a wall of text: at most six blocks per screen, and any block opens into up to six more.
npm MIT