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.
-
Frugal, embeddable code-graph building block for agentic systems — folder/file/AST graph in a local DuckDB file, with impact and explain tools over MCP.
MIT -
mcp-awaitgithub.com/ricardo-hdrn/mcp-awaitupdated this year
Non-blocking awaiter for bash commands. Get your agent rid of timeouts, sleeps, while. Also supports files, ports, etc.
npm MIT ★ 2 -
aegis-mcpgithub.com/cleburn/aegis-mcpupdated this year
Runtime enforcement. Loads policy into server memory, validates every agent action before execution. Blocked actions get a specific reason and an override protocol. Zero token overhead — agents never load governance files.
npm MIT ★ 3 -
Air traffic control for AI agent teams: an MCP server that lets agents claim files, block conflicts, share decisions and brief newcomers, all on one MongoDB Atlas cluster.
-
A MCP or embeddable semantic-search building block for agentic systems — hybrid vector + exact-token search over a local DuckDB file, no external vector database.
MIT ★ 3 -
pi-secrets-guardgithub.com/vaibhav-patel/pi-secrets-guardupdated this year
Block secrets and PII before they land: regex + entropy scanning for files, diffs, and AI coding agents (CLI + MCP + skill + pi extension).
MIT -
Local-first persistent memory layer for AI agents. SQLite-backed, MCP-compatible, cross-agent. Privacy: secret-blocking writes, file-only storage.
npm MIT ★ 2 -
Safety layer for AI coding agents: blocks dangerous commands and scripts, savepoints and rollback for project files, HMAC-signed tamper-evident audit log. MCP server + CLI.
NOASSERTION ★ 1 -
Declaw -- Secure AI Sandboxesno update data
Secure runtime for AI agents. Run AI agents and their tools in Firecracker microVMs with network policies, PII scanning, prompt injection defense, and audit logging. 7 tools: create_sandbox, run_command, read_file, write_file, list_files, kill_sandbox, list_sandboxes. Security presets (none / standard / strict) let you control guardrails per sandbox: restrict outbound traffic to specific domains, redact PII from command output, block prompt injections, and get full audit trails.
smithery -
A Model Context Protocol server that gives an agent read and write access to a local Exocortex node — PARA buckets, blocks, links and tags, plus the workspace's own conventions so the agent files things where you would. Stateless, local only; there is no hub endpoint.
-
Question boards with rich blocks (markdown, charts, mermaid, tables, code, diffs, video, sandboxed HTML), clickable local file-links, and element-level annotations for AI coding agents (Claude Code, Codex, …): ask users structured questions, present inter
npm MIT -
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 -
MCP server for terminal operations and file editing
npm MIT -
MCPTap is a lightweight LLM proxy for AI agents that intercepts traffic (currently over 200 providers) and controls MCP tool calls / protects files from AI agent.
NOASSERTION ★ 1 -
An enhanced MCP server for Capacities API 2.0 with full CRUD, precise block editing, Markdown support, file uploads, and API key pooling.
go MIT ★ 3 -
MCP server for WordPress. Purpose-built abilities for SEO, content, blocks, the database and files — every write is previewed, snapshotted, and reverted automatically if the site breaks.
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.
pypi MIT ★ 4 -
syncralis-web-agentgithub.com/pslkk/syncralis-web-agentupdated this year
Enterprise-grade MCP server giving any MCP client a real, trust-checked, SSRF-protected browser: API-based web search (Tavily/Brave, no anti-bot blocking), verify sites, read pages and social/official feeds, click, and download files (images, PDFs, Office
npm ISC -
Headless MCP server that composes and renders Universal LPC character spritesheets: 657 items, 6 body types, palette recoloring, 15 animation row blocks, attribution files included. No browser.
npm GPL-3.0 ★ 3 -
Local ledger for development ports — leases a block per project slot, renders env files, resolves service names to URLs, and serves it all over MCP. No daemon, no listener, no secrets.
MIT -
Makes wrong code fail. A checker for any repository, a scanner for known prompt-injection signatures in versioned files, a gate (hooks, CI, ruleset) that blocks the commit, and a generator whose projects start passing.
Apache-2.0 ★ 2 -
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 -
MCP server for on-chain Solana cabal & rug detection — exit-liquidity verdict, funding-cluster, same-block bundle and coordinated-selling detection, serial-launcher deployer history, honeypot check. npx, 5 free scans/mo or 250 with a free key. Card, USDC or x402. Also: wallet case files + Dev Launch Radar (Telegram, Chrome).
npm MIT ★ 2