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_independentgithub.com/PrecIQ/mcp_server_independentupdated this year
https://www.udemy.com/course/model-context-protocol part 2 with independent server
-
Model Context Protocol (MCP) server for the Financial Independence community
MIT -
Model-independent grocery price MCP: local, HTTP, Docker, and cloud deployment
MIT -
Model-independent MCP tools for background tabs in your existing Chrome window
npm MIT -
polyphony-mcpgithub.com/exusiaiwei/polyphonyupdated this year
Reference MCP server for the Polyphony protocol — let any model participate in GitHub Discussions as an independent voice.
npm MIT -
Local-first, model-independent personal memory for AI clients via MCP.
MIT -
model-context-protocol-servergithub.com/PAIshanMadusha/model-context-protocol-serverupdated this year
A monorepo containing three independent MCP (Model Context Protocol) servers, implemented using three different runtime environments.
MIT ★ 1 -
loregithub.com/Vany/loreactive
An independent multi-model code reviewer that remembers the codebase between sessions
MIT ★ 10 -
A FalkorDB repair lab and MCP tool server for brick models, with counterfactual queries and independently replayable repair proofs.
MIT -
@nanorix/mcp-serverupdated this year
Nanorix Model Context Protocol (MCP) server — drive sealed ephemeral capsule lifecycle as agent tools. Every capsule produces an independently verifiable AuditProof.
npm Apache-2.0 -
An independent MCP server for Blender: modeling, materials, animation, AI 3D generation, and Microsoft Flight Simulator content
pypi AGPL-3.0 ★ 34 -
The substrate is the asset; the model is an interchangeable client. Agent Context Substrate (ACS): model-independent memory for AI agents.
MIT -
A research prototype for a model-independent, verifiable shared knowledge layer for local or remote LLMs
Apache-2.0 -
A multi-LLM council for Claude Code — convenes Gemini, GPT and Mistral for independent second opinions and cross-model consensus, over MCP.
MIT -
Independent model benchmarks in your agent: the Artificial Analysis MCP server for Claude, ChatGPT, Cursor and Gemini CLI
MIT ★ 4 -
Claude Code orchestrates OpenCode worker agents: dynamic model routing, parallel-write safety, independent verification and read-only review.
MIT -
Model-independent Agent Skill and MCP server for DeepSeek official Search and Fetch APIs.
MIT -
dmngithub.com/cloud0fly/dmnactive
Bounded multi-model message network on DeepSeek Harness: independent root sessions, private memory, durable queues, Desktop panel and MCP tools.
MIT -
Community Model Context Protocol server for TopSolid® 7 — bring any MCP-compatible AI agent into your CAD/PDM workflow. Independent project, not affiliated with TOPSOLID SAS.
MIT ★ 8 -
Give your coding agent an adversarial critic: an independent, fresh-session MCP reviewer for code and docs, with built-in convergence and any model you bring.
npm MIT ★ 2 -
A lightweight, model-independent MCP server providing AI assistants with practical software development tools for repository analysis, code explanation, error analysis, dependency checking, and test execution.
pypi 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 -
A universal, platform-independent Model Context Protocol (MCP) server for Apache Flink, enabling AI-powered monitoring, diagnostics, and cluster management across Kubernetes, Docker, YARN, and standalone environments.
pypi Apache-2.0 ★ 2 -
Local communication bridge for independent AI coding sessions, with MCP connectors and a multi-model API discussion room. Built with TypeScript, Node.js and WebSocket.
MIT -
Local AI agent broker for small businesses: MCP server, job queue, independent review gate and local-first (Ollama) model routing, with audit trails and approvals
MIT -
TractorBeeam-MCPgithub.com/Ringosystems/TractorBeeam-MCPupdated this year
Independent Model Context Protocol (MCP) server for Veeam Backup for Microsoft 365 (VB365): read-only review by default, plus an opt-in, confirm-gated, audited action/restore tier.
oci MIT ★ 1 -
Let ChatGPT Chat read, edit and save local Windows files and run commands via MCP. No model API calls. Independent tasks, conflict-aware saves. 普通 Chat 处理本地文件的开源部署包。
NOASSERTION ★ 1 -
Figma MCP adapter (Model Context Protocol) for DCC-MCP: AI agents read and edit Figma pages, frames and nodes and export PNG/SVG via the Figma Plugin API. Independent, unreleased adapter.
MIT -
A standalone MCP (Model Context Protocol) server that provides AI context orchestration for any project with a `.ai-context` folder. This server runs independently and can be used by multiple projects without installation via `npx`.
MIT -
dsh plugin: register codex-web-search-mcp (model-independent OpenAI Codex / Grok web search & deep research MCP server) as a native dsh MCP tool set (mcp__codex-web-search__*).
npm MIT ★ 5 -
house-of-wisdom-mcpgithub.com/EzzoHamdan/house-of-wisdom-mcpupdated this year
House of Wisdom MCP: Multi-model consultation council. Diverse AI model families investigate independently and return their own perspectives; the orchestrator weighs them. Inspired by the medieval Bayt al-Hikma.
pypi MIT ★ 4 -
mediator-agentgithub.com/zdkelemen/mediator-agentupdated this year
Impartial, vendor-independent AI mediator for product-manager vs. architect disputes - CLI, Slack, Microsoft Teams (no Azure Bot needed), generic webhook, and MCP for any agentic CLI. Claude or any OpenAI-compatible model.
MIT -
mcp-serversgithub.com/rebase-master/mcp-serversupdated this year
This repository is a collection of custom MCP (Model Context Protocol) servers. Each branch in this repository contains an independent MCP server designed for a specific use case, including weather data retrieval, utilities, and AI integrations.
★ 1 -
One leader. Every model. Every MCP. Open-source MCP control plane that turns Claude, ChatGPT, Grok and Gemini into one engineering team: durable delegation, scoped GitHub grants and an independent review gate on the exact commit. No model APIs.
MIT ★ 3 -
codex-web-search-mcpgithub.com/dhicoc/codex-web-search-mcpupdated this year
Model-independent web search & deep research MCP server (Rust rewrite), powered by OpenAI Codex / Grok search endpoints. Cross-platform prebuilt binaries are pulled via optionalDependencies; the `codex-web-search-mcp` bin resolves and launches the right o
npm MIT -
lechatai-mcpgithub.com/rocnubie/lechatai-mcpupdated this year
LeChat AI (lechatai.online) is an independent guide and resource hub for Mistral's Le Chat conversational AI platform. The site covers the platform's capabilities in depth — from its speed benchmarks and pricing tiers to its European data compliance stance and open-weight model philosophy.
MIT -
PRIMA generates verifiable digital evidence: a canonical manifest, a timestamp proof anchored in the Bitcoin blockchain (via OpenTimestamps), and an independently verifiable certificate. FAIR4RS software: public JSON Schema, JSON-LD metadata, OpenAPI spec, and a Model Context Protocol (MCP) server for LLM agents.
Apache-2.0 -
opencode-routinesgithub.com/4nkitd/opencode-routinesupdated this year
Open Routines is a single Go binary that exposes a Model Context Protocol (MCP) server. It lets an OpenCode agent create routines — one-time or recurring tasks — that are executed later by a fresh OpenCode instance, then independently verified by a second one.
GPL-3.0 ★ 1 -
Official Model Context Protocol (MCP) server for SPHIOR AI Governance — let your AI agent (Claude, Cursor, Cline, Windsurf, Zed, VS Code) record its own executions as tamper-evident, independently verifiable evidence (hash-only) for ISO 42001 / EU AI Act
npm Apache-2.0 -
Litigation intelligence MCP server that detects lawsuit risk before cases are filed. This server gives any MCP-compatible AI client — Claude, Cursor, Windsurf, Cline — direct access to pre-litigation signals drawn from 7 US government data sources, scored by 4 independent risk models into a composite **Litigation Probability Score (0-100)**.
MIT -
Patlytics — independent third-party profile of a public API surface, by API Evangelist. Patlytics is an AI-powered patent intelligence platform purpose-built for intellectual-property work, applying generative AI and large language models across the full patent lifecycle: invention harvesting and disclosure, patent application drafting, office-acti
-
One AI skill + MCP server for Claude Code, Codex and Hermes: Jev (TypeSafe) gates large-model turns (event triage, review verdicts, owner questions, tool choice), runs build-and-repair loops with independent review, routes models and skills, and guards Git steps. Script-only watch mode and a shared HTTP server.
MIT ★ 4 -
Local MCP broker for coding agents from Cursor, Antigravity, ZCode, Codex, and Claude Code. Configure agent pools, models, and effort across projects; run parallel workers in isolated workspaces and coordinate independent reviews with durable sessions and artifacts.
MIT -
Open-source, LLM-agnostic second brain. Connect any LLM (local llama.cpp, Claude, Codex, GPT, Gemini, Grok, Ollama) via MCP — memory lives as Markdown in YOUR GitHub repo, independent of any model. Desktop, VPS or bot VM. MIT.
MIT ★ 2 -
Openart — independent third-party profile of a public API surface, by API Evangelist. OpenArt is an all-in-one AI creation platform for generating and editing images, video, audio, and 3D content from a single workspace. It aggregates leading generative models (Seedance, Google Veo, Sora, GPT Image, Kling and others) and adds tools for consistent c
-
Rindler — independent third-party profile of a public API surface, by API Evangelist. Rindler is a Y Combinator (Summer 2026) company that operates a hosted Model Context Protocol (MCP) server turning any pre-onboarded website — including sites that have no API — into a deterministic, typed set of tools that AI agents can reliably use.
-
sqlpeekactive
MCP (Model Context Protocol) server that gives an AI agent live, read-only access to SQL Server databases using the connection strings already in your codebase, with EF Core entity-to-table/view mapping built in. Read-only is enforced in independent layers; optional HTTP transport, per-query audit logging, and CI-exportable EF mappings support central team deployment.
nuget -
Open-source meeting rooms with live transcription, an AI assistant that answers into the meeting, written minutes, and your own coding agent (Claude Code, opencode) in the room over MCP. Self-host on AWS or use kelabo.me. Model- and supplier-independent.
npm MIT ★ 3 -
Turn Obsidian inbox notes into checked, linked knowledge cards: one model drafts, an independent reviewer checks each card against the source, code writes the vault in one recoverable step. Daily FSRS review. Agent Skill, MCP or CLI. 把 Obsidian 收件箱笔记变成经独立复核、互相关联的知识卡片,并用 FSRS 每日复习。
MIT -
Security infrastructure your AI can't be — deterministic, daily CVE intel past your model's training cutoff, whole-repo-aware, author-independent, and shift-left: secure_prompt secures the prompt before code generation. The security MCP for vibe coding: 670 rules, 39 tools, CLI + doctor for Next.js, Supabase, Clerk, Stripe, Prisma, Hono & MCP.
npm Apache-2.0 ★ 6 -
Selvedgeno update data
**Persistent decision memory for AI coding agents.** Selvedge records why code changed, which approaches were rejected, and when decisions deserve another look, so future sessions can retrieve that context before editing. Query a function, database column, API route or dependency instead of reconstructing its history from an old conversation. Claude Code, Codex, Cursor, Copilot, Gemini CLI and Windsurf can connect through MCP. The CLI works independently. Decisions live in a local SQLite store, with no required hosted account and no LLM in the core storage or retrieval path. A saved explanation is testimony supplied by a person or agent. Selvedge does not extract hidden model reasoning, verify that an explanation is true, or guarantee that an agent will consult it. [Compatibility and capabilities](https://selvedge.sh/reference/compatibility/) · [56-second technical demo](https://youtu.be/wXoA9htThAM)
smithery -
Tetheredno update data
Control Mac power modes, prevent sleep, keep your Mac awake, and manage background apps during AI coding, builds, rendering, and local model inference. Tethered lets your AI assistant discover and apply saved profiles for Low Power, Automatic, or High Power mode where supported; display brightness; fan settings; and keep-awake behavior. Profile settings can deprioritize or suspend selected background apps, including policies triggered by memory pressure. Inspect memory pressure, RAM and swap usage, session status, and task safeguard warnings. Finite sessions expire automatically; unlimited sessions require an explicit end. Power settings describe requested controls, not independently measured hardware state. Requires an Apple Silicon Mac running macOS 15 or later, Tethered 1.2.0+ installed and running under the same macOS account, Pro access, AI task sessions enabled, and permissions required by the selected profile. Runs locally over stdio. Intel Macs and cloud-only clients are unsupported. No connection credentials or saved profiles are included.
smithery -
the-metis-fca-handbook-ai-harness-mcpno update data
# Metis FCA Handbook AI Harness — MCP Server An MCP (Model Context Protocol) server that integrates the Metis FCA Handbook AI Harness into Claude Desktop and other MCP-compatible agents. **Tool name:** `evaluate_fca_handbook_applicability` Use this tool to analyze FCA Handbook applicability for a product, service, or firm. Returns structured compliance reasoning with verbatim handbook citations. ## Why choose The Metis FCA Handbook AI Harness? - **Efficiency** Multiplies effectiveness of compliance advice. Saves £80+ in token fees per Harness run. - **Deals with "Hard Problem"**, in which LLMs' token incentives prioritise training data so results are unreliable. - **Verbatim citations** Quotes verbatim entries from the FCA Handbook. Other AI systems struggle to do this. - **Matches real-world need** You do not have to start off knowing which sections you are looking for. Carries out structured searches across all 10,000+ FCA Handbook entries. - **Secure Design** Harness compartmentalisation, one-shot structure, and statelessness fits natively with emerging AI agent security standards such as OWASP Top 10 for Agentic Applications 2026. - **AI Accessible** Integrates easily with AI workflows and agents. Your LLM can use it as a tool. ## Design Principles The Harness is built on proven principles: - **Stateless** — Each request is independent; no session coupling - **One-shot** — Complete analysis in a single call; no multi-turn state - **Clear contract** — Explicit input/output schemas for easy integration - **Hosted** — Single canonical source; no version drift or stale data ## Use Cases ### Compliance AI Platforms Embed FCA reasoning as a service within your compliance platform. Users ask natural-language questions; your platform calls the Harness and presents structured reasoning. ### AI Agent Workflows Agents building compliance workflows can include FCA Handbook reasoning as a composed tool—no external API calls, just MCP configuration. ### Compliance Review Automation Integrate into document review or due-diligence pipelines. Automatically screen new rules against FCA applicability. ## For Regulatory Screening FS firms screening MCP servers will find: - **Simple model:** Stateless, no hidden state, no background jobs - **Clear contract:** Explicit input schema, output schema, error modes - **Transparent updates:** Version pinning; no automatic upgrades - **Single point of failure:** If the Harness is down, it is obvious; no cascading config issues - **Audit-friendly:** All calls logged centrally, not distributed
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 -
@purili/mcp-serveractive
Free web search and indexed page context from Purili's independent index, exposed as MCP tools.
npm MIT -
Open-source task commons where AI agents do bounded public-good work, publish evidence, and review results.
MIT -
FinFreedomgithub.com/nugrahalabib/FinFreedomupdated this year
Indonesia-native personal finance OS — budgeting, FIRE planning (Monte Carlo), investments, and a first-class MCP server for AI agents. Next.js 15 + Prisma + TypeScript.
MIT -
Harness for AI coding agents: an actor-critic loop with executed checks, bounded file scope, an independent reviewer and independent acceptance tests. CLI and MCP server.
npm Apache-2.0 -
A deterministic first-pass filter for unsupported claims in LLM output, computed without calling another LLM. Not a standalone hallucination detector. A spec plus reference implementation, shipped as touchstone-mcp.
pypi Apache-2.0 -
Provider-independent MCP with ERE gates and Ed25519
NOASSERTION ★ 1