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.
-
@ebenova/scope-guard-mcpgithub.com/ebenova/scope-guard-mcpupdated this year
MCP server for Scope Guard — AI-powered contract enforcement and scope violation detection. Detects scope creep in client messages and generates formal change orders.
npm MIT -
scope-guard-mcpgithub.com/dgtalquantumleap-ai/scope-guard-mcpupdated this year
Scope Guard MCP — AI contract scope enforcement and change order generation
-
leakrank-guardgithub.com/ProtoTeemo/leakrank-guardupdated this year
Scans code changes for leaked secrets and insecure config, with actionable fixes for AI agents. MCP server, docs for the leakrank-guard npm package.
MIT -
CodeRef-AI:Vibe Coding 项目的治理外脑 | 安全、健康、变更守护平台 CodeRef AI: The Governance External Brain for Vibe Coding Projects | Security, Health, Change Guard Platform
NOASSERTION ★ 4 -
Local-first project memory for AI coding tools: extract codebase conventions into searchable Recipes, expose them through MCP, and enforce changes with Guard.
MIT ★ 3 -
site-abilities-mcpgithub.com/ademyavuzz/site-abilities-mcpupdated this year
Guarded WordPress abilities for MCP clients, with read-only defaults and recoverable changes.
GPL-2.0 ★ 1 -
OpenAI Codex integration for Signetry: MCP server + lifecycle-hook guard to govern coding-agent changes. Split from signetry-plugins.
Apache-2.0 -
Read-only dbt schema-change risk assessment with lineage, verified SQL evidence, guarded agents, MCP tools and reproducible evaluation.
MIT -
MCP server driving Ansys SpaceClaim headlessly through PyAnsys Geometry, plus a DSH plugin bundle. Guards the operations that report success without changing geometry.
MIT ★ 2 -
The tower of guard for parallel coding agents. Keeps parallel coding agents from stepping on each other. Claims, contracts and change notices over MCP.
cargo MIT ★ 4 -
Canvas extension for Claude Desktop: lets Claude read and edit your Canvas LMS courses with a course guard on every change. One-click install.
MIT -
Async Rust MCP server for the HPE Juniper Mist cloud — bearer-token auth, org/site-scoped tools, bounded responses, guarded WAN-edge change control
oci MIT ★ 1 -
The compiler's answers for Claude Code: who calls this, what breaks if I change it, which tests guard it. A code graph MCP server for C#, TypeScript, Java, Go, Rust and Python.
MIT -
Self-hosted agent memory in your Obsidian vault: an MCP server with hybrid search, link graph, change feed, tasks and guarded writes, for claude.ai, ChatGPT and Claude Code.
oci MIT ★ 18 -
Subscription/Renewal Guard — an agent flags price hikes, quiet usage and trial conversions and drafts one action with its evidence; nothing changes until a human clicks Approve. HACK47: OFFGRID entry.
MIT -
Unofficial fork of opencode-mcp: MCP server for OpenCode coding workflows, durable async jobs, project resources, and explicit user input, with V2 live-observation and guarded project-read changes
npm MIT -
Prove that what already worked still works after an agent changed the code. Picture checks, guards for fixed bugs, a pre-release walkthrough and known-good markers — as a CLI and as an MCP server.
npm MIT -
CLI for Ordo, an open-source decision engine. Write decisions as rule files, test and trace them, and see which decisions a change moves. Includes an MCP server for coding agents and Ordo Guard.
npm MIT -
MCP server that drafts ISO management-system documents clause by clause (Annex SL): grounding on the client's Word documents, exact-fidelity .docx output, change tracking and a runtime fidelity guard. Clause 4 complete (ISO 9001/14001/45001/37001).
MIT -
A Kiro Power and MCP server for AWS re:Invent attendees. It reads your code, locally or on GitHub, finds sessions to match, plans your week as a Kiro spec, guards every booking, and puts your seats in Apple and Google Wallet as boarding passes that alert you when a room or time changes. Unofficial; your badge is your ticket.
npm Apache-2.0 -
Agent triage, measured: does this edit need a human, or can the AI handle it? We measure whether the graph under the agent can reach the tests that guard a change (0.42 pooled, 7 repos) and ship the fail-closed gate that routes unproven maps to human verification. CLI · MCP · SARIF · in-engine on HydraDB.
MIT ★ 2 -
Vetono update data
93 agentic MCP tools + 49 specialist agents for every major AI CLI — self-learning, no API keys. Veto gives Claude Code, Codex CLI, Gemini CLI, Cursor, Windsurf, Zed, and JetBrains a council of specialist agents, persistent cross-platform memory, a self-learning router, CI/CD gates, and dependency-hallucination + decision-drift guards — all powered by your existing AI subscription. No separate API keys, no extra billing. **Highlights** - **Council debate** — multi-agent GREEN/YELLOW/RED verdicts on risky changes (LLM-backed via MCP Sampling, with deterministic fallback) - **Cross-platform memory & session handoff** — save on Claude, resume on Gemini or Codex; nothing needs re-explaining - **Self-learning router** — improves task routing from recorded outcomes - **Guards & gates** — CI gate, diff review, secrets scan, dependency-hallucination verification, decision-drift enforcement - **Compact mode** — advertise 9 tools instead of 93 and save ~16K context tokens; every tool stays callable **Links**: [GitHub](https://github.com/jigyasudham/veto) · [npm](https://www.npmjs.com/package/@jigyasudham/veto)
smithery -
LeakRank Guardno update data
Scans code changes for leaked secrets and insecure config, with actionable fixes for AI agents.
npm -
GoGuard - Intelligent Go code quality assurance MCP server with smart change detection and risk analysis
npm MIT -
Let an AI agent build and change your n8n workflows with a guaranteed way back: every write is backed up, version-checked, and verified by readback.
npm MIT ★ 6 -
SSH for AI agents (Claude Code, Codex, Cursor) where reads run freely and every change needs a signed human approval that the server itself enforces.
Apache-2.0 -
Protect customer promises when Jira plans change. RippleGuard connects commitments to Jira work, flags delivery risks, and explains the evidence through Rovo, Teamwork Graph, and read-only MCP tools. Built on Atlassian Forge for Codegeist 2026.
-
OSBO.AI policy at the point of generation: an MCP server for Claude Code, Cursor and OpenAI-compatible agents (validate changes, check a dependency, match a snippet against the corpus, explain licence obligations), plus a pre-commit hook and VS Code wirin
npm MIT -
bumpguard-mcpgithub.com/appcreationsca/bumpguard-mcpupdated this year
Guard your dependency bumps: an MCP server that tells your AI agent which parts of YOUR code break when you upgrade a dependency, and verifies AI-written code against the installed API - static analysis, never runs third-party code.
pypi MIT ★ 5