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.
-
A Model Context Protocol server for Kingdee OA approval automation
npm MIT -
@archiesun/dingtalk-mcp-task-approvalgithub.com/archiesun/dingtalk-mcpupdated this year
钉钉任务审批MCP服务器 - 待办任务、OA审批、审批附件
npm MIT -
approvals-mcpgithub.com/larioscow/approvals-mcpupdated this year
An MCP approval gate for AI agents
MIT -
An example in creating a MCP server. For this example, data will be recent FDA approvals of drugs.
MIT -
MCP server that stops an AI agent from sending anything until a person approves it
MIT -
shopify-approver-mcp-servergithub.com/umerkhan95/shopify-app-approverupdated this year
MCP server for AI agent integration (Claude Code, Windsurf, OpenCode)
cargo MIT -
Make an AI agent wait for a person's approval before it acts. MCP server + client for the Vibez.now approval API.
MIT -
mcp-approvalgithub.com/zavora-ai/mcp-approvalupdated this year
Approval MCP Server — multi-stage approval workflows for legal and media-content agents: configurable workflow templates, stage rules (all-of/any-of/quorum), decisions, delegation, escalation, SLA clocks, and an immutable audit trail
cargo Apache-2.0 -
telegram-approvergithub.com/codex-k8s/telegram-approverupdated this year
📨 Telegram approver for yaml-mcp-server: delivers high-risk action requests to one trusted chat, supports Approve/Deny/Deny-with-reason (text or voice), handles concurrent approvals, and sends async webhook decisions with correlation IDs, timeouts, and health endpoints.
MIT -
Autonomous image generation agent using MCP servers with built-in approval logic for bulk requests. Automatically generates single images and pauses for cost approval when handling multi-image tasks.
-
A review queue for AI agents: they submit work over MCP or REST, you approve, edit or send it back, and they pick up your decision.
MIT -
Local-first approval plane for coordinating AI coding harnesses: human gate on irreversible actions, SQLite audit trail, MCP facade.
MIT -
本地素材对照审批工具:原图/成品并排审批,一键标记+问题标签+圈图标注+批量操作,结果可导出 JSON/CSV。自带演示素材,支持 MCP 与命令行,可被 AI agent 直接驱动。
MIT ★ 1 -
Approval Risk Auditor — audit EVM wallets for unlimited/stale token approvals and get ready-to-sign revoke calldata. Apify Actor + MCP server.
MIT -
Let AI agents notify you on LINE and wait for your approval (Cloudflare Worker + MCP server + CLI)
MIT -
MCP-Shipping-Order-System-with-Approval-Workflowgithub.com/SahSanjeev/MCP-Shipping-Order-System-with-Approval-Workflowupdated this year
A Streamlit-based web application that demonstrates a shipping order system with an approval workflow for large orders. Features Order Submission: Submit shipping requests with container count and destination Automatic Approval: Orders with 5 or fewer containers are auto-approved Approval Workflow: Large orders (5+ ) require manual approval
-
Human approval requests for agent actions: expiring, single-use decisions. Trusted executors must enforce the gate; not a same-user security boundary.
npm MIT -
A human review and approval queue for AI agent output, with a Node.js SDK, CLI, MCP server, audit log, and Cloudflare adapters.
npm MIT -
MCP server that holds irreversible agent actions until a human approves them, with a hash-chained audit log.
MIT -
MCP server where AI reads freely but every write is a human-approved plan: diffs, budget caps, drift refusal, undo, audit log.
MIT -
MCP server implementing a human-in-the-loop approval gate for AI agents, with a tamper-evident hash-chained audit log.
MIT -
Holds risky AI agent tool calls for a person, ties each approval to one exact request, and logs every decision. 210 checks, synthetic data.
MIT -
An AI agent prepares an action, only a human approves the exact preview, then the agent runs it once. MCP server + Agent Skill + reusable gate. MIT.
MIT -
Claude agent over MCP that drafts HubSpot updates and cannot write until a signed Slack approval binds to the exact change. Evals, attack suite, retries, audit log. Synthetic data.
MIT -
Personal assistant add-on scans sources (email, texts, finance, etc) and recommends a queue of cards with scripted follow-up actions.
MIT ★ 1 -
PR blast radius analyzer: a 0-1 risk score for every pull request so AI-reviewed, low-risk PRs auto-approve into the merge queue. GitHub Action, CLI, Claude Code plugin, MCP server.
npm MIT ★ 3 -
confirm-mcpgithub.com/confirm-ai/confirm-mcpupdated this year
MCP server for human approvals. Any MCP agent gets a request_approval tool: pause on risky actions, a human approves or edits, then resume.
MIT ★ 2 -
Approval-gated Streamable HTTP MCP for Alexa+: plan, approve, execute, verify — clean-room hackathon demo.
MIT -
Spend approval gate for AI agents — enforce budget limits, per-asset caps and human-in-the-loop thresholds before an agent moves money, with a signed audit hash.
npm MIT -
mayigithub.com/asiraky/mayiactive
Secure, exact-action approvals for software agents.
Apache-2.0 -
Approval workflows for AI agents
npm MIT ★ 33 -
Impri MCP server — human-in-the-loop approval inbox for AI agents
npm MIT -
mcp-governance-policygithub.com/zavora-ai/mcp-governance-policyupdated this year
Governance Policy MCP server for ADK-Rust Enterprise — policy evaluation, approvals, simulation, and audit evidence
cargo Apache-2.0 -
mcp-workflowgithub.com/zavora-ai/mcp-workflowupdated this year
Workflow engine MCP server — state machines, approvals, task management, case routing, work orders, change control
cargo Apache-2.0 -
Open-source approval gateway for AI agent tool calls: policy, human approval, one-time execution grants, and audit evidence.
npm Apache-2.0 ★ 1 -
Real-time audit and approval system for Claude Code tool calls.
MIT ★ 19 -
MCP server for Raposa Aval: request_human_approval — a named person approves or rejects, silence is not consent, hash-chained audit log. Local (uvx) or remote at dcescrypt.com/api/mcp
pypi MIT ★ 1 -
@jabee/mcpactive
Ask a person to approve something on WhatsApp, from an AI agent, over MCP.
npm MIT -
@signedapproval/mcp-servergithub.com/alexfloyd13/signedapprovalupdated this year
MCP server for SignedApproval — human-in-the-loop approval for AI agents
npm MIT -
mcp-server-viahumanupdated this year
MCP server for ViaHuman - Add human approval gates to LLM workflows
npm MIT -
notiworld-cliactive
Notify yourself or ask for approval from scripts and AI agents: a Notiworld CLI and MCP server.
npm MIT -
sesame-mcpgithub.com/lavanpuri1999/sesameupdated this year
MCP server exposing the Sesame human-in-the-loop approval API as an agent tool
pypi MIT -
The approval inbox for AI agents. Approve, deny or answer from your terminal, desktop or phone. Works with Claude Code, Codex, Cursor, omp and any MCP agent.
NOASSERTION ★ 3 -
psephos-mcpactive
MCP server for Psephos: agents ask for your approval on your phone and wait for the answer.
npm MIT -
bonanza-mcpgithub.com/c6zks4gssn-droid/bonanza-labs-websiteupdated this year
MCP server for AI agent payments — spending firewall, budget checks, and approval flows via the Model Context Protocol
pypi Apache-2.0 -
Human approvals for agent actions. Gate refunds with Auth0-verified, exact-operation approval and resume them as MCP Tasks. Experimental TypeScript reference implementation with a hosted demo. Unofficial.
MIT -
@decionis/presence-mcpupdated this year
MCP server for the Presence Human Approval Gate: pause an AI agent's consequential tool call until a named person approves it, with a sealed Presence Record either way.
npm Apache-2.0 -
Open-source authority layer for AI agents: who may approve what, how decisions escalate, and the evidence.
Apache-2.0 -
MCP Server for controlled command execution with interactive approval system in trusted development environments
npm BSD-3-Clause -
agent-guard-mcpgithub.com/dygogogo/agent-guard-mcpupdated this year
MCP Guard Server - Budget control, approval workflows and audit logging for AI agents (Claude Code, Cursor, ChatGPT)
MIT -
@cheqpoint/mcpactive
Cheqpoint MCP server - human-in-the-loop approval tools for Claude, Cursor, and any MCP client
npm MIT -
The open decision record for AI agents: playbook, evidence, rules, earned autonomy, approvals, outcomes, flows and MCP.
pypi Apache-2.0 -
olivetin-mcpgithub.com/vaddisrinivas/olivetin-mcpupdated this year
Hardened MCP SSE server for OliveTin — full proto 1:1 coverage, built-in approval, auth support
MIT ★ 1 -
agentledgergithub.com/agentledgerhq/agentledgerupdated this year
Budget controls, approvals and logs for AI agents using a Credit Card. Single Go binary, zero dependencies.
npm ★ 4 -
Lightweight remote execution harness for AI agents: scoped tools, approvals, and a URL whitelist over CLI, MCP, or HTTP
npm Apache-2.0 -
Human-in-the-loop review and approval for AI agents. MCP server at mcp.agentfabric.dev
-
palisadegithub.com/palisadescan/palisadeupdated this year
Read-only onchain security MCP — scan any contract, approval, or token before you sign. Robinhood Chain + EVM + Solana.
MIT -
Standalone L1 supervisor agent for flux7-mesh — rules engine + pluggable LLM (Ollama, Anthropic, Claude Code MCP callback). Auto-resolves approval gates.
Apache-2.0 ★ 1 -
Self-hosted studio to review, approve and publish social content with your team and your AI agents: frame-accurate comments, approvals bound to the exact file, a calendar that publishes to nine networks, and an MCP server for Claude.
NOASSERTION ★ 5 -
whatsapp-mcpgithub.com/meharajM/whatsapp-mcpupdated this year
Human-in-the-loop approvals & notifications for AI agents via WhatsApp (MCP server).
npm ISC