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.
-
Let your AI trading agent trade on your broker or exchange within hard limits: order size, order rate, profit-and-loss stop and kill switch. Free, open-source, runs on your computer. Checks every order before it is sent.
Apache-2.0 ★ 3 -
agent-policy-gateway-mcpgithub.com/AiAgentKarl/agent-policy-gateway-mcpupdated this year
Compliance & guardrails for AI agents — PII filtering, audit logging, GDPR/AI Act checks, kill switch
MIT -
MCP server to browse, rank and subscribe to three.ws copy-trade signal feeds with a kill switch.
Apache-2.0 ★ 9 -
evidra-lockgithub.com/vitas/evidra-lockupdated this year
MCP Kill-switch for AI agents. Validates infrastructure operations before execution. Fail-closed. Evidence-backed.
Apache-2.0 ★ 8 -
Kali Linux container exposed to AI agents via MCP, behind a gateway with a network kill-switch
MIT ★ 1 -
ratgithub.com/hekmon/ratactive
RAT (Remote Agent Terminal): persistent shells for AI agents over MCP and mutual TLS, tmux under the hood, with an operator kill switch
MIT ★ 2 -
MCP server for the Binance Spot + Wallet REST API — deposits, withdrawals, every trade, balances, market data, and kill-switch-gated spot/OCO/TWAP/convert trading with a plain API key (83 tools, no OAuth, no withdrawals).
Apache-2.0 ★ 1 -
accela-mcpgithub.com/Donatoni/accela-mcpupdated this year
MCP server for the Accela Civic Platform - safe-by-default, read-only out of the box, with opt-in write groups for records, inspections, documents, workflow, and payments. Encrypted token storage, dry-run writes, YAML kill-switch.
NOASSERTION ★ 1 -
MCP server and Python CLI for Google Ads — GAQL reporting, plus campaign, budget and bid changes an AI agent can only make through a preview you approve, with guardrails, a kill switch and a full audit log.
MIT -
Approvals, spend limits and a kill switch for AI agents, set up in one command: npx immiscible init. See it first, offline and with no account: npx immiscible try. Installs a fail-closed Claude Code hook, prints MCP setup for Claude Code, Cursor and VS Co
npm MIT -
Give an AI agent a real Solana wallet without giving it your money. The agent gets a spending allowance the SPL Token program enforces on-chain, plus guardrails (per-tx cap, daily cap, recipient and host allowlists, expiry, kill switch), x402 payments, an
npm Apache-2.0 -
Meta Ads MCP server + Python client for the Marketing API. An AI agent can read Facebook and Instagram campaigns, ad sets and ads and propose changes; every write goes through a preview a human approves, with guardrails, a kill switch and an audit log.
MIT