FRENES

Aggregators and gateways · MCP server

AISIX AI Gateway: MCP server, setup and security

AISIX AI Gateway is an open-source MCP server that lets an AI agent access upstream MCP servers through tool permissions, guardrails and rate limits. Its repository has 204 stars and its last commit is from October 22, 2026 and it is licensed under Apache-2.0.

Actively maintained

What AISIX AI Gateway does

According to its repository: “Self-hosted MCP gateway fronting upstream servers with per-tool access control, guardrails, rate limits and usage logs; also proxies LLM and A2A agent traffic.”

An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. AISIX AI Gateway is listed under Aggregators and gateways, a category of 141 servers in the directory, where it ranks #42 by stars.

Topics declared by the repository: ai-agents, ai-gateway, anthropic, bedrock, gateway, gemini.

Installing and connecting AISIX AI Gateway

Distribution modes declared in the official MCP registry:

  • Docker (OCI) image

Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: Rust.

Security: what to check

An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.

None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to AISIX AI Gateway. That does not replace reading the code.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on April 17, 2026, the api7/aisix repository has 204 stars and 43 forks, with 54 open issues. It has more stars than 78% of the servers in the directory. It received changes this month. Version published in the registry: 1.3.0 (September 21, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

PaperclipPaperclip : 106.8K106.8KOpenWork MCP GatewayOpenWork MCP Gateway : 24.2K24.2KGitDiagramGitDiagram : 18.4K18.4KAIHOTAIHOT : 8.5K8.5KBasebalance.cloud — x402 RPCBasebalance.cloud — x402 RPC : 7.5K7.5KTreg.toTreg.to : 6K6KMockserver monorepoMockserver monorepo : 5K5KDBHubDBHub : 3.7K3.7KAISIX AI GatewayAISIX AI Gateway : 204204
GitHub stars of the most followed servers in the category (log scale); AISIX AI Gateway in orange. Checked October 25, 2026.

Verdict

AISIX AI Gateway is a reasonable choice; check the points below before connecting it.

Strengths

  • Active project: recent commit
  • Widely followed: 204 stars
  • Listed in the official MCP registry
  • Permissive licence (Apache-2.0)

Frequently asked questions

How do I install AISIX AI Gateway?

AISIX AI Gateway is distributed as Docker (OCI) image. Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of api7/aisix.

Is AISIX AI Gateway free?

The code is published under the Apache-2.0 licence and can be used free of charge.

Is AISIX AI Gateway safe?

No risk signal found (system access, secrets, licence, abandonment). As with any MCP server, keep rights minimal and read the code before sensitive use.

Is it an official server?

Nothing says so: it is a project published by api7 on GitHub. Check who maintains it before giving it access.

What are the alternatives to AISIX AI Gateway?

In the same category: GitDiagram, Mockserver monorepo, Paperclip, and Basebalance.cloud — x402 RPC & MCP gateway. GitDiagram and Mockserver monorepo score higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score