Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/chaselen/knife4j-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/chaselen/knife4j-mcp/knife4j-mcp)<a href="https://agentmods.dev/mcp/chaselen/knife4j-mcp/knife4j-mcp"><img src="https://agentmods.dev/badge/mcp/chaselen/knife4j-mcp/knife4j-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/chaselen/knife4j-mcp/knife4j-mcp"><img src="https://agentmods.dev/badge/mcp/chaselen/knife4j-mcp/knife4j-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
knife4j-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{ "knife4j-mcp": { "command": "npx", "args": [ "-y", "@chaselen/knife4j-mcp" ] } }
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 9 lines scan A e673c180d7f1
knife4j-mcp is an MCP server published in the GitHub repository chaselen/knife4j-mcp (0 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
swagger-docs-mcp
Read-only MCP server for querying live Swagger 2.0 API documentation, including Knife4j / Springfox doc.html entry points. Runs locally from the swagger-docs-mcp npm package.
openapi-mcp-server
A Model Context Protocol (MCP) server that exposes OpenAPI endpoints as MCP tools. Runs locally from the @lucid-spark/openapi-mcp-server npm package.
mcpgate
A stateless gateway that turns any OpenAPI spec into MCP tools on the fly. Runs locally from the mcpgate Python package.
tieline
Static FE-BE contract-drift checker: finds frontend calls the backend does not expose. CLI + MCP. Runs locally from the @nugehs/tieline npm package.
knife4j-mcp
MCP server for Knife4j OpenAPI documentation. Runs locally from the knife4j-mcp npm package.
mcp-server
Model Context Protocol (MCP) server for AI-assisted development of CAP applications. Runs locally from the @cap-js/mcp-server npm package.