AI agents call get_spring_project to retrieve information from Springdocs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries project information from Spring documentation. The 'get_' prefix and retrieval-focused naming convention, combined with the context of a documentation server (springdocs-mcp), indicates a read-only operation that returns data without modifying or deleting anything. No code execution, financial impact, or destructive capabilities are evident.
From the tool's definition Tool name 'get_spring_project' and description prefix 'Récupère les détails complets d[...]' indicate data retrieval. The incomplete description suggests fetching complete project details, which is a read operation with no side effects.
Documented attack patterns abuse exactly the kind of access get_spring_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Springdocs, and nothing reaches the server without passing your rules. This is the rule we recommend for get_spring_project:
{
"version": "1",
"default": "deny",
"tools": {
"get_spring_project": {}
}
}get_spring_project is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Récupère les détails complets d. It is categorised as a Read tool in the Springdocs MCP Server, which means it retrieves data without modifying state.
Register the Springdocs MCP server in PolicyLayer and add a rule for get_spring_project: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Springdocs. Nothing to install.
get_spring_project is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_spring_project rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_spring_project. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_spring_project is provided by the Springdocs MCP server (tky0065/springdocs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Springdocs, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
12 Springdocs tools catalogued and risk-classified — across an index of 43,000+ MCP servers.