search_decisions
AI agents call search_decisions to retrieve information from JurisCassation MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
search_decisions appears to be a query/search function that retrieves Court of Cassation decisions without modifying them. The server is explicitly designed for accessing and searching legal decisions, not altering them. While the empty description introduces some ambiguity, the context from sibling tools and the server's stated purpose strongly indicates this is a read-only search operation.
From the tool's definition Tool name 'search_decisions' combined with server description stating it 'Provides AI agents with access to Moroccan Court of Cassation decisions through search tools' and sibling tools like 'search_local', 'get_stats', 'list_chambers' which are clearly…
Attacks that exploit this kind of access
search_decisions. It is categorised as a Read tool in the JurisCassation MCP Server MCP Server, which means it retrieves data without modifying state.
Register the JurisCassation MCP Server MCP server in PolicyLayer and add a rule for search_decisions: 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 JurisCassation MCP Server. Nothing to install.
search_decisions 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 search_decisions 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 search_decisions. 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.
search_decisions is provided by the JurisCassation MCP Server MCP server (slapash/juriscassation-api). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →