Search through municipal codes and ordinances
AI agents call search_municipal_codes to retrieve information from MunicipalMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Searching municipal codes is a read-only operation that queries a database of legal documents and returns matching results. There are no side effects, no data modification, no code execution, and no destructive actions. The worst-case misuse would be excessive queries or information gathering, which poses minimal security risk.
From the tool's definition Tool name 'search_municipal_codes' and description 'Search through municipal codes and ordinances' indicate a search operation that retrieves and queries legal documents without modifying or executing operations.
Attacks that exploit this kind of access
Search through municipal codes and ordinances. It is categorised as a Read tool in the MunicipalMCP MCP Server, which means it retrieves data without modifying state.
Register the Municipal MCP server in PolicyLayer and add a rule for search_municipal_codes: 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 MunicipalMCP. Nothing to install.
search_municipal_codes 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_municipal_codes 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_municipal_codes. 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_municipal_codes is provided by the Municipal MCP server (skatterbrainz/municipalmcp). 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 →