List all analyses for a project with trend data
AI agents call list_project_analyses to retrieve information from MCP Code Analyzer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries historical analysis data for a project, returning trend information without creating, modifying, deleting, or executing any operations. It has no side effects and presents no blast radius if misused by an AI agent beyond potentially exposing analysis metadata.
From the tool's definition Tool name 'list_project_analyses' and description 'List all analyses for a project with trend data' indicate a retrieval operation with no modification or execution of code. The verb 'List' is a classic read operation.
Attacks that exploit this kind of access
List all analyses for a project with trend data. It is categorised as a Read tool in the MCP Code Analyzer MCP Server, which means it retrieves data without modifying state.
Register the MCP Code Analyzer MCP server in PolicyLayer and add a rule for list_project_analyses: 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 MCP Code Analyzer. Nothing to install.
list_project_analyses 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 list_project_analyses 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 list_project_analyses. 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.
list_project_analyses is provided by the MCP Code Analyzer MCP server (polocap/mcp_security). 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 →