List all dialogue projects in the shared workspace. Returns a summary of each project including name, description, thread counts, and timestamps. Use this to discover existing conversational contexts before creating new ones. Args: - response_format (string, optional):
AI agents call dialogue_list_projects to retrieve information from Claude Dialogue MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward query/list operation that discovers and retrieves metadata about existing projects. It reads data from the shared workspace without altering, creating, or destroying anything. The blast radius of misuse is minimal—an AI could only learn about existing conversation contexts, not act upon them destructively or financially.
From the tool's definition Tool description states 'List all dialogue projects' and 'Returns a summary of each project' — retrieval-only operation with no modification, creation, or deletion of data. No side effects or state changes.
Attacks that exploit this kind of access
List all dialogue projects in the shared workspace. Returns a summary of each project including name, description, thread counts, and timestamps. Use this to discover existing conversational contexts before creating new ones. Args: - response_format (string, optional):. It is categorised as a Read tool in the Claude Dialogue MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude Dialogue MCP server in PolicyLayer and add a rule for dialogue_list_projects: 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 Claude Dialogue MCP. Nothing to install.
dialogue_list_projects 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 dialogue_list_projects 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 dialogue_list_projects. 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.
dialogue_list_projects is provided by the Claude Dialogue MCP server (themethodolojeeorg/claude-dialogue-mcp). 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 →