Search across thread titles, tags, and message content. Searches within a specific project or across all projects. Returns matching thread summaries. Args: - query (string): Search term - project_id (string, optional): Limit search to a specific project Returns: Array of matching thread summaries.
AI agents call dialogue_search 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.
dialogue_search is a search/query function that retrieves information from threads and projects without any side effects. It takes a search query and optional project_id as parameters and returns matching results. This is a classic Read operation—data retrieval with no capability to modify, delete, execute, or create resources.
From the tool's definition Tool description states it 'Search[es] across thread titles, tags, and message content' and 'Returns matching thread summaries.' The operation is purely retrieving/querying existing data with no modification, creation, deletion, or execution of commands.
Attacks that exploit this kind of access
Search across thread titles, tags, and message content. Searches within a specific project or across all projects. Returns matching thread summaries. Args: - query (string): Search term - project_id (string, optional): Limit search to a specific project Returns: Array of matching thread summaries. 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_search: 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_search 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_search 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_search. 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_search 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 →