notes_search
Full-text search in your notebook. By default searches only your own notes. Pass filter_agent_id=<int> to search another agent's notebook, or "all" (or "*") for workspace-wide. Or list all notes for a person/thread by scope_ref_id.
This record as markdown: /tools/io-github-saloprj-dialogbrain/notes-search.md
What notes_search does on Dialogbrain
AI agents call notes_search to retrieve information from Dialogbrain without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | integer | — | Max results (default 10, max 50) |
query | string | — | Text to search for in note keys and values. Optional if scope_ref_id is provided. |
scope | string | — | Limit search to scope |
scope_ref_id | string | — | Filter by specific thread_id or person_id. If provided without query, lists all notes for that ref. |
filter_agent_id | string | — | Optional. Omit to search only your own notes. Pass a numeric agent_id as a string (e.g. "57") to search another agent's notebook (read-only). Pass "all" or "*" |
Parameters from the server's own tool schema.
Why notes_search is rated Low
This tool retrieves and queries existing note data without any side effects or modifications. The ability to search across different scopes (own notes, specific agents, workspace-wide) does not elevate it beyond a Read operation. The severity is low because search operations on notes typically have minimal blast radius—they return information but do not alter system state or trigger external actions.
From the tool's definition Tool performs 'full-text search' in a notebook with options to filter by agent or workspace. The description uses query-oriented language: 'search', 'list all notes'. No mention of creating, modifying, or deleting data.
Attacks that exploit this kind of access
The rule that runs notes_search safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Dialogbrain, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For notes_search, this is the rule to start with:
notes_search is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Dialogbrain, apply this rule, and every notes_search call is checked against it from then on.
Questions about notes_search
Full-text search in your notebook. By default searches only your own notes. Pass filter_agent_id=<int> to search another agent's notebook, or "all" (or "*") for workspace-wide. Or list all notes for a person/thread by scope_ref_id. It is categorised as a Read tool in the Dialogbrain MCP Server, which means it retrieves data without modifying state.
notes_search accepts 5 parameters: limit, query, scope, scope_ref_id, filter_agent_id. The full parameter table on this page comes from the server's own tool schema.
Register the Dialogbrain MCP server in PolicyLayer and add a rule for notes_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 Dialogbrain. Nothing to install.
notes_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 notes_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 notes_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.
notes_search is provided by the Dialogbrain MCP server (https://api.dialogbrain.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Dialogbrain, and thousands of servers like it.
This server
Across the catalogue