search_links
Search links/URLs shared across the workspace — by type, owner, or associated contact. For files use search.files; for message content use search.messages.
This record as markdown: /tools/io-github-saloprj-dialogbrain/search-links.md
What search_links does on Dialogbrain
AI agents call search_links 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 | — | Maximum links to return. |
owner | string | — | Link owner: 'self' (user's own) or 'contact' (from others). OMIT to include links regardless of owner. |
query | string | — | What to search for in shared links. |
link_kind | string | — | Filter links by type. OMIT to include all kinds — picking a value narrows the search and is a common cause of zero-result mistakes. |
contact_hint | string | — | Name hint to filter links for a specific contact. OMIT to skip. |
Parameters from the server's own tool schema.
Why search_links is rated Low
This tool queries and retrieves existing link data from the workspace without modifying, deleting, or executing anything. It is purely a read operation that enables discovery of shared URLs with various filtering parameters. The low severity reflects minimal blast radius — even if misused by an AI agent, it only exposes already-shared links within the workspace.
From the tool's definition Tool name is 'search_links' and description states 'Search links/URLs shared across the workspace' with filtering options by 'type, owner, or associated contact'.
Attacks that exploit this kind of access
The rule that runs search_links 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 search_links, this is the rule to start with:
search_links 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 search_links call is checked against it from then on.
Questions about search_links
Search links/URLs shared across the workspace — by type, owner, or associated contact. For files use search.files; for message content use search.messages. It is categorised as a Read tool in the Dialogbrain MCP Server, which means it retrieves data without modifying state.
search_links accepts 5 parameters: limit, owner, query, link_kind, contact_hint. 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 search_links: 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.
search_links 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_links 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_links. 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_links 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