images_search
Searches images in this workspace by visual content using vector embeddings (Voyage multimodal-3). Pass a text description; returns ranked file_ids with cosine scores and presigned download URLs. Up to 50 results.
This record as markdown: /tools/io-github-saloprj-dialogbrain/images-search.md
What images_search does on Dialogbrain
AI agents call images_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 number of results. |
query | string | Yes | Text description of what you're looking for (3-4000 chars). |
mime_type | string | — | Optional — restrict to a specific image MIME (e.g. "image/png"). Filter is applied after RAG (same caveat as collection_id). |
collection_id | integer | — | Optional — restrict to images attached to this collection. Filter is applied after RAG, so you may get fewer than `limit` results; pass a larger limit to broade |
score_threshold | number | — | Minimum cosine similarity (0.0 returns all, higher = stricter). |
Parameters from the server's own tool schema.
Why images_search is rated Low
This is a search/query operation that retrieves and ranks existing image metadata and provides download URLs. It has no side effects—it does not create, modify, delete, or execute code.
From the tool's definition Tool description states it 'Searches images in this workspace by visual content' and 'returns ranked file_ids with cosine scores and presigned download URLs.' The verbs 'searches' and 'returns' indicate data retrieval with no modification, deletion, or…
Attacks that exploit this kind of access
The rule that runs images_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 images_search, this is the rule to start with:
images_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 images_search call is checked against it from then on.
Questions about images_search
Searches images in this workspace by visual content using vector embeddings (Voyage multimodal-3). Pass a text description; returns ranked file_ids with cosine scores and presigned download URLs. Up to 50 results. It is categorised as a Read tool in the Dialogbrain MCP Server, which means it retrieves data without modifying state.
images_search accepts 5 parameters: limit, query, mime_type, collection_id, score_threshold. Required: query. 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 images_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.
images_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 images_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 images_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.
images_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