oe_collections_classify
Predict hashtags for every unsorted chat (or all chats with reclassify_all). Combines curated keyword rules with a per-tag log-odds-ratio signature trained from your existing memberships. Returns the proposed plan as JSON; use oe_collections_bulk_apply to actually write.
This record as markdown: /tools/htlin222-openevidence-mcp/oe-collections-classify.md
What oe_collections_classify does on :
AI agents call oe_collections_classify to retrieve information from : without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why oe_collections_classify is rated Low
The tool only predicts/proposes hashtag classifications and returns JSON — it does not persist any changes. The description explicitly states you must use a separate tool (oe_collections_bulk_apply) to actually write changes, making this a read/analysis-only operation.
From the tool's definition Returns the proposed plan as JSON; use oe_collections_bulk_apply to actually write
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs oe_collections_classify safely
PolicyLayer is an MCP gateway: it sits between your AI agents and :, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For oe_collections_classify, this is the rule to start with:
oe_collections_classify 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 :, apply this rule, and every oe_collections_classify call is checked against it from then on.
Questions about oe_collections_classify
Predict hashtags for every unsorted chat (or all chats with reclassify_all). Combines curated keyword rules with a per-tag log-odds-ratio signature trained from your existing memberships. Returns the proposed plan as JSON; use oe_collections_bulk_apply to actually write. It is categorised as a Read tool in the : MCP Server, which means it retrieves data without modifying state.
Register the : MCP server in PolicyLayer and add a rule for oe_collections_classify: 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 :. Nothing to install.
oe_collections_classify 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 oe_collections_classify 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 oe_collections_classify. 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.
oe_collections_classify is provided by the : MCP server (htlin222/openevidence-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on :, and thousands of servers like it.
This server
Across the catalogue