update_saved_view
Revise one of YOUR OWN saved views in place, keeping its id and any existing team share. Only the fields you send change; the rest are left exactly as they were, while scorecard-enrolled views require the current definition_revision; after a conflict or uncertain reply, read current state and del...
This record as markdown: /tools/com-meta-council-decision-intelligence/update-saved-view.md
What update_saved_view does on Meta Council
AI agents use update_saved_view to create or update resources in Meta Council, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Meta Council environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | — | New name for the view. |
columns | array | — | Replacement column list, in order. At most 20. |
filters | object | — | Saved question. Omitted reader selects ordinary tickets. Attention accepts reason; reviewed_attention accepts state and follow_up. Triage refuses other non-defa |
sort_by | string | null | — | New sorting field; null clears it. Clear explicit grouping and sorting when switching to triage. |
view_id | string | Yes | The view's id, from list_saved_views. |
group_by | string | null | — | New grouping field; null clears it. Clear explicit grouping and sorting when switching to triage. |
sort_dir | string | — | New sort direction. |
scorecard | object | null | — | Optional private ordinary live ticket counts; omit to retain, null to clear while retaining a nonzero revision. At most 10000 matching tickets, no actions or ro |
expected_revision | integer | — | Current definition_revision, required to configure a scorecard or change any previously enrolled view. On conflict or uncertain reply, read current state and de |
Parameters from the server's own tool schema.
Why update_saved_view is rated Medium
An AI agent can call update_saved_view faster than any human can review: one bad instruction and it creates or modifies resources in Meta Council by the hundred, each call as confident as the last.
Risk signalsHigh parameter count (24 properties)
Attacks that exploit this kind of access
The rule that runs update_saved_view safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Meta Council, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For update_saved_view, this is the rule to start with:
update_saved_view stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Meta Council, apply this rule, and every update_saved_view call is checked against it from then on.
Questions about update_saved_view
Revise one of YOUR OWN saved views in place, keeping its id and any existing team share. Only the fields you send change; the rest are left exactly as they were, while scorecard-enrolled views require the current definition_revision; after a conflict or uncertain reply, read current state and deliberately reconcile. Sharing a view does not let its readers revise it -- only the owner may. Requires authentication and the tickets:write scope. It is categorised as a Write tool in the Meta Council MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
update_saved_view accepts 9 parameters: name, columns, filters, sort_by, view_id, group_by, sort_dir, scorecard, expected_revision. Required: view_id. The full parameter table on this page comes from the server's own tool schema.
Register the Meta Council MCP server in PolicyLayer and add a rule for update_saved_view: 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 Meta Council. Nothing to install.
update_saved_view is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_saved_view 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 update_saved_view. 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.
update_saved_view is provided by the Meta Council MCP server (https://meta-council.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Meta Council, and thousands of servers like it.
This server
Across the catalogue