manage_portal
Create a Portal, replace capture policy, lock/unlock new admissions, mute/remove a participant, start/stop consented recording or draft a grounded follow-up. Read current capture policy and preserve unrelated settings. For moderation use participantId from get_portal room.participants[].participa...
This record as markdown: /tools/adrata-adrata-mcp/manage-portal.md
What manage_portal does on Adrata
AI agents use manage_portal to create or update resources in Adrata, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Adrata environment.
Why manage_portal is rated Medium
An AI agent can call manage_portal faster than any human can review: one bad instruction and it creates or modifies resources in Adrata by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs manage_portal safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Adrata, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For manage_portal, this is the rule to start with:
manage_portal 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 Adrata, apply this rule, and every manage_portal call is checked against it from then on.
Questions about manage_portal
Create a Portal, replace capture policy, lock/unlock new admissions, mute/remove a participant, start/stop consented recording or draft a grounded follow-up. Read current capture policy and preserve unrelated settings. For moderation use participantId from get_portal room.participants[].participantId. delegate grants a named Sloan agent read/draft access to saved artifacts with explicit consent and expiry; revoke_delegation stops new admissions; already admitted operations may finish. delegated_draft uses the independently authenticated agent credential and saves privately for the owner. This does not join a call. Creates no invitations and sends no email. Previews by default; live writes require dryRun:false, approved:true, reason and stable idempotencyKey. It is categorised as a Write tool in the Adrata MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Adrata MCP server in PolicyLayer and add a rule for manage_portal: 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 Adrata. Nothing to install.
manage_portal 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 manage_portal 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 manage_portal. 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.
manage_portal is provided by the Adrata MCP server (@adrata/adrata-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Adrata, and thousands of servers like it.
This server
Across the catalogue