manage_inbound
Configure inbound intake and speed-to-lead, manage sources/rules/pools, assign or acknowledge a lead, update scoring or rescore, test live intake, or import CSV. All admin/owner checks use the same handlers as the UI. force reassignment needs admin rights. delete_source refuses sources with histo...
This record as markdown: /tools/adrata-adrata-mcp/manage-inbound.md
What manage_inbound does on Adrata
AI agents use manage_inbound 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_inbound is rated Medium
An AI agent can call manage_inbound 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.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
The rule that runs manage_inbound 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_inbound, this is the rule to start with:
manage_inbound 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_inbound call is checked against it from then on.
Questions about manage_inbound
Configure inbound intake and speed-to-lead, manage sources/rules/pools, assign or acknowledge a lead, update scoring or rescore, test live intake, or import CSV. All admin/owner checks use the same handlers as the UI. force reassignment needs admin rights. delete_source refuses sources with history; pause instead. test with mode live creates a real test lead. import_csv creates/routes up to 500 leads. Secret reveal and rotation require explicit approval. Requires auditReason and stable idempotencyKey. Payload: settings {enabled,fallbackOwnerId,slaMinutes,businessHours,escalationSteps}; source {kind,name,status,fieldMap,allowedOrigins}; rule {name,isActive,conditions,action}; pool {name,memberIds}; reorder {ids}; assign {leadId,force}; test {profile,mode}; import {csv}; score_settings uses the settings read shape. 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_inbound: 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_inbound 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_inbound 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_inbound. 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_inbound 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