Update the send-safety policy for the current MCP session. Changes are NOT persisted — the server resets to env-var defaults on restart. Env vars act as ceilings; values exceeding them are rejected. Hard lock via SOLAPI_MCP_DISABLE_SEND=true cannot be unlocked here.
AI agents use update_mcp_policy to create or update resources in SOLAPI MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SOLAPI MCP Server environment.
This is a Write operation because it modifies session configuration state reversibly (changes are not persisted and reset on restart). It does not delete data (not Destructive), send messages itself (not Execute in the messaging sense), or move money (not Financial).
From the tool's definition Tool name 'update_mcp_policy' and description states it 'Update[s] the send-safety policy for the current MCP session', modifying session configuration.
Attacks that exploit this kind of access
Update the send-safety policy for the current MCP session. Changes are NOT persisted — the server resets to env-var defaults on restart. Env vars act as ceilings; values exceeding them are rejected. Hard lock via SOLAPI_MCP_DISABLE_SEND=true cannot be unlocked here. It is categorised as a Write tool in the SOLAPI MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SOLAPI MCP Server MCP server in PolicyLayer and add a rule for update_mcp_policy: 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 SOLAPI MCP Server. Nothing to install.
update_mcp_policy 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_mcp_policy 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_mcp_policy. 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_mcp_policy is provided by the SOLAPI MCP Server MCP server (solapi/solapi-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →