neuron_switch_instance
Switch the MCP server to target a different Neuron backend instance. Auth tokens are preserved per instance — if you've previously logged in to an instance, switching back restores your session automatically. Call with no args to list known instances and see which is active.
This record as markdown: /tools/io-github-conquext-neuron/neuron-switch-instance.md
What neuron_switch_instance does on Neuron
AI agents use neuron_switch_instance to create or update resources in Neuron, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Neuron environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
url | string | — | Base API URL of the Neuron instance (e.g., 'https://api.client.com/api/v1'). Omit to list known instances. |
Parameters from the server's own tool schema.
Why neuron_switch_instance is rated Medium
An AI agent can call neuron_switch_instance faster than any human can review: one bad instruction and it creates or modifies resources in Neuron by the hundred, each call as confident as the last.
Risk signalsAccepts URL/endpoint input (url)
Attacks that exploit this kind of access
The rule that runs neuron_switch_instance safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Neuron, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For neuron_switch_instance, this is the rule to start with:
neuron_switch_instance 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 Neuron, apply this rule, and every neuron_switch_instance call is checked against it from then on.
Questions about neuron_switch_instance
Switch the MCP server to target a different Neuron backend instance. Auth tokens are preserved per instance — if you've previously logged in to an instance, switching back restores your session automatically. Call with no args to list known instances and see which is active. It is categorised as a Write tool in the Neuron MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
neuron_switch_instance accepts 1 parameter: url. The full parameter table on this page comes from the server's own tool schema.
Register the Neuron MCP server in PolicyLayer and add a rule for neuron_switch_instance: 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 Neuron. Nothing to install.
neuron_switch_instance 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 neuron_switch_instance 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 neuron_switch_instance. 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.
neuron_switch_instance is provided by the Neuron MCP server (neuron-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Neuron, and thousands of servers like it.
This server
Across the catalogue