# neuron_create_bot Create a new AI bot with specified name, model, and behavior instructions. Returns the created bot object. Agent View of the PolicyLayer registry record for `neuron_create_bot`. HTML page: https://policylayer.com/tools/io-github-conquext-neuron/neuron-create-bot ## Facts - Tool: `neuron_create_bot` - Server: Neuron (`neuron-mcp-server`) — https://policylayer.com/tools/io-github-conquext-neuron.md - Install: `npx -y neuron-mcp-server` - Homepage: https://github.com/conquext/neuron - Risk category: Write (Medium risk) - Registry record: grade F, identity unverified - Server auth posture: open - Server CORS policy: * - Server rate-limited: no - Parameters: 11 (2 required) - Recommended policy verdict: Rate-limited ## Parameters | Parameter | Type | Required | Description | | --- | --- | --- | --- | | `name` | string | yes | Display name for the bot | | `llmModel` | string | no | OpenRouter model ID (e.g., 'google/gemini-2.5-flash-lite', 'openrouter/auto') | | `maxTokens` | number | no | Maximum number of tokens the bot can generate per response | | `assignment` | string | no | One-sentence role definition for the bot (max 2000 chars) | | `systemPrompt` | string | yes | System prompt that defines the bot's behavior, personality, and response guidelines | | `llmTemperature` | number | no | Temperature parameter controlling response randomness (0 = deterministic, 2 = creative) | | `fallbackMessage` | string | no | Message sent when the bot cannot understand user input (max 2000 chars) | | `greetingMessage` | string | no | Automatic greeting sent when a new conversation starts (max 2000 chars) | | `escalationPrompt` | string | no | Prompt template used when escalating to a human agent (max 5000 chars) | | `responsibilities` | array | no | Array of responsibility descriptions defining what the bot handles | | `whatsappChannelId` | string | no | Unique identifier (UUID) of the WhatsApp channel to associate with the bot | Parameters from the server's own tool schema. ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "neuron_create_bot", "arguments": { "name": "", "systemPrompt": "" } } } ``` ## Why neuron_create_bot is rated Medium This tool creates a new bot resource, which is a reversible write operation. The severity is medium because creating a bot in a messaging platform could enable spam, phishing, or unauthorized automated communications if misused by an AI agent, but the action itself is not destructive and can be undone by deletion. Confidence is high as the name and description clearly indicate a create/write operation. From the tool's own definition: "Tool name 'create' and description states 'Create a new AI bot' with 'Returns the created bot object' indicating data creation/persistence." Risk signals: High parameter count (11 properties) ## Use case AI agents use neuron_create_bot 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. ## Recommended policy (PolicyLayer) Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Neuron: ```json { "version": "1", "default": "deny", "tools": { "neuron_create_bot": { "limits": [ { "counter": "neuron_create_bot_rate", "window": "minute", "max": 30, "scope": "grant" } ] } } } ``` ## Other tools on Neuron (230) - `neuron_delete_ad_request` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-ad-request.md - `neuron_delete_blog_post` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-blog-post.md - `neuron_delete_bot` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-bot.md - `neuron_delete_broadcast` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-broadcast.md - `neuron_delete_campaign` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-campaign.md - `neuron_delete_channel` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-channel.md - `neuron_delete_contact` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-contact.md - `neuron_delete_contact_list` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-contact-list.md - `neuron_delete_kb_entry` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-kb-entry.md - `neuron_delete_knowledge_base` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-knowledge-base.md - `neuron_delete_message` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-message.md - `neuron_delete_newsletter` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-newsletter.md - `neuron_delete_outbound_webhook` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-outbound-webhook.md - `neuron_delete_tool` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-tool.md - `neuron_delete_webhook` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-webhook.md - `neuron_leave_group` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-leave-group.md - `neuron_logout` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-logout.md - `neuron_post_to_newsletter` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-post-to-newsletter.md - `neuron_remove_bot_channel` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-remove-bot-channel.md - `neuron_remove_member` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-remove-member.md - `neuron_remove_profile_picture` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-remove-profile-picture.md - `neuron_remove_tool_secret` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-remove-tool-secret.md - `neuron_revoke_api_key` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-revoke-api-key.md - `neuron_revoke_group_invite` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-revoke-group-invite.md - `neuron_revoke_invitation` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-revoke-invitation.md - `neuron_send_broadcast` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-send-broadcast.md - `neuron_stop_ad_request` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-stop-ad-request.md - `neuron_stop_campaign` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-stop-campaign.md - `neuron_unpublish_from_pool` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-unpublish-from-pool.md - `neuron_bot_api_chat` — Execute — https://policylayer.com/tools/io-github-conquext-neuron/neuron-bot-api-chat.md - …and 200 more: https://policylayer.com/tools/io-github-conquext-neuron.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-conquext-neuron · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-conquext-neuron