agents_update

SERVERDialogbrain SOURCEhttps://api.dialogbrain.com/mcp

Medium RISK CLASS

Category Write

Parameters 121 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-saloprj-dialogbrain/agents-update.md

WHAT IT DOES

What agents_update does on Dialogbrain

AI agents use agents_update to create or update resources in Dialogbrain, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dialogbrain environment.

Parameter	Type	Required	Description
`name`	string	—	New name for the agent
`model`	string	—	Canonical source for which LLM the agent runs on. To switch models pass JUST this — do NOT also rewrite prompt_text (any 'duty model' section in the prompt is s
`script`	string	—	rule_based deterministic action (no LLM): Python run in the workbench sandbox on each matched event. Reads `inputs` (raw_data, message_id, from_name, …) and cal
`status`	string	—	Agent status: 'active', 'paused', or 'archived'. OMIT to leave the status unchanged.
`agent_id`	integer	Yes	ID of the agent to update
`priority`	integer	—	Agent priority for trigger matching. LOWER number = HIGHER priority (wins tiebreaks). Typical range 1-100. Fallback auto-reply agents use 10; specialised/topica
`prompt_id`	integer	—	Prompt ID to assign (null to detach)
`send_mode`	string	—	Default send mode: 'auto' or 'draft'. OMIT to leave the send-mode unchanged.
`fast_model`	string	—	Model for the fast-path responder (voice, text auto-reply, agent executor). Defaults to deepseek-chat when unset. Non-Anthropic models (deepseek-chat, gpt-4.1-n
`api_surface`	string	—	OpenAI HTTPS endpoint for this agent's LLM calls (Phase 3a). 'chat_completions' (default, also when null) routes to /v1/chat/completions. 'responses' routes to
`description`	string	—	New description for the agent
`prompt_text`	string	—	DESTRUCTIVE — REPLACES the entire system prompt. Pass ONLY when the user explicitly asks to edit/rewrite the prompt. To READ the prompt use prompts.get. When up

Parameters from the server's own tool schema.

RISK

Why agents_update is rated Medium

An AI agent can call agents_update faster than any human can review: one bad instruction and it creates or modifies resources in Dialogbrain by the hundred, each call as confident as the last.

Risk signalsAccepts freeform code/query input (script) · High parameter count (61 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs agents_update safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Dialogbrain, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For agents_update, this is the rule to start with:

agents_update Rate-limited

agents_update 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "agents_update": {
      "limits": [
        {
          "counter": "agents_update_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Dialogbrain, apply this rule, and every agents_update call is checked against it from then on.

FAQ

Questions about agents_update

What does the agents_update tool do? +

Update an existing AI agent's configuration. All parameters are optional — only provided fields will be updated. Use this to: - Enable or disable an agent - Change agent name or description - Assign or detach a prompt - Change default send mode - Replace knowledge collections - Update agent status - Change agent priority for trigger matching (lower number = higher priority) - Override which tools the agent can/can't call on triggered runs - Override which context sections (situation, communication style, job state, conversation history, thread summary) the agent receives - Opt into boilerplate prompt sections (safety guidelines, data confidentiality, factual accuracy) — all default OFF. It is categorised as a Write tool in the Dialogbrain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does agents_update accept? +

agents_update accepts 12 parameters: name, model, script, status, agent_id, priority, prompt_id, send_mode, fast_model, api_surface, description, prompt_text. Required: agent_id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on agents_update? +

Register the Dialogbrain MCP server in PolicyLayer and add a rule for agents_update: 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 Dialogbrain. Nothing to install.

What risk level is agents_update? +

agents_update is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit agents_update? +

Yes. Add a rate_limit block to the agents_update 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.

How do I block agents_update completely? +

Set action: deny in the PolicyLayer policy for agents_update. 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.

What MCP server provides agents_update? +

agents_update is provided by the Dialogbrain MCP server (https://api.dialogbrain.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Dialogbrain, and thousands of servers like it.

This server

All 225 Dialogbrain tools →

Across the catalogue

aroflo_create_or_update_record on AroFlo MCP →team_manager_register_agents on Team Manager MCP → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →