Medium Risk

update_composition

Update your agent composition without re-registering. Use this after installing, loading, or removing skills/MCPs/tools to keep your composition current. Preserves your agent identity. Supports both flat legacy fields and rich nested components with sub-components — when sub-components are provid...

High parameter count (18 properties)

Part of the ACR — Agent Composition Records MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

@tethral/acr-mcp Write Risk 2/5

AI agents use update_composition to create or modify resources in ACR — Agent Composition Records. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call update_composition repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach ACR — Agent Composition Records.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

acr-agent-composition-records.yaml
tools:
  update_composition:
    rules:
      - action: allow
        rate_limit:
          max: 30
          window: 60

See the full ACR — Agent Composition Records policy for all 25 tools.

Tool Name update_composition
Category Write
Risk Level Medium

View all 25 tools →

Agents calling write-class tools like update_composition have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.

What does the update_composition tool do? +

Update your agent composition without re-registering. Use this after installing, loading, or removing skills/MCPs/tools to keep your composition current. Preserves your agent identity. Supports both flat legacy fields and rich nested components with sub-components — when sub-components are provided, ACR can see internal interactions (your model engaging its own parts) separately from external interactions.. It is categorised as a Write tool in the ACR — Agent Composition Records MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_composition? +

Add a rule in your Intercept YAML policy under the tools section for update_composition. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the ACR — Agent Composition Records MCP server.

What risk level is update_composition? +

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

Can I rate-limit update_composition? +

Yes. Add a rate_limit block to the update_composition rule in your Intercept 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 update_composition completely? +

Set action: deny in the Intercept policy for update_composition. 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 update_composition? +

update_composition is provided by the ACR — Agent Composition Records MCP server (@tethral/acr-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on ACR — Agent Composition Records

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept
github.com/policylayer/intercept →
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.