Low Risk

list_checkpoints

List all available checkpoints for a task.

Part of the Taskflow MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

AI agents call list_checkpoints to retrieve information from Taskflow without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though list_checkpoints only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

taskflow.yaml
tools:
  list_checkpoints:
    rules:
      - action: allow

See the full Taskflow policy for all 50 tools.

Tool Name list_checkpoints
Category Read
MCP Server Taskflow MCP Server
Risk Level Low

View all 50 tools →

Agents calling read-class tools like list_checkpoints 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 Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

What does the list_checkpoints tool do? +

List all available checkpoints for a task.. It is categorised as a Read tool in the Taskflow MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on list_checkpoints? +

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

What risk level is list_checkpoints? +

list_checkpoints is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit list_checkpoints? +

Yes. Add a rate_limit block to the list_checkpoints 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 list_checkpoints completely? +

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

list_checkpoints is provided by the Taskflow MCP server (@dalmasonto/taskflow-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Taskflow

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.