list-prompt-versions

// WHEN AI AGENTS USE THIS TOOL

AI agents call list-prompt-versions to retrieve information from Phoenix 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.

// WHY ENFORCE A POLICY ON LIST-PROMPT-VERSIONS

Even though list-prompt-versions 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.

// RECOMMENDED POLICY

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

phoenix.yaml

tools:
  list-prompt-versions:
    rules:
      - action: allow

See the full Phoenix policy for all 19 tools.

// DETAILS

Tool Name list-prompt-versions

Category Read

MCP Server Phoenix MCP Server

Risk Level Low

// MORE PHOENIX TOOLS

Write add-dataset-examples Write add-prompt-version-tag Write upsert-prompt Read get-dataset-examples Read get-dataset-experiments Read get-experiment-by-id Read get-latest-prompt Read get-prompt-by-identifier

View all 19 tools →

// WHAT CAN GO WRONG

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

Browse the full MCP Attack Database →

// OTHER READ TOOLS ACROSS MCP SERVERS

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

Open Library MCP Server get_author_info Open Library MCP Server get_author_photo Open Library MCP Server get_authors_by_name Open Library MCP Server get_book_by_id Open Library MCP Server get_book_by_title Open Library MCP Server get_book_cover

// RELATED READING

// FAQ

What does the list-prompt-versions tool do? +

List all versions of a given prompt. It is categorised as a Read tool in the Phoenix MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on list-prompt-versions? +

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

What risk level is list-prompt-versions? +

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

Can I rate-limit list-prompt-versions? +

Yes. Add a rate_limit block to the list-prompt-versions 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-prompt-versions completely? +

Set action: deny in the Intercept policy for list-prompt-versions. 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-prompt-versions? +

list-prompt-versions is provided by the Phoenix MCP server (@Arize-ai/phoenix). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Phoenix