get_token_reduction

Get token reduction statistics for CoD vs CoT

Part of the MCP Chain of Draft (CoD) Prompt Tool MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

brendancopley/mcp-chain-of-draft-prompt-tool Read

// WHEN AI AGENTS USE THIS TOOL

AI agents call get_token_reduction to retrieve information from MCP Chain of Draft (CoD) Prompt Tool 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 GET_TOKEN_REDUCTION

Even though get_token_reduction 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.

brendancopley-mcp-chain-of-draft-prompt-tool.yaml

tools:
  get_token_reduction:
    rules:
      - action: allow

See the full MCP Chain of Draft (CoD) Prompt Tool policy for all 7 tools.

// DETAILS

Tool Name get_token_reduction

Category Read

MCP Server MCP Chain of Draft (CoD) Prompt Tool MCP Server

Risk Level Low

// MORE MCP CHAIN OF DRAFT (COD) PROMPT TOOL TOOLS

Read analyze_problem_complexity Read chain_of_draft_solve Read code_solve Read get_performance_stats Read logic_solve Read math_solve

// WHAT CAN GO WRONG

Agents calling read-class tools like get_token_reduction 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 get_token_reduction tool do? +

Get token reduction statistics for CoD vs CoT. It is categorised as a Read tool in the MCP Chain of Draft (CoD) Prompt Tool MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_token_reduction? +

Add a rule in your Intercept YAML policy under the tools section for get_token_reduction. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the MCP Chain of Draft (CoD) Prompt Tool MCP server.

What risk level is get_token_reduction? +

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

Can I rate-limit get_token_reduction? +

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

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

get_token_reduction is provided by the MCP Chain of Draft (CoD) Prompt Tool MCP server (brendancopley/mcp-chain-of-draft-prompt-tool). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

get_token_reduction

Enforce policies on MCP Chain of Draft (CoD) Prompt Tool