get_metric

Single-target operation

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

// WHEN AI AGENTS USE THIS TOOL

AI agents call get_metric to retrieve information from PreReason 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_METRIC

Even though get_metric 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.

prereason.yaml

tools:
  get_metric:
    rules:
      - action: allow

See the full PreReason policy for all 5 tools.

// DETAILS

Tool Name get_metric

Category Read

MCP Server PreReason MCP Server

Risk Level Low

// MORE PREREASON TOOLS

Read get_context Read get_health Read list_briefings Read list_metrics

// WHAT CAN GO WRONG

Agents calling read-class tools like get_metric 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_metric tool do? +

Get a single metric with pre-reasoned signal interpretation, trend analysis (7d/30d/90d), confidence score with factor breakdown, momentum, and percentile ranking. Available metrics: bitcoin-price, bitcoin-market-cap, bitcoin-volume-24h, bitcoin-change-24h, bitcoin-dominance, bitcoin-hash-rate, bitcoin-difficulty, bitcoin-tx-count, bitcoin-tx-volume, bitcoin-active-addresses, fed-balance, m2-supply, treasury-10y, rrp, eur-usd, cny-usd, yield-curve, tga, net-liquidity, hash-ribbon, mvrv-proxy, etf-spy, etf-qqq, etf-iwm, etf-vxx, etf-uup, usdt-market-cap, usdt-dominance, btc-price-200d-ma, btc-price-200d-distance. Requires API key authentication. Returns analyzed context (signal, trend direction, momentum, 90d percentile), not raw values. Use when you need to understand what a metric means for decision-making, not just its number.. It is categorised as a Read tool in the PreReason MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_metric? +

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

What risk level is get_metric? +

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

Can I rate-limit get_metric? +

Yes. Add a rate_limit block to the get_metric 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_metric completely? +

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

get_metric is provided by the PreReason MCP server (@prereason/mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

get_metric

Enforce policies on PreReason