Low Risk

matrix_tool

Calculates travel times and distances between multiple points using Mapbox Matrix API.

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

AI agents call matrix_tool to retrieve information from Mapbox 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 matrix_tool 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.

waldzell-agentics-mcp-server.yaml
tools:
  matrix_tool:
    rules:
      - action: allow

See the full Mapbox policy for all 9 tools.

Tool Name matrix_tool
Category Read
MCP Server Mapbox MCP Server
Risk Level Low

View all 9 tools →

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

Calculates travel times and distances between multiple points using Mapbox Matrix API.. It is categorised as a Read tool in the Mapbox MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on matrix_tool? +

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

What risk level is matrix_tool? +

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

Can I rate-limit matrix_tool? +

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

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

matrix_tool is provided by the Mapbox MCP server (Waldzell-Agentics/mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Mapbox

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.