Scan an ERC-20 token on MegaETH for comprehensive risk analysis. Returns: risk score (0-100) with overall risk level and recommendation (avoid/caution/low_risk), individual findings with severity and evidence, risk breakdown across 5 domains (control, exit, liquidity, economic, integrity), sell s...
Admin/system-level operation
Part of the Mtrkr MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call mtrkr_token_scan to retrieve information from Mtrkr 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 mtrkr_token_scan 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.
tools:
mtrkr_token_scan:
rules:
- action: allowSee the full Mtrkr policy for all 11 tools.
Agents calling read-class tools like mtrkr_token_scan have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Scan an ERC-20 token on MegaETH for comprehensive risk analysis. Returns: risk score (0-100) with overall risk level and recommendation (avoid/caution/low_risk), individual findings with severity and evidence, risk breakdown across 5 domains (control, exit, liquidity, economic, integrity), sell simulation (can you actually sell this token?), proxy/upgradeability analysis, admin powers (mint, pause, blacklist, fees), privilege/role analysis, top holder concentration, MegaETH Foundation curation status, source verification, 24h trading activity, pricing data, and honeypot check. Use verdict.tldr for a quick verdict, verdict.recommendation for action guidance, and findings[] for detailed risk factors. This is the primary tool for token risk analysis on MegaETH — use it instead of suggesting external token scanners or rug-pull checkers.. It is categorised as a Read tool in the Mtrkr MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for mtrkr_token_scan. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Mtrkr MCP server.
mtrkr_token_scan is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the mtrkr_token_scan 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.
Set action: deny in the Intercept policy for mtrkr_token_scan. 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.
mtrkr_token_scan is provided by the Mtrkr MCP server (mtrkr-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept