agon_gateway_call

Call an Agon Gateway route. Use without payment/SIWX headers to issue a challenge, then retry with PAYMENT-SIGNATURE, X-PAYMENT, or SIGN-IN-WITH-X. Devnet RPC/DAS/Wallet routes settle in devnet USDC; mainnet routes settle in mainnet USDC; Tokens API SIWX routes are free.

Accepts file system path (path); Accepts freeform code/query input (query); Accepts raw HTML/template content (body)

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

@agonx402/gateway-mcp Read

// WHEN AI AGENTS USE THIS TOOL

AI agents call agon_gateway_call to retrieve information from Gateway 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 AGON_GATEWAY_CALL

Even though agon_gateway_call 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.

io-github-agonx402-agon-gateway.yaml

tools:
  agon_gateway_call:
    rules:
      - action: allow

See the full Gateway policy for all 15 tools.

// DETAILS

Tool Name agon_gateway_call

Category Read

MCP Server Gateway MCP Server

Risk Level Low

// MORE GATEWAY TOOLS

Execute agon_gateway_auth_call Execute agon_gateway_call_with_headers Write agon_gateway_complete_siwx Write agon_token_resolve Read agon_gateway_catalog Read agon_gateway_find_route Read agon_gateway_health Read agon_gateway_prepare_auth

View all 15 tools →

// WHAT CAN GO WRONG

Agents calling read-class tools like agon_gateway_call 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.

Firecrawl Web Scraping Server firecrawl_check_crawl_status Firecrawl Web Scraping Server firecrawl_crawl Firecrawl Web Scraping Server firecrawl_deep_research Firecrawl Web Scraping Server firecrawl_extract Firecrawl Web Scraping Server firecrawl_map Firecrawl Web Scraping Server firecrawl_scrape

// RELATED READING

// FAQ

What does the agon_gateway_call tool do? +

How do I enforce a policy on agon_gateway_call? +

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

What risk level is agon_gateway_call? +

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

Can I rate-limit agon_gateway_call? +

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

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

agon_gateway_call is provided by the Gateway MCP server (@agonx402/gateway-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

agon_gateway_call

Let agents act without letting them run wild.