Generic escape hatch: call any Agon Gateway route, run the configured signer hook on a 402, and retry. For Tokens market-data questions, prefer the higher-level agon_token_quote / agon_token_resolve / agon_token_chart / agon_token_search / agon_token_batch_quote tools -- they pre-format the route...
Accepts file system path (path); Accepts freeform code/query input (query); Accepts raw HTML/template content (body); High parameter count (10 properties)
Part of the Gateway MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents invoke agon_gateway_auth_call to trigger processes or run actions in Gateway. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
agon_gateway_auth_call can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. Intercept enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
tools:
agon_gateway_auth_call:
rules:
- action: allow
rate_limit:
max: 10
window: 60
validate:
required_args: trueSee the full Gateway policy for all 15 tools.
Agents calling execute-class tools like agon_gateway_auth_call have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Execute risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
agon_gateway_auth_call is one of the high-risk operations in Gateway. For the full severity-focused view — only the high-risk tools with their recommended policies — see the breakdown for this server, or browse all high-risk tools across every MCP server.
Generic escape hatch: call any Agon Gateway route, run the configured signer hook on a 402, and retry. For Tokens market-data questions, prefer the higher-level agon_token_quote / agon_token_resolve / agon_token_chart / agon_token_search / agon_token_batch_quote tools -- they pre-format the route, parse the response, and avoid shell quoting. Use this tool only for routes those higher-level tools do not cover (custom Tokens routes, Solana RPC, DAS, Helius Wallet, payment-channel routes). Devnet RPC/DAS/Wallet routes pay in devnet USDC; mainnet RPC/DAS/Wallet routes pay in mainnet USDC; Tokens API SIWX routes are free on either cluster. The signer must hold the USDC mint for the cluster of the route.. It is categorised as a Execute tool in the Gateway MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Add a rule in your Intercept YAML policy under the tools section for agon_gateway_auth_call. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Gateway MCP server.
agon_gateway_auth_call is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the agon_gateway_auth_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.
Set action: deny in the Intercept policy for agon_gateway_auth_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.
agon_gateway_auth_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.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.