USE THIS FIRST for any 'find an asset / what tokens exist for X / list assets matching Y' question. Free over SIWX. Returns ranked candidates with assetIds, symbols, and short descriptions for queries like 'bitcoin etf', 'tokenized treasury', 'gold mining', 'AI tokens'. Prefer agon_token_resolve ...
Single-target operation
Part of the Gateway MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call agon_token_search 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.
Even though agon_token_search 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:
agon_token_search:
rules:
- action: allowSee the full Gateway policy for all 15 tools.
Agents calling read-class tools like agon_token_search 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.
USE THIS FIRST for any 'find an asset / what tokens exist for X / list assets matching Y' question. Free over SIWX. Returns ranked candidates with assetIds, symbols, and short descriptions for queries like 'bitcoin etf', 'tokenized treasury', 'gold mining', 'AI tokens'. Prefer agon_token_resolve when the query is a single name/ticker; use search when the query is broader or ambiguous. Do NOT use web search for asset discovery on Agon-tracked classes (crypto, tokenized stocks, ETFs, treasuries, metals, currencies).. It is categorised as a Read tool in the Gateway MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for agon_token_search. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Gateway MCP server.
agon_token_search 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 agon_token_search 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_token_search. 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_token_search 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.