Call this whenever the user asks for a wallet summary, wallet list, their wallets, wallet balances, verified holdings, or Proof of Funds ceiling. Returns all wallets for the authenticated user with their balances, verification status, and Proof of Funds ceiling. The response renders an inline You...
Part of the Mcp Server server.
Free to start. No card required.
AI agents call get_wallet_summary to retrieve information from Mcp Server 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 get_wallet_summary 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.
{
"version": "1",
"default": "deny",
"tools": {
"get_wallet_summary": {}
}
}See the full Mcp Server policy for all 19 tools.
These attack patterns abuse exactly the kind of access get_wallet_summary gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Call this whenever the user asks for a wallet summary, wallet list, their wallets, wallet balances, verified holdings, or Proof of Funds ceiling. Returns all wallets for the authenticated user with their balances, verification status, and Proof of Funds ceiling. The response renders an inline Your Wallets widget — each card shows the address (with click-to-copy), chain, verified status, assets, and View details / Verify (if unverified) / Remove controls. Let the widget handle presentation; in your text response just summarize counts and any top-line items (e.g. "You have 3 wallets, 2 verified, POF ceiling $65k"). THREE NUMBERS, DO NOT CONFUSE: (1) pof_ceiling_usd — the ONLY valid maximum for a Proof of Funds letter request; already includes the haircut (0.98× stablecoins, 0.935× volatile) and excludes unverified wallets. (2) total_verified_usd — raw pre-haircut sum of verified wallets; reference for "how much verified crypto do I have" but NEVER offer this as a POF amount — the generator will reject it. (3) Σ wallets[].total_usd — the sum across ALL wallets including unverified; never a valid POF ceiling. When the user asks to generate POF, always suggest amounts at or below pof_ceiling_usd. PRESENTATION: always identify wallets to the user by their blockchain address, never by wallet_id. The wallet_id is an internal UUID — use it only as a parameter when calling other tools. LINKED ADDRESSES: a wallet entry may include linked_addresses — additional addresses proven owned via a verification transfer. ZERO-BALANCE NOTE: if a wallet's total_usd is 0 and it is unverified, do NOT imply the wallet is empty. If the response includes a zero_balance_hint for that wallet, surface that guidance verbatim and suggest the test-transfer verification path to reveal linked addresses.. It is categorised as a Read tool in the Mcp Server MCP Server, which means it retrieves data without modifying state.
Register the Mcp Server MCP server in PolicyLayer and add a rule for get_wallet_summary: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Server. Nothing to install.
get_wallet_summary 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 get_wallet_summary rule in your PolicyLayer 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 PolicyLayer policy for get_wallet_summary. 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.
get_wallet_summary is provided by the Mcp Server MCP server (https://mcp.realopen.app/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 19 Mcp Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.