Get 25 (per page) addresses or entities with the most common interactions with input addresses Default sort is net value transferred between them. Also returns the top 3 tokens transferred by count for each counterparty Note: To get related wallets: - Focus on direct value transfers to get most l...
Part of the Nansen-MCP server.
Free to start. No card required.
AI agents call address_counterparties to retrieve information from Nansen-MCP 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 address_counterparties 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": {
"address_counterparties": {}
}
}See the full Nansen-MCP policy for all 24 tools.
These attack patterns abuse exactly the kind of access address_counterparties 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.
Get 25 (per page) addresses or entities with the most common interactions with input addresses Default sort is net value transferred between them. Also returns the top 3 tokens transferred by count for each counterparty Note: To get related wallets: - Focus on direct value transfers to get most likely addresses. - Include CEX deposit addresses (not withdrawal addresses!) as well. - Also go one level deeper: - Find addresses that interacted with the most likely addresses. - Find addresses that deposited to the same CEX deposit (NOT withdrawal!) addresses. - Address structure / string is not important, but the relationship is! Sorting Options (all fields support "asc"/"desc"): Available for sorting: volOut, volIn, numTxOut, numTxIn, usdNetflow Examples: Query by addresses with new type-safe sorting { "addresses": ["0x123..."], "sourceInput": "Combined", "groupBy": "wallet", "chain": "ethereum", "timeRange": {"from": "30D_AGO", "to": "NOW"}, "order_by": "usdNetflow", "order_by_direction": "desc" } Query by entity { "entityId": "Binance", "sourceInput": "Combined", "groupBy": "entity", "chain": "all", "timeRange": {"from": "7D_AGO", "to": "NOW"} }. It is categorised as a Read tool in the Nansen-MCP MCP Server, which means it retrieves data without modifying state.
Register the Nansen- MCP server in PolicyLayer and add a rule for address_counterparties: 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 Nansen-MCP. Nothing to install.
address_counterparties 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 address_counterparties 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 address_counterparties. 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.
address_counterparties is provided by the Nansen- MCP server (nansen-ai/Nansen-MCP). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 24 Nansen-MCP 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.