Fetch historical on-chain activity directly from event logs via eth_getLogs. Use this when the API-based get_pool_activity returns empty or incomplete data (the API only stores a limited time window of recent transactions). Supports TWO contract types: 1. Curve StableSwap-NG pool (pool_address): ...
Risk signalsHigh parameter count (10 properties)
Part of the Spectra server.
Free to start. No card required.
AI agents call get_onchain_activity to retrieve information from Spectra 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_onchain_activity 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_onchain_activity": {}
}
}See the full Spectra policy for all 25 tools.
These attack patterns abuse exactly the kind of access get_onchain_activity 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.
Fetch historical on-chain activity directly from event logs via eth_getLogs. Use this when the API-based get_pool_activity returns empty or incomplete data (the API only stores a limited time window of recent transactions). Supports TWO contract types: 1. Curve StableSwap-NG pool (pool_address): TokenExchange, AddLiquidity, RemoveLiquidity 2. Spectra PrincipalToken vault (pt_address): Mint (deposit→PT+YT), Redeem (burn PT→IBT), YieldClaimed Provide pool_address, pt_address, or both. When both are provided, events from both contracts are fetched in parallel, merged, and sorted by block number. Returns raw token amounts (not USD values — USD conversion is not available from on-chain data alone). The rpc_url parameter lets you supply an RPC endpoint for any chain, including chains without hardcoded RPCs (e.g., Katana, Monad). If omitted, falls back to the server's default public RPC for the chain (if available). Block range strategy: - Specify from_block/to_block for exact ranges - Or specify lookback_hours to scan the last N hours (converted to blocks using estimated block times — approximate, not exact) - Default: last ~24 hours if no range is specified Limitations: - No USD values (only raw token amounts in native decimals) - Block timestamps are fetched for first/last block only (time range display) - Public RPCs may rate-limit large scans; use a premium RPC for deep history - Maximum 500,000 blocks per request (to prevent timeout) Use get_pool_activity for recent data with USD values and rich analysis. Use this tool for historical data beyond the API's retention window.. It is categorised as a Read tool in the Spectra MCP Server, which means it retrieves data without modifying state.
Register the Spectra MCP server in PolicyLayer and add a rule for get_onchain_activity: 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 Spectra. Nothing to install.
get_onchain_activity 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_onchain_activity 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_onchain_activity. 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_onchain_activity is provided by the Spectra MCP server (spectra-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 25 Spectra 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.