Query event logs. Auto-decodes 47+ events: ERC20/721/1155 transfers (NFTs + tokens, Mint/Burn), Uniswap V2-V4 swaps, Aave V3 / Compound V2+V3 lending, Seaport NFT marketplace, Lido staking, flash loans. Pass eventSignature for auto-topic0. Returns eventSummary + logs. Default RPC (Alchemy free ti...
High parameter count (13 properties)
Part of the Kosyak Evm MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call get_logs to retrieve information from Kosyak Evm 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_logs 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:
get_logs:
rules:
- action: allowSee the full Kosyak Evm policy for all 43 tools.
Agents calling read-class tools like get_logs 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.
Query event logs. Auto-decodes 47+ events: ERC20/721/1155 transfers (NFTs + tokens, Mint/Burn), Uniswap V2-V4 swaps, Aave V3 / Compound V2+V3 lending, Seaport NFT marketplace, Lido staking, flash loans. Pass eventSignature for auto-topic0. Returns eventSummary + logs. Default RPC (Alchemy free tier) limits eth_getLogs range to ~10 blocks — `autoChunk: "onError"` (default) retries wide queries chunked with `requestDelayMs` pacing (default 50ms) and 429/CU-exceeded retry with exponential backoff (`maxRetriesPerChunk`=3). On partial failure returns `partialScan:true` with `failedRanges` — prefer partial results to all-or-nothing error. Use `autoChunk: "always"` for known large ranges.. It is categorised as a Read tool in the Kosyak Evm MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for get_logs. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Kosyak Evm MCP server.
get_logs 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_logs 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 get_logs. 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_logs is provided by the Kosyak Evm MCP server (kosyak-evm-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept