get_staking_positions
Fetch Lido (stETH/wstETH) and EigenLayer staking positions for a wallet across supported chains. Returns per-protocol staked amounts, USD value, APR, and EigenLayer delegation target.
This record as markdown: /tools/io-github-szhygulin-vaultpilot-mcp/get-staking-positions.md
What get_staking_positions does on VaultPilot MCP
AI agents call get_staking_positions to retrieve information from VaultPilot MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
chains | array | — | Subset of chains to scan. Omit to scan all chains where staking is supported (Lido: ethereum + arbitrum; EigenLayer: ethereum only). |
wallet | string | Yes | 0x-prefixed EVM wallet address (40 hex chars) to inspect. |
Parameters from the server's own tool schema.
Why get_staking_positions is rated Low
This tool retrieves and queries staking data (amounts, USD values, APR, delegation targets) from blockchain protocols without creating, modifying, deleting, or executing any operations. It has no side effects and poses minimal security risk—the primary concern is information disclosure about wallet holdings, which is low severity.
From the tool's definition Tool performs a 'Fetch' operation that 'Returns' staking position data without modifying any state. Description uses passive retrieval language: 'Fetch...positions', 'Returns per-protocol staked amounts'.
Attacks that exploit this kind of access
The rule that runs get_staking_positions safely
PolicyLayer is an MCP gateway: it sits between your AI agents and VaultPilot MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_staking_positions, this is the rule to start with:
get_staking_positions is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect VaultPilot MCP, apply this rule, and every get_staking_positions call is checked against it from then on.
Questions about get_staking_positions
Fetch Lido (stETH/wstETH) and EigenLayer staking positions for a wallet across supported chains. Returns per-protocol staked amounts, USD value, APR, and EigenLayer delegation target. It is categorised as a Read tool in the VaultPilot MCP MCP Server, which means it retrieves data without modifying state.
get_staking_positions accepts 2 parameters: chains, wallet. Required: wallet. The full parameter table on this page comes from the server's own tool schema.
Register the VaultPilot MCP server in PolicyLayer and add a rule for get_staking_positions: 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 VaultPilot MCP. Nothing to install.
get_staking_positions 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_staking_positions 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_staking_positions. 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_staking_positions is provided by the VaultPilot MCP server (vaultpilot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on VaultPilot, and thousands of servers like it.
This server
Across the catalogue