get_solana_staking_positions
READ-ONLY — enumerate a Solana wallet's liquid-staking (Marinade mSOL, Jito jitoSOL) and native stake-account positions. Returns three sections: (1) Marinade — mSOL balance + SOL-equivalent via the on-chain mSolPrice field; (2) Jito — jitoSOL balance + SOL-equivalent via the stake pool's totalLam...
This record as markdown: /tools/io-github-szhygulin-vaultpilot-mcp/get-solana-staking-positions.md
What get_solana_staking_positions does on VaultPilot MCP
AI agents call get_solana_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 |
|---|---|---|---|
wallet | string | Yes | Solana wallet to enumerate staking positions for. Returns three sections: Marinade (mSOL LST balance + SOL-equivalent via on-chain exchange rate), Jito (jitoSOL |
Parameters from the server's own tool schema.
Why get_solana_staking_positions is rated Low
This tool retrieves and displays existing staking position information from a Solana wallet without creating, modifying, deleting, or executing any transactions. The explicit 'READ-ONLY' designation and purely informational nature (returning balances, activation statuses, validator information) classify it as a Read operation with minimal risk if misused by an AI agent—it cannot move funds or trigger irreversible…
From the tool's definition Tool description explicitly states 'READ-ONLY' and describes enumeration/return of staking position data with no modifications: 'enumerate a Solana wallet's liquid-staking...positions. Returns three sections...'.
Attacks that exploit this kind of access
The rule that runs get_solana_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_solana_staking_positions, this is the rule to start with:
get_solana_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_solana_staking_positions call is checked against it from then on.
Questions about get_solana_staking_positions
READ-ONLY — enumerate a Solana wallet's liquid-staking (Marinade mSOL, Jito jitoSOL) and native stake-account positions. Returns three sections: (1) Marinade — mSOL balance + SOL-equivalent via the on-chain mSolPrice field; (2) Jito — jitoSOL balance + SOL-equivalent via the stake pool's totalLamports/poolTokenSupply ratio; (3) native stakes — all SPL stake-program accounts where this wallet has withdrawer authority, each annotated with activation status (activating / active / deactivating / inactive) and validator vote account. Parallel to EVM's get_staking_positions. Single tool call returning the full view; individual sections are separately readable via the underlying module functions for portfolio integration. It is categorised as a Read tool in the VaultPilot MCP MCP Server, which means it retrieves data without modifying state.
get_solana_staking_positions accepts 1 parameter: 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_solana_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_solana_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_solana_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_solana_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_solana_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