solana_stake

Stake SOL via Sanctum liquid staking to earn yield. Returns an LST (liquid staking token). Requires AGENTI_SOLANA_PRIVATE_KEY.

SERVERAgenti SOURCEnirholas/agenti

Critical RISK CLASS

Category Financial

Parameters 00 required

Recommended Approval-gatedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/nirholas-agenti/solana-stake.md

WHAT IT DOES

What solana_stake does on Agenti

AI agents use solana_stake to commit financial operations through Agenti, usually the final step of a payment, billing, or trading workflow. A call moves real money.

RISK

Why solana_stake is rated Critical

Staking SOL is a financial operation that moves cryptocurrency into a staking protocol, committing real funds. Misuse could result in unintended locking of user assets into a liquid staking contract. The requirement for a private key ('Requires AGENTI_SOLANA_PRIVATE_KEY') confirms this is an on-chain transaction with real financial consequences.

From the tool's definition 'Stake SOL via Sanctum liquid staking to earn yield' and server description 'autonomously hold, spend, earn, and receive cryptocurrency' — commits SOL to a staking contract, a financial transaction that locks funds and issues LST tokens.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs solana_stake safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Agenti, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For solana_stake, this is the rule to start with:

solana_stake Approval-gated

Any call to solana_stake is blocked until a human approves it. The rest of the server keeps working.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "solana_stake": {
      "deny_if": [
        {
          "conditions": [],
          "on_deny": "Requires human approval."
        }
      ]
    }
  }
}

GATE THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Agenti, apply this rule, and every solana_stake call is checked against it from then on.

FAQ

Questions about solana_stake

What does the solana_stake tool do? +

Stake SOL via Sanctum liquid staking to earn yield. Returns an LST (liquid staking token). Requires AGENTI_SOLANA_PRIVATE_KEY. It is categorised as a Financial tool in the Agenti MCP Server, which means it involves financial transactions. Block by default and require explicit approval.

How do I enforce a policy on solana_stake? +

Register the Agenti MCP server in PolicyLayer and add a rule for solana_stake: 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 Agenti. Nothing to install.

What risk level is solana_stake? +

solana_stake is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit solana_stake? +

Yes. Add a rate_limit block to the solana_stake 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.

How do I block solana_stake completely? +

Set action: deny in the PolicyLayer policy for solana_stake. 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.

What MCP server provides solana_stake? +

solana_stake is provided by the Agenti MCP server (nirholas/agenti). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Agenti, and thousands of servers like it.

This server

All 73 Agenti tools → Critical-risk tools on this server →

Across the catalogue

menese_stake on Mcp Menesesdk → All critical-risk MCP tools → The MCP Attack Database →

Guides

Govern MCP payment tools →Human-in-the-loop →Tool call approval →