hydra_create_agent_key

Mint NEAR function-call access keys scoped to specific contracts (with a NEAR allowance cap) for autonomous agent use. Generates one fresh ed25519 keypair per receiverContract (NEAR

ServerNear Hydra
CategoryWrite

How to control hydra_create_agent_key ↓

WHAT IT DOES

What hydra_create_agent_key does on Near Hydra

AI agents use hydra_create_agent_key to create or update resources in Near Hydra — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Near Hydra environment.

THE RISK

Medium Risk

Why hydra_create_agent_key needs a policy

This tool creates new cryptographic credentials (ed25519 keypairs) and writes them to the blockchain via key minting. While not directly moving funds, it creates scoped access keys that enable autonomous agent operations on NEAR contracts with financial allowances.

From the tool's definition Mint NEAR function-call access keys scoped to specific contracts (with a NEAR allowance cap) for autonomous agent use. Generates one fresh ed25519 keypair per receiverContract.

Documented attack patterns abuse exactly the kind of access hydra_create_agent_key gives an agent:

POLICY

How to control hydra_create_agent_key

PolicyLayer is an MCP gateway — it sits between your AI agents and Near Hydra, and nothing reaches the server without passing your rules. This is the rule we recommend for hydra_create_agent_key:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "hydra_create_agent_key": {
      "limits": [
        {
          "counter": "hydra_create_agent_key_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

hydra_create_agent_key stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Near Hydra — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Near Hydra tools

Financial hydra_swap_execute Execute an end-to-end cross-chain swap via NEAR Intents 1Click. Auto-routes the origin sen Financial hydra_swap_submit_deposit Notify 1Click that the deposit transaction has been broadcast. depositAddress comes from a Financial hydra_ensure_gas Top up the derived foreign-chain address with native gas, via a small NEAR Intents 1Click Financial hydra_send_btc Send BTC from a Chain-Signature-derived Bitcoin address. UTXO selection via Mempool API. S Financial hydra_send_evm Send a transaction on an EVM chain from a Chain-Signature-derived address. Supports native Financial hydra_send_ft Send a NEP-141 fungible token from the configured account. Calls ft_transfer with 1 yoctoN Financial hydra_send_near Send native NEAR from the configured account. SAFE BY DEFAULT: dry=true returns the plan w Financial hydra_send_solana Send native SOL from a Chain-Signature-derived Solana address. SAFE: dry=true returns the

All 21 Near Hydra tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about hydra_create_agent_key

What does the hydra_create_agent_key tool do? +

Mint NEAR function-call access keys scoped to specific contracts (with a NEAR allowance cap) for autonomous agent use. Generates one fresh ed25519 keypair per receiverContract (NEAR. It is categorised as a Write tool in the Near Hydra MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on hydra_create_agent_key? +

Register the Near Hydra MCP server in PolicyLayer and add a rule for hydra_create_agent_key: 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 Near Hydra. Nothing to install.

What risk level is hydra_create_agent_key? +

hydra_create_agent_key is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit hydra_create_agent_key? +

Yes. Add a rate_limit block to the hydra_create_agent_key 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 hydra_create_agent_key completely? +

Set action: deny in the PolicyLayer policy for hydra_create_agent_key. 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 hydra_create_agent_key? +

hydra_create_agent_key is provided by the Near Hydra MCP server (nikshepsvn/near-hydra). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Near Hydra tool call.

Start from Near Hydra, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

21 Near Hydra tools catalogued and risk-classified — across an index of 43,000+ MCP servers.