Logiqical

74 tools. 25 can modify or destroy data without limits.

10 destructive tools with no built-in limits. Policy required.

Last updated:

25 can modify or destroy data
49 read-only
74 tools total

Community server · catalogue entry verified 01/07/2026

How to control Logiqical ↓

What Logiqical exposes to your agents

Read (49) Write / Execute (15) Destructive / Financial (10)
Critical Risk

The most dangerous Logiqical tools

25 of Logiqical's 74 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Logiqical

PolicyLayer is an MCP gateway — it sits between your AI agents and Logiqical, and nothing reaches the server without passing your rules. These are the rules we recommend:

Block financial tools by default
{
  "build_buy_and_stake_txs": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Deny destructive operations
{
  "perps_cancel_orders": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "perps_enable_hip3": {
    "limits": [
      {
        "counter": "perps_enable_hip3_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "bridge_chains": {
    "limits": [
      {
        "counter": "bridge_chains_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Logiqical — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON LOGIQICAL →

Instant setup, no code required.

All 74 Logiqical tools

READ 49 tools
Read bridge_chains Get all supported chains for cross-chain bridging via Li.Fi Read bridge_connections Get available bridge paths between two chains Read bridge_info Get reference info: supported chain IDs, USDC addresses, native token constant Read bridge_quote Get a cross-chain bridge quote with unsigned transaction. Agent signs the tx on the source chain. Read bridge_routes Get multiple cross-chain bridge route options Read bridge_status Check the status of a cross-chain bridge transfer Read bridge_token Get info for a specific token on a chain Read bridge_tokens Get tokens available on specified chains Read broadcast_tx Broadcast a signed transaction to Avalanche C-Chain Read dex_balance Check balance of any token for a wallet Read dex_quote Get a swap quote with expected output and price impact Read dex_token_info Look up any ERC-20 token by contract address Read dex_tokens List popular tokens available for swapping on Avalanche Read get_balances Get a wallet Read get_quote Get a price quote for buying ARENA with AVAX. Shows fee breakdown. Read get_sell_quote Get a price quote for selling ARENA for AVAX. Read get_skill Get the full Logiqical skill documentation (markdown) Read get_stake_info Get staking position: amount staked and pending rewards Read launchpad_activity Get recent buy/sell activity for a launchpad token Read launchpad_graduating Get tokens closest to graduating (deploying LP to DEX) Read launchpad_overview Get platform overview: total tokens, fees, contract addresses Read launchpad_portfolio Get your launchpad token positions and PnL Read launchpad_quote Get a buy or sell quote for a launchpad token Read launchpad_recent Get recently launched tokens on Arena launchpad Read launchpad_search Search for tokens by name, symbol, or contract address Read launchpad_token_info Get comprehensive info for a launchpad token Read launchpad_top_volume Get trending tokens by volume Read perps_auth_payload Get EIP-712 payload for a perps auth step Read perps_auth_status Check which auth steps are completed for perps Read perps_get_executions Get perps trade execution history Read perps_get_orders Get open perps orders Read perps_get_positions Get current perps positions and margin summary from Hyperliquid Read perps_registration_status Check perps registration and wallet status Read perps_trading_pairs Get all 250+ perpetual trading pairs with leverage limits and precision Read perps_wallet_address Get your Hyperliquid API wallet address Read social_chat_conversations List all chat conversations Read social_chat_dms List direct message conversations Read social_chat_groups List group chats Read social_chat_members Get members of a chat group Read social_chat_messages Read messages from an Arena chat room Read social_me Get your agent Read social_search_users Search Arena users by name or handle Read social_top_users Get top/trending Arena users Read social_user_by_handle Get Arena user profile by handle Read tickets_balance Get ticket balance for a user on a subject Read tickets_buy_price Get the buy price for Arena tickets (supports fractional: 0.5, 1.2, 3) Read tickets_fees Get Arena ticket fee structure (protocol, subject, referral) Read tickets_sell_price Get the sell price for Arena tickets Read tickets_supply Get total ticket supply for a subject

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about Logiqical

Can an AI agent move money through the Logiqical MCP server? +

Yes. The Logiqical server exposes 9 financial tools including build_buy_and_stake_txs, build_sell_arena_tx, build_stake_txs. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

Can an AI agent delete data through the Logiqical MCP server? +

Yes. The Logiqical server exposes 1 destructive tools including perps_cancel_orders. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Logiqical? +

The Logiqical server has 10 write tools including perps_enable_hip3, perps_register, perps_update_leverage. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Logiqical.

How many tools does the Logiqical MCP server expose? +

74 tools across 4 categories: Destructive, Execute, Read, Write. 49 are read-only. 25 can modify, create, or delete data.

How do I enforce a policy on Logiqical? +

Register the Logiqical MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Logiqical tool call.

Deterministic rules across all 74 Logiqical tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

74 Logiqical tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.