typus-perp-mcp
MCP server for Typus Perp, enabling AI agents to query markets, manage positions, and execute trades on the Typus Perp DEX on Sui.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
Typus-Lab
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
mint_stake_lpDeposit tokens into the TLP liquidity pool and optionally stake the resulting TLP. Requires PRIVATE_KEY in .env.
stake_lpStake existing TLP tokens in the stake pool to earn rewards. Requires PRIVATE_KEY in .env.
unstakeBegin unstaking TLP (starts the unlock countdown). Requires PRIVATE_KEY in .env.
unstake_redeemUnstake and immediately redeem TLP for underlying tokens in one transaction. ⚠️ This does NOT return tokens to your wallet directly — you must call claim() afterwards to receive the underlying collateral. Requires PRIVATE_KEY in .env.
redeem_tlpRedeem TLP tokens (already unstaked) for underlying assets. ⚠️ This does NOT return tokens to your wallet directly — you must call claim() afterwards to receive the underlying collateral. Full flow: unstake → redeem_tlp → claim. Requires PRIVATE_KEY in .env.
claimClaim redeemed TLP tokens back as underlying collateral. This is the final step after unstake → redeem → claim. Requires PRIVATE_KEY in .env.
harvest_rewardHarvest pending staking reward tokens (e.g. TYPUS tokens). Requires PRIVATE_KEY in .env.
swapSwap tokens using Typus Perp liquidity pool. Requires PRIVATE_KEY in .env.
get_marketsGet all active trading markets and their configurations on Typus Perp (leverage, fees, funding rates, etc.)
get_lp_poolsGet TLP liquidity pool information including TVL and per-token liquidity amounts
get_stake_poolsGet TLP staking pool information including current TLP price and total staked shares
get_positionsGet all open positions for a wallet address, including liquidation price, unrealized PnL, funding fee, borrow fee, and close fee for each position
get_ordersGet all pending (unfilled) trading orders for a specific wallet address
get_user_stakeGet a user's TLP staking positions including staked share amounts, claimable rewards, and any shares currently in the unstaking cooldown period
create_orderCreate a trading order on Typus Perp. Requires PRIVATE_KEY in .env. Size and collateral amounts are raw integers — use get_markets to find size_decimal for the trading token.
cancel_orderCancel a pending trading order. Requires PRIVATE_KEY in .env.
increase_collateralAdd more collateral to an existing position to reduce liquidation risk. Requires PRIVATE_KEY in .env.
release_collateralWithdraw excess collateral from an existing position. Requires PRIVATE_KEY in .env.
collect_funding_feeCollect accumulated funding fees for a position. Requires PRIVATE_KEY in .env.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
NETWORKPRIVATE_KEYcp .env.example .env # then edit .env to add yourSUI_RPC_URLTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
19/19 tools missing one or more hints — mint_stake_lp (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); stake_lp (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); unstake (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +16 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool inputs are validated
Only 5/19 tool handlers declare input schemas (26%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 0/19 tool handlers wrap calls in try/catch (0%)
Wrap each tool handler body in try/catch and return a structured error response.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tests exist
No test files found
Add tests that exercise each declared tool.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.10.2 (high), @modelcontextprotocol/sdk@1.10.2 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/typus-lab/typus-perp-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check