DeFi Guard MCP
The safety layer that checks a DeFi transaction or token before your agent (or you) signs — on Base L2.
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
iinniitt
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.
aave_position_healthCheck the live health of an Aave V3 position on Base: health factor, total collateral/debt (USD), LTV and liquidation threshold. A health factor below 1.0 means the position is liquidatable.
quote_swapReal exact-input swap quote on Base via Uniswap V3 QuoterV2. Tries all fee tiers (0.01%, 0.05%, 0.3%, 1%) and returns the best executable output. Amounts are human units (e.g. '0.5').
token_risk_snapshotLiquidity risk snapshot of an ERC-20 on Base: metadata plus REAL market depth measured by round-trip quotes (WETH -> token -> WETH) at two trade sizes. High round-trip loss = thin/illiquid or high-fee market; a token you cannot exit is a risk regardless of its chart.
token_safety_screenPre-trade safety screen for an ERC-20 on Base — the 'is this safe to buy/approve BEFORE I sign' check. Verifies you can actually SELL it back (honeypot detection), measures the real round-trip cost (buy+sell fees/tax), and reports whether ownership is renounced (a live owner can often change taxes, …
scan_dangerous_capabilitiesScan a token/contract's DEPLOYED BYTECODE on Base for owner-only powers that can harm holders — mint, pause, blacklist, adjustable fees/taxes, max-tx limits, trading toggles, and proxy upgradeability. Flags the PRESENCE of each capability (a selector match in the code), i.e. what the operator COULD …
approval_riskAssess the risk of an existing ERC-20 approval on Base BEFORE it can be abused: reads the live allowance an owner has granted a spender, flags UNLIMITED approvals (the allowance-drain vector — a compromised or malicious spender can pull up to the allowance), and reports whether the spender is a cont…
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
BASE_RPC_URLNo API keys required — works out of the box against public Base RPCs (bring your own RPC for speed via ). Read-only: it never holds keys, signs, or submits.DEFI_GUARD_LICENSE_KEYDEFI_GUARD_METERINGDEFI_GUARD_TIERTool 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
6/6 tools missing one or more hints — aave_position_health (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); quote_swap (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); token_risk_snapshot (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +3 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 handlers catch errors
5/6 tool handlers wrap calls in try/catch (83%)
Wrap each tool handler body in try/catch and return a structured error response.
Tests exist
No test files found
Add tests that exercise each declared tool.
Production dependencies are patched
0 critical, 1 high severity in production deps — @modelcontextprotocol/sdk@1.0.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Domain consistency
npm scope @iniit doesn't match GitHub owner iinniitt
Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.
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/iinniitt/defi-guard-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