ToolTrust
A4/100
Smithery

ic3moore-defimind-ai

mcpsmithery

@Smithery

**Live Uniswap V2/V3, Balancer, and Curve stableswap LP analytics over MCP.** Read real on-chain pool state through your own RPC (BYO-RPC, supplied per call) and get exact-math answers to LP questions — position PnL, price-move scenarios, pool health, rug signals, slippage, and depeg risk — or build a portable **State Twin** you can run unlimited counterfactuals against locally, off the MCP. **Authless & zero-config** — no account, no API key. Nothing is stored or logged; your RPC URL is redacted from any output. Each call reads the pool, runs the analysis, and returns a typed result. **Full docs: https://www.defimind.ai/mcp** These aren't API wrappers — they're closed-form AMM math, powered by the open-source [DeFiPy](https://defipy.org) library and its State Twin substrate. V3 impermanent loss is computed over the position's tick range via concentrated-liquidity math; Balancer IL is weight-aware; stableswap IL uses the amplified-invariant formula where small depegs can produce outsized IL at high A. **The math is open; the reports are paid.** ### Two surfaces - **Reactive primitives (10)** — one question, one answer, one chain read. The four scenario tools also take a **vector** input (e.g. `price_change_pcts[]`, `amounts_in[]`) to sweep a whole grid/curve in a single call. - **State-twin builder (1)** — `BuildStateTwin` returns the pool's state as a portable, verifiable JSON twin; rehydrate it locally to run any number of counterfactuals with **zero further RPC** (build once, run N). ### Tools (11) **Uniswap V2/V3** - `AnalyzePosition` — V2/V3 PnL decomposition (IL, fees, net) - `SimulatePriceMove` — "what if price moves X%?" scenarios - `CheckPoolHealth` — TVL, reserves, LP concentration, fee tier - `DetectRugSignals` — threshold-based rug-signal flags - `CalculateSlippage` — slippage, price impact, max trade size **Balancer (2-asset weighted)** - `AnalyzeBalancerLP` — weight-aware PnL decomposition (IL, net) - `SimulateBalancerMove` — weight-aware "what if the base moves X%?" scenarios **Curve stableswap (2-asset plain)** - `AnalyzeStableswapLP` — PnL via the amplified-invariant IL formula - `SimulateStableswapMove` — "what if the peg shifts X%?" depeg scenarios - `AssessDepegRisk` — IL across a depeg ladder (2%–50%), with a constant-product benchmark **State twin builder (all four pool types)** - `BuildStateTwin` — read a pool once and return a portable State Twin (JSON + `content_hash`) for unlimited off-MCP, zero-RPC analysis Each tool takes `pool_address`, `rpc_url`, and `pool_type` (`uniswap_v2` | `uniswap_v3` | `balancer` | `stableswap`), plus optional `chain_id` guard and `block_number` pin. Each reactive tool is protocol-specific and advertises only the `pool_type` values it accepts (pointing one at an unsupported type returns a clean error before any chain read); `BuildStateTwin` spans all four. Balancer tools cover 2-asset weighted pools; stableswap tools cover 2-asset plain Curve pools. Built on [DeFiPy](https://defipy.org) · [State Twins paper](https://arxiv.org/abs/2605.11522) · [MCP Docs](https://www.defimind.ai/mcp)

By Smithery | 36 findings | Scanned 7/4/2026 | tooltrust-scanner/v0.3.19

12 Low24 Info

Risk Summary

Safe With Normal Controls

Excessive Permissions is the main signal, but overall risk remains within an acceptable range.

Potential impact: The agent may gain overly broad access to files, network, databases, or execution capabilities.

Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.

Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.

Security Findings (36)

  • LowAS-002

    ⚠️Excessive Permissions

    AnalyzePosition:input schema exposes 11 properties (threshold: 10)

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×11

    tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration

    AnalyzePositionAnalyzeBalancerLPAnalyzeStableswapLPSimulatePriceMoveSimulateBalancerMoveSimulateStableswapMoveCheckPoolHealthDetectRugSignalsCalculateSlippageAssessDepegRiskBuildStateTwin

    Fix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.

  • InfoAS-002

    ⚠️Excessive Permissions ×11

    declared capabilities: network access

    AnalyzePositionAnalyzeBalancerLPAnalyzeStableswapLPSimulatePriceMoveSimulateBalancerMoveSimulateStableswapMoveCheckPoolHealthDetectRugSignalsAssessDepegRiskBuildStateTwin

    declared capabilities: code/command execution, network access

    CalculateSlippage

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable ×11

    Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.

    AnalyzePositionAnalyzeBalancerLPAnalyzeStableswapLPSimulatePriceMoveSimulateBalancerMoveSimulateStableswapMoveCheckPoolHealthDetectRugSignalsCalculateSlippageAssessDepegRiskBuildStateTwin

    Fix: Review and remediate the identified issue.

  • InfoAS-010

    🔑Insecure Secret Handling ×2

    input parameter "token_in_name" accepts a credential (informational; not evidence of insecure handling)

    CalculateSlippage

    input parameter "depeg_token_name" accepts a credential (informational; not evidence of insecure handling)

    AssessDepegRisk

    Fix: Avoid accepting raw credentials as input parameters. Use secret managers (e.g. 1Password CLI, AWS Secrets Manager) and ensure credentials are never logged or stored in agent traces.

Scan this tool yourself

Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.

Install once, then scan any MCP server:

$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash
$ tooltrust-scanner scan --server "npx -y ic3moore-defimind-ai"

Adjust the package name if your npm registry name differs from the tool ID. View source

Add badge to your README

Copy this Markdown to show your ToolTrust grade on GitHub.

[![ToolTrust Grade A](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-a.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)