EchoLedger

Live LP analytics — Uniswap V2/V3, Balancer, Curve stableswap: PnL, health, slippage, depeg risk.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

    What data it sees

    Do you need an account

    No: the server works without sign-in

    Live LP analytics — Uniswap V2/V3, Balancer, Curve stableswap: PnL, health, slippage, depeg risk.

    How to connect

    How to connect EchoLedger to Claude

    The server address to paste into Claude settings:

    https://mcp.echoledger.ai/mcp

    1. Open Claude (claude.ai or the desktop app).
    2. Go to Settings → Connectors.
    3. Click Add custom connector.
    4. Paste the server address copied below into Remote MCP server URL and click Add.
    5. In a chat, click + → Connectors and switch the new connector on.

    Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

    Authorization

    After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

    How to connect EchoLedger to ChatGPT

    The server address to paste into ChatGPT settings:

    https://mcp.echoledger.ai/mcp

    1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
    2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
    3. Open Settings → Connectors and click Create.
    4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
    5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
    6. In a new chat open + → Apps/Connectors and enable the connector.

    OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

    Authorization

    On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

    How to connect EchoLedger to Cursor

    The server address to paste into Cursor settings:

    https://mcp.echoledger.ai/mcp

    Fastest: click Open in Cursor below and confirm the prompt.

    Manually:

    1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
    2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
    3. Save the file. The server appears in the MCP list; authorize it there if asked.

    Authorization

    If the service needs sign-in, an authorize button appears next to the server in the MCP list.

    Server tool list (11)

    Raw names from tools/list. Only developers need these.

    AnalyzePositionAnalyze why a Uniswap V2 or V3 LP position is gaining or losing money. Decomposes PnL into impermanent loss, accumulated fees, and net result, with optional real APR if a holding period is supplied. Returns current value, hold value, IL percentage, fee income, net PnL, real APR, and a diagnosis label.
    AnalyzeBalancerLPAnalyze a 2-asset Balancer weighted-pool LP position's PnL. Decomposes impermanent loss using the weighted-pool formula where the base token's weight affects IL magnitude. Values are denominated in opp-token units per BalancerImpLoss's convention; fee income is not attributed in v1 because Balancer pools only expose vault-level fees with no per-LP attribution.
    AnalyzeStableswapLPAnalyze a 2-asset Curve-style Stableswap LP position's PnL using the amplified-invariant IL formula where small depegs can produce surprisingly large IL at high A. Values are in peg-numeraire (tokens valued 1:1); fee income is not attributed in v1 (pool-global only); positions whose implied alpha is in the unreachable regime return None on il_percentage, net_pnl, and real_apr.
    SimulatePriceMoveProject a Uniswap V2 or V3 LP position's value at a hypothetical price change from the CURRENT pool state (not from entry). A price_change_pct of -0.30 asks 'what if price drops 30% from here'. Returns new value, IL at the simulated price, and percentage change in position value. Fee projection is not modeled (always null).
    SimulateBalancerMoveProject a 2-asset Balancer weighted-pool LP position's value at a hypothetical price change from the CURRENT pool state. The shock is applied to the base-token price in opp units; IL depends on both the shock magnitude and the pool's weights. Returns new value in opp-numeraire, IL at the simulated price, and percentage change.
    SimulateStableswapMoveProject a 2-asset Curve-style Stableswap LP position's value at a hypothetical depeg from the CURRENT pool state. The shock multiplies the pool's current alpha by (1 + price_change_pct); at high A, large shocks may be physically unreachable and in that case new_value, il_at_new_price, and value_change_pct are returned as null. Values are in peg-numeraire.
    CheckPoolHealthSnapshot pool-level health metrics for a Uniswap V2 or V3 pool: TVL in token0 numeraire, reserves, accumulated fees, LP concentration, and swap activity. Answers 'is this a pool I would deposit into?' at the pool level (not position level). num_swaps and fee_accrual_rate_recent are V2-only; V3 returns null for these because V3 has no per-swap history array. A single-block live snapshot also returns null for the LP-concentration and swap metrics (unrecoverable from state alone).
    DetectRugSignalsDetect rug-pull signals on a Uniswap V2 or V3 pool via three threshold checks: suspiciously low TVL, top-LP concentration above a limit, and inactive-pool-with-liquidity. Composes over CheckPoolHealth and returns per-signal booleans plus a count-based risk level (low/medium/high/critical). The inactive-with-liquidity signal is V2-only; V3 pools report False for it with a note in details.
    CalculateSlippageCalculate slippage and price-impact decomposition for a proposed swap on a Uniswap V2 or V3 pool. Returns spot vs execution price, slippage percentage, slippage cost in output-token units, and price impact. Also returns the maximum trade size that stays within 1% slippage for V2 pools; V3 returns null for that field because tick-crossing math has not yet been inverted.
    AssessDepegRiskQuantify a 2-asset Curve-style Stableswap LP position's exposure to a stablecoin depeg. Computes IL at multiple depeg levels (default 2%, 5%, 10%, 20%, 50%) via the closed-form stableswap-invariant expansion, with an optional V2 constant-product benchmark at each level. Some depeg levels are physically unreachable at high A — unreachable scenarios return null on il_pct, lp_value_at_depeg, and hold_value_at_depeg; the V2 benchmark stays populated.
    BuildStateTwinRead a pool's on-chain state once and return it as a serialized State Twin (JSON): the protocol-specific snapshot plus a content_hash, in the wire form a client rehydrates locally. Use this to pull a single managed-RPC twin, then run any number of counterfactuals (price moves, IL, slippage) client-side, off this server. Covers Uniswap V2/V3, Balancer 2-asset weighted, and Curve 2-asset plain stableswap pools. The endpoint stores and logs nothing — your rpc_url is never persisted.