Skip to content

AgentData - Executable Liquidity / Exit-Cost

by phenicea · remote · no sign-in to list tools · v0.1.0 · published by GitHub user phenicea

Size-aware exit cost, depeg risk & liquidity fragility for a Base token (x402, testnet).

Changes · 1
CompareRegistry entry

1 tool: 1 change things.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http agentdata-liquidity-exit-cost https://agentdata-liquidity-exit-cost.onrender.com/mcp/

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

1 tool

Changes things 1Claude Code: ask
  • liquidity_exit_costSize-aware exit cost, depeg risk, and liquidity fragility for a token on Base.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Size-aware exit cost, depeg risk, and liquidity fragility for a token on Base. Given a token and a sell size, returns the realized cost of exiting (price impact + fee, in bps and units), the best route across venues, an aggregated fragility score, and — for pegged assets — a depeg-risk score. Computed deterministically from on-chain AMM state, so the result is reproducible and auditable. Three tiers by compute depth (default 'risk'): 'quote' = best-route exit cost for one size; 'risk' = exit cost + fragility (+ depeg for pegged tokens); 'deep' = adds a multi-size exit-cost curve, max-size-before-cost thresholds, and an internal cross-check. Pricing per call (USDC): quote = $0, risk = $0, deep = $0. Status: testnet/preview — payment runs over the x402 HTTP surface, not this tool.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agentdata-liquidity-exit-cost https://agentdata-liquidity-exit-cost.onrender.com/mcp/

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__agentdata-liquidity-exit-cost__liquidity_exit_cost"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agentdata-liquidity-exit-cost. Review it before you use it.