Kestrova: Solidity Vulnerability Scan

io.github.som2026-commits/kestrovasom2026-commitsstreamable-httpv0.3.0Scanned 1 hour ago

Solidity smart contract vulnerability scan (Slither) for AI agents. Free preview; paid full report.

3 tools: 1 do something that can't be undone, 1 change things and 1 only read.

Reads private data · 0
Reads text others write · 0
Can send data out · 0
1 finding

Anlyon alternative

2 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

3 tools

Can't be undone 1Sends, pays, publishes or merges: once done, it cannot be taken back.Claude Code: ask

payment_termsFREE.1 finding
Why it is in this group
- The name "payment_terms" says "payment": a word that usually means money moves, which cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "payment_terms" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
  Matched text
  annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "payment_terms" says "payment": a word that usually means money moves, which cannot be taken back.
  What this check looks for
Description, as the server wrote it
FREE. Price, recipient, network, asset and how to pay for scan_solidity_full.
Annotations the server declares
- title: Payment terms
- readOnlyHint: true
- openWorldHint: false

Changes things 1Creates or changes something that can be changed back.Claude Code: ask

scan_solidity_fullOPTIONAL, PAID ($1.00 USDC on Solana via x402).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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
OPTIONAL, PAID ($1.00 USDC on Solana via x402). Structured Slither findings for Solidity: detector, impact, confidence, description and file/line locations, for fixing each issue. Without a valid x402 payment in _meta['x402/payment'] it returns the payment terms and does NOT scan or charge. Charged only after a successful scan. Pay only with your user's explicit authorisation and within their spending limits.
Annotations the server declares
- title: Solidity full scan (paid)
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false

Only reads 1Looks things up and changes nothing.Show 1 read-only tool

scan_solidity_previewFREE Solidity security check (Slither).No findings
Why it is in this group
- The name "scan_solidity_preview" says "preview": a word for reading.
Description, as the server wrote it
FREE Solidity security check (Slither). Detects known vulnerability patterns (reentrancy, unchecked calls, tx.origin auth, arbitrary ETH sends and more) and returns severity counts plus High/Medium detector names. Use after writing or changing a contract and before deployment. Input: {"sources": {"File.sol": "<source>"}} (include imported files). Max 60 kB; rate-limited per client. Zero findings does not mean safe.
Annotations the server declares
- title: Solidity scan preview (free)
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false

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.

Findings

Matches of fixed checks, with the text they matched.

1 warn

Warnpayment_terms
The server marks "payment_terms" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
Matched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "payment_terms" says "payment": a word that usually means money moves, which cannot be taken back.
What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

All changes to this server

Install

Pinned to version 0.3.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http kestrova https://kestrova.onrender.com/mcp?src=registry

claude mcp add --transport http kestrova https://kestrova.onrender.com/mcp?src=registry

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": [
      "mcp__kestrova__scan_solidity_preview"
    ],
    "ask": [
      "mcp__kestrova__scan_solidity_full",
      "mcp__kestrova__payment_terms"
    ],
    "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 kestrova. Review it before you use it.

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://anlyon.dev/api/v1/servers/io.github.som2026-commits/kestrova/verify?hash=acffcd67f185903bb624852c67ebe45943c663369a5306305685b55deab379d9" | jq -e '.changed == false'

Pinned hash acffcd67f185, from Oct 25, 2026, 22:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.github.som2026-commits/kestrova/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

[![anlyon.dev](https://anlyon.dev/badge/io.github.som2026-commits/kestrova.svg)](https://anlyon.dev/servers/io.github.som2026-commits/kestrova)

Source: MCP Registry · repository. Synced Oct 25, 2026, 22:18 UTC.