Skip to content

Magneta Contract Risk MCP server

io.github.Bosacks/magneta-contract-riskBosacksstreamable-httpv0.1.1Scanned

Smart-contract risk reports for AI agents on 20 EVM chains, paid per call via x402 ($0.02 USDC).

4 tools: 1 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 1 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 2
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here changes things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Magneta Contract Risk MCP server can do

The Magneta Contract Risk MCP server is published by the GitHub account Bosacks. It has 4 tools. It can create or change data (1 tool: contract_quick_flags), but cannot delete data. 3 tools only read.

2 tools bring in text other people can write (contract_risk_summary and contract_quick_flags).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 15, 2026, version 0.1.1.

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.

4 tools

Changes things 1Claude Code: ask
  • contract_quick_flagsFree, no payment: bytecode-only preview of a deployed smart contract.Reads text others writeNo 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.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Free, no payment: bytecode-only preview of a deployed smart contract. Covers proxy/upgradeability, ERC-20 probe (name, symbol, owner, paused), risky selectors found in the bytecode (mint, blacklist, fee/tax setters, pause, upgrade), SELFDESTRUCT/DELEGATECALL opcodes, and a partialScore/partialLevel computed from those on-chain signals only. Does NOT cover source verification (Blockscout, Sourcify) nor aderyn static analysis, so partialScore can be lower than the real risk. contract_risk_summary ($0.01 in USDC via x402) is the full report. Read-only, no side effects; an EOA is rejected; identical requests within 10 minutes return the cached result; the HTTP twin GET /v1/flags/:chainId/:address is rate limited to 30 requests per minute per IP.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 3Show 3 read-only tools
  • contract_risk_summaryAnalyze a deployed smart contract and return a deterministic risk report: 0-100 score with level (low/medium/high/critical), proxy/upgradeability, owner and pause state, risky sele…Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "analyze": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Analyze a deployed smart contract and return a deterministic risk report: 0-100 score with level (low/medium/high/critical), proxy/upgradeability, owner and pause state, risky selectors found in the bytecode (mint, blacklist, fee/tax setters, pause, upgrade), SELFDESTRUCT/DELEGATECALL opcodes, source verification (Blockscout, Sourcify) and aderyn static-analysis findings. Use it before trading, bridging, approving or integrating a token or protocol contract; Use contract_quick_flags first for a free bytecode-only preview when you are not sure the full report is worth paying for. Use supported_chains first if you are unsure the chain id is covered, and scoring_rubric to interpret the score. Paid: $0.01 in USDC on Base per call via x402. The first call answers with an x402 payment challenge; an x402-enabled client pays automatically and the same call then returns the report. Read-only, no side effects. Error cases (unsupported chain, invalid address, address is not a contract, upstream data source failure or timeout) return an isError result with an error message and are not charged; identical requests within 10 minutes return the cached report.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • scoring_rubricReturn the exact rubric behind contract_risk_summary scores: points per flag, the level thresholds and what each flag means.No findings

    Why it is in this group

    • The description's first verb is "return": a word for reading.
    Description, as the server wrote it
    Return the exact rubric behind contract_risk_summary scores: points per flag, the level thresholds and what each flag means. Free, read-only, no parameters. Call it to explain a score to a user or to decide your own threshold before acting on a report.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • supported_chainsList the EVM chains contract_risk_summary can analyze, as { chainId, name, testnet } objects.No findings

    Why it is in this group

    • The description's first verb is "list": a word for reading.
    Description, as the server wrote it
    List the EVM chains contract_risk_summary can analyze, as { chainId, name, testnet } objects. Free, read-only, no payment and no parameters. Call it when you need to map a chain name to its id or to check coverage before paying for a report.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • 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 outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
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.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:56 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
1
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://x402.magneta.finance/mcp: tools/list returned 4 tools to an anonymous client, including contract_quick_flags (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

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

  1. Tools2 changed.~2 changedView diff

Install

Pinned to version 0.1.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http magneta-contract-risk https://x402.magneta.finance/mcp
claude mcp add --transport http magneta-contract-risk https://x402.magneta.finance/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": [
      "mcp__magneta-contract-risk__contract_risk_summary",
      "mcp__magneta-contract-risk__supported_chains",
      "mcp__magneta-contract-risk__scoring_rubric"
    ],
    "ask": [
      "mcp__magneta-contract-risk__contract_quick_flags"
    ],
    "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 magneta-contract-risk. Review it before you use it.

Capability tags behind 2 rules
  • mcp__magneta-contract-risk__contract_risk_summary untrusted-input
  • mcp__magneta-contract-risk__contract_quick_flags untrusted-input

Pin

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://radar.anlyon.com/api/v1/servers/io.github.Bosacks/magneta-contract-risk/verify?hash=7524a580bd403f6e1b3789516d7fe44e398d27c3ebb2849e56e0da4d9e614a68" | jq -e '.changed == false'

Pinned hash 7524a580bd40, from Nov 15, 2026, 17:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.Bosacks/magneta-contract-risk/changes.xml

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

Badge

Anlyon Radar badge for io.github.Bosacks/magneta-contract-risk
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.Bosacks/magneta-contract-risk.svg)](https://radar.anlyon.com/servers/io.github.Bosacks/magneta-contract-risk)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:14 UTC.

Magneta Contract Risk MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Magneta Contract Risk MCP server safe?

No scan can promise that. What its definitions show: 4 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Magneta Contract Risk MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Magneta Contract Risk MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Magneta Contract Risk MCP server have?

4 tools: 1 write, 3 read. contract_quick_flags, contract_risk_summary, supported_chains and scoring_rubric.

Does the Magneta Contract Risk MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Magneta Contract Risk MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Magneta Contract Risk MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 2, 2026. Every change is on this page and in its Atom feed.