Skip to content

NEUS MCP

by neus · remote · no sign-in to list tools · v1.3.9 · published by GitHub user neus

The trust harness for AI agents. Set what an agent can do before it acts.

Changes · 2
CompareRegistry entry

4 tools: 2 change things and 2 only read.

Scanned Oct 21, 2026

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

claude mcp add --transport http neus https://mcp.neus.network/mcp

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • Warnproofable_verify_or_guide

    The server marks "proofable_verify_or_guide" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "resolve": a word for reading.

    What this check looks for

Tools

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

4 tools

Changes things 2Claude Code: ask
  • proofable_proofs_checkDoes this wallet already have the required proofs?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
    Does this wallet already have the required proofs? Returns pass or fail, not records. Reading proof bodies needs a signed-in session, which is what unlocks proofable_proofs_get; signed-out callers get this check and can sign in to go further. Omit the wallet when signed in.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • proofable_verify_or_guideResolve a verification request for the selected Proofable checks.1 finding

    Why it is in this group

    • The description's first verb is "resolve": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    Findings

    • Warn

      The server marks "proofable_verify_or_guide" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "resolve": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Resolve a verification request for the selected Proofable checks. Returns current qualifying proofs when they exist; otherwise returns the single next step. This tool does not create a proof.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 2Claude Code: allow
  • proofable_contextReturn the signed-in Proofable profile and its current read-only context: proof index, agents, permissions, and verifier summary.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 signed-in Proofable profile and its current read-only context: proof index, agents, permissions, and verifier summary. Use once after sign-in.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • proofable_verifiers_catalogReturn supported check definitions with the inputs and networks each requires.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 supported check definitions with the inputs and networks each requires.

    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 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 1.3.9. Values in angle brackets are yours to fill in.

claude mcp add --transport http neus https://mcp.neus.network/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__neus__proofable_context",
      "mcp__neus__proofable_verifiers_catalog"
    ],
    "ask": [
      "mcp__neus__proofable_proofs_check",
      "mcp__neus__proofable_verify_or_guide"
    ],
    "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 neus. Review it before you use it.