Skip to content

MCP Operation Risk

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

Operation-level risk guidance for consolidated MCP tools, including schema drift and retry signals.

Changes · 1
CompareRegistry entry

2 tools: 1 change things and 1 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 operation-risk https://87-106-119-237.sslip.io/mcp-operation-risk/mcp

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • Warnevaluate_operation_risk

    The server marks "evaluate_operation_risk" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "evaluate_operation_risk" says "evaluate": a word for a change.

    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.

2 tools

Changes things 1Claude Code: ask
  • evaluate_operation_riskCheck whether the actual operation inside an MCP tool call is safe before execution.1 finding

    Why it is in this group

    • The name "evaluate_operation_risk" says "evaluate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "evaluate_operation_risk" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "evaluate_operation_risk" says "evaluate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Check whether the actual operation inside an MCP tool call is safe before execution. Use this when one MCP tool exposes multiple operations with different side effects, so whole-tool permissions are too coarse. Provide the native MCP server identity, the tool's tools/list metadata and the intended arguments. For supported consolidated tools, distinguish read, create/add, update/mutate and delete/destructive operations. Return ALLOW, DENY, or REQUIRE_APPROVAL. Unknown, unsupported, ambiguous, or schema-changed calls fail closed with REQUIRE_APPROVAL. The evaluator never executes the source operation.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
Only reads 1Claude Code: allow
  • describe_operation_risk_serviceCheck whether the actual operation inside an MCP tool call is safe before execution.No findings

    Why it is in this group

    • The name "describe_operation_risk_service" says "describe": a word for reading.
    Description, as the server wrote it
    Check whether the actual operation inside an MCP tool call is safe before execution. Use this when one MCP tool exposes multiple operations with different side effects, so whole-tool permissions are too coarse. Provide the native MCP server identity, the tool's tools/list metadata and the intended arguments. For supported consolidated tools, distinguish read, create/add, update/mutate and delete/destructive operations. Return ALLOW, DENY, or REQUIRE_APPROVAL. Unknown, unsupported, ambiguous, or schema-changed calls fail closed with REQUIRE_APPROVAL. The evaluator never executes the source operation.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true

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.

Install

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

claude mcp add --transport http operation-risk https://87-106-119-237.sslip.io/mcp-operation-risk/mcp

Run in a terminal.

Claude Code permissions

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

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__operation-risk__describe_operation_risk_service"
    ],
    "ask": [
      "mcp__operation-risk__evaluate_operation_risk"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as operation-risk. Review it before you use it.