Skip to content

POSTFACT — Resolve Ambiguous Side Effects Before Retry

by GSterlingPress · remote · no sign-in to list tools · v0.1.1 · published by GitHub user GSterlingPress

Resolve whether an uncertain side-effecting action completed before software retries it.

Changes · 1
CompareRegistry entry

1 tool: 1 change things.

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 postfact https://postfact-api-production.up.railway.app/mcp

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • Warnresolve_outcome

    The server marks "resolve_outcome" 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 "resolve_outcome" says "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.

1 tool

Changes things 1Claude Code: ask
  • resolve_outcomeCall after a side-effecting API/tool action fails ambiguously and before retrying.1 finding

    Why it is in this group

    • The name "resolve_outcome" says "resolve": a word for reading.
    • The description's first verb is "call": 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 "resolve_outcome" 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 "resolve_outcome" says "resolve": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Call after a side-effecting API/tool action fails ambiguously and before retrying. POSTFACT returns DONE only with affirmative completion evidence, NOT_DONE only with affirmative non-execution evidence, otherwise UNKNOWN. UNKNOWN is the safe default.

    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.

Install

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

claude mcp add --transport http postfact https://postfact-api-production.up.railway.app/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": [],
    "ask": [
      "mcp__postfact__resolve_outcome"
    ],
    "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 postfact. Review it before you use it.