Skip to content

io.github.devlollc/torneo

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

Observatory operated and funded by devlo: real tools on frozen tasks; intervals, cost, limits.

Changes · 2
CompareRegistry entry

9 tools: 2 change things and 7 only read.

Scanned Oct 21, 2026

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

claude mcp add --transport http torneo https://torneo.ai/api/mcp

Tools

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

9 tools

Changes things 2Claude Code: ask
  • request_tournamentRequest a tournament using need.v1.No findings

    Why it is in this group

    • The name "request_tournament" says "request": a word for a change.
    Description, as the server wrote it
    Request a tournament using need.v1. Advisory only; never starts a run or spends. Follow the returned id with get_need.
  • submit_needLog an advisory need.v1 request.No findings

    Why it is in this group

    • The name "submit_need" says "submit": a word for a change.
    Description, as the server wrote it
    Log an advisory need.v1 request. Do not include personal or secret data. Returns need-id; persistence is partial until private ingestion and publication.
Only reads 7Claude Code: allow
  • decideRead-only decision.v1 for one category and a declared context: constraint applicability first, then EVIDENCE or ABSTAIN with a stable reason_code (answer_rule.v3).No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    Read-only decision.v1 for one category and a declared context: constraint applicability first, then EVIDENCE or ABSTAIN with a stable reason_code (answer_rule.v3). An abstention removes the verdict only; evidence, reservations and gaps stay. Never a rank on overlapping intervals. Replay and attestation verdicts are as of the last build.
  • explain_limitsLimits, freshness, conflicts and answer rule of a category or run.No findings

    Why it is in this group

    • The name "explain_limits" says "explain": a word for reading.
    Description, as the server wrote it
    Limits, freshness, conflicts and answer rule of a category or run. Read before citing evidence.
  • get_auto_tournamentAutomatic attempts, including failures: current private-store state when configured, otherwise a published snapshot.No findings

    Why it is in this group

    • The name "get_auto_tournament" says "get": a word for reading.
    Description, as the server wrote it
    Automatic attempts, including failures: current private-store state when configured, otherwise a published snapshot. No execution is triggered.
  • get_needFollow need-id in current private-store state when configured, otherwise the published snapshot.No findings

    Why it is in this group

    • The name "get_need" says "get": a word for reading.
    Description, as the server wrote it
    Follow need-id in current private-store state when configured, otherwise the published snapshot. Unknown or unavailable means partial, not refused.
  • get_resultsCanonical evidence for a category.No findings

    Why it is in this group

    • The name "get_results" says "get": a word for reading.
    Description, as the server wrote it
    Canonical evidence for a category. Cite observed_at, uncertainty and limits; never the best tool. INSUFFICIENT_EVIDENCE is not a ranking.
  • get_runCanonical result bundle or explicit PRE_REGISTERED state.No findings

    Why it is in this group

    • The name "get_run" says "get": a word for reading.
    Description, as the server wrote it
    Canonical result bundle or explicit PRE_REGISTERED state. Unknown cost is null / UNKNOWN.
  • list_categoriesDiscover categories with dated status and fixture flags.No findings

    Why it is in this group

    • The name "list_categories" says "list": a word for reading.
    Description, as the server wrote it
    Discover categories with dated status and fixture flags. Fixtures are synthetic, never real evidence.

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 torneo https://torneo.ai/api/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__torneo__list_categories",
      "mcp__torneo__get_results",
      "mcp__torneo__get_run",
      "mcp__torneo__explain_limits",
      "mcp__torneo__get_auto_tournament",
      "mcp__torneo__get_need",
      "mcp__torneo__decide"
    ],
    "ask": [
      "mcp__torneo__submit_need",
      "mcp__torneo__request_tournament"
    ],
    "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 torneo. Review it before you use it.