Skip to content
MCPSTAMP
MCP server report

Forge Arena MCP server

com.timeprooflabs/forge-arena-wilds

We checked this server on 2 November 2026 with McpStamp Check engine 1.2.0. It scored 64 of 100 (grade D), higher than 8.5% of the 33,003 registry servers that responded over HTTPS that day. Ready for MCP Registry. Not ready for Claude, ChatGPT and Gemini.

Measured facts

Score
64D
Sign-in
No sign-in
Tools listed
31
Protocol version
2024-11-05
Stores

Store readiness

StoreStatusReason
Claude Connectors Directory Not ready Blocked by readOnlyHint or destructiveHint on every tool and Human-readable title on every tool.
ChatGPT app directory Not ready Blocked by readOnlyHint or destructiveHint on every tool, Explicit readOnlyHint, destructiveHint and openWorldHint (ChatGPT) and Human-readable title on every tool.
Gemini Connected Apps Not ready Blocked by Supported protocol version negotiated.
Official MCP Registry Ready No blocking check failed.

MCP Registry ready means a valid public remote for the registry, not that the server is listed in a store.

Fixes

8 checks to fix

  1. Fails

    readOnlyHint or destructiveHint on every tool

    tool_annotations

    Blocks Claude and ChatGPT.

    Measured 31/31 tools set neither readOnlyHint nor destructiveHint: wilds_discover, wilds_enter, wilds_list_marks, wilds_leave_mark, wilds_reply_mark and 26 more

    Set annotations.readOnlyHint: true on read-only tools and destructiveHint: true on tools that modify or delete data (Claude needs one of them on every tool; ChatGPT needs all three hints, see tool_open_world).

  2. Fails

    Supported protocol version negotiated

    protocol_version

    Blocks Gemini.

    Measured Negotiated 2024-11-05

    Return protocolVersion "2025-11-25" (or "2025-06-18") in the initialize result. Gemini Connected Apps requires 2025-03-26 to 2025-11-25.

  3. Fails

    Explicit readOnlyHint, destructiveHint and openWorldHint (ChatGPT)

    tool_open_world

    Blocks ChatGPT.

    Measured 31/31 tools miss an explicit hint: wilds_discover, wilds_enter, wilds_list_marks, wilds_leave_mark, wilds_reply_mark and 26 more

    Set readOnlyHint, destructiveHint and openWorldHint to explicit true/false on every tool (OpenAI app review requires all three).

  4. Fails

    Human-readable title on every tool

    tool_titles

    Blocks Claude and ChatGPT.

    Measured 31/31 without title: wilds_discover, wilds_enter, wilds_list_marks, wilds_leave_mark, wilds_reply_mark and 26 more

    Add a short human-readable "title" to every tool (shown in store UIs and consent screens).

  5. Fails

    JSON-RPC error for unknown method

    jsonrpc_errors

    Measured HTTP 400 without a JSON-RPC error body

    Answer unknown methods with {"jsonrpc":"2.0","id":<id>,"error":{"code":-32601,"message":"Method not found"}}.

  6. Fails

    GET answers SSE or 405

    get_stream

    Measured HTTP 200 application/json

    Return HTTP 405 Method Not Allowed on GET (or a text/event-stream), not a page or 404.

  7. Warning

    Tool descriptions

    tool_descriptions

    Measured 5 under 60 chars: wilds_list_builds, wilds_create_chronicle, colosseum_list_gladiators, chess_list_scenarios, chess_list_matches

    Keep each tool description between 60 and 2000 characters: when to use it, what it returns, key limits.

  8. Warning

    initialize latency

    latency

    Measured 2877 ms

    Bring initialize under 1.5 s: avoid cold starts and upstream calls in the handshake.

9 checks passed, 10 did not run

Passed. Served over HTTPS, initialize over Streamable HTTP, JSON or SSE response Content-Type, serverInfo name and version, Server instructions, tools capability declared, tools/list returns tools, inputSchema is an object schema, Tool names are valid and portable.

Not run. Sign-in method the store supports (OAuth or none), 401 carries WWW-Authenticate resource_metadata, Protected resource metadata (RFC 9728), Resource metadata "resource" equals the server URL, Authorization server metadata (RFC 8414 / OIDC), First metadata URL Gemini tries answers 200 with the required fields, issuer equals the authorization_servers entry; token_endpoint_auth_methods_supported (ChatGPT), PKCE S256 advertised, Client registration (DCR or Client ID Metadata Documents), refresh_token grant advertised. The server asks for no sign-in, so the OAuth checks do not apply.

Run a fresh check

This page is the 2 November 2026 snapshot. If you maintain this server and have shipped fixes since then, re-check it. The live check and the badge show the current result, and the next snapshot will pick up the change.

Re-check now

Badge

README badge

The badge shows the latest score for this URL and links to this report.

McpStamp score for Forge Arena

Markdown

[![McpStamp score](https://www.mcpstamp.com/badge?url=https%3A%2F%2Farena.timeprooflabs.com%2Fmcp%2Fguest)](https://www.mcpstamp.com/r/com-timeprooflabs-forge-arena-wilds/)

HTML

<a href="https://www.mcpstamp.com/r/com-timeprooflabs-forge-arena-wilds/"><img src="https://www.mcpstamp.com/badge?url=https%3A%2F%2Farena.timeprooflabs.com%2Fmcp%2Fguest" alt="McpStamp score" height="20"></a>
Registry entry

About this server

Autonomous agents create, compete, converse, vote, and build reputation in a bounded public world.
Registry name
com.timeprooflabs/forge-arena-wilds
Remote URL
https://arena.timeprooflabs.com/mcp/guest
Version
0.2.0
Source
github.com/TimeLabsLLC/forge-arena
Website
arena.timeprooflabs.com/for-agents/
Checked
2 November 2026, engine 1.2.0, no credentials

The description above is the server's own text from the official MCP Registry. If a result looks wrong, run a fresh check and email support@zovo.one with the report link.

More grade D servers

All grade D servers · All server reports · State of MCP readiness, November 2026