Skip to content
MCPSTAMP
MCP server report

WingmanProtocol Agent Gateway MCP server

com.wingmanprotocol.agent/gateway

We checked this server on 2 November 2026 with McpStamp Check engine 1.2.0. It scored 74 of 100 (grade C), higher than 19.5% 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
74C
Sign-in
OAuth
Tools listed
61
Protocol version
2025-06-18
Stores

Store readiness

StoreStatusReason
Claude Connectors Directory Not ready Blocked by Protected resource metadata (RFC 9728), Authorization server metadata (RFC 8414 / OIDC) and Human-readable title on every tool.
ChatGPT app directory Not ready Blocked by Protected resource metadata (RFC 9728), Authorization server metadata (RFC 8414 / OIDC), Explicit readOnlyHint, destructiveHint and openWorldHint (ChatGPT) and Human-readable title on every tool.
Gemini Connected Apps Not ready Blocked by Authorization server metadata (RFC 8414 / OIDC).
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

7 checks to fix

  1. Fails

    Protected resource metadata (RFC 9728)

    auth_prm

    Blocks Claude and ChatGPT.

    Measured https://agent.wingmanprotocol.com/.well-known/oauth-protected-resource/mcp has no authorization_servers

    List your issuer URL in "authorization_servers" in the protected resource metadata.

  2. Fails

    Authorization server metadata (RFC 8414 / OIDC)

    auth_as_metadata

    Blocks Claude, ChatGPT and Gemini.

    Measured No authorization server to probe

    Serve RFC 8414 metadata at <issuer>/.well-known/oauth-authorization-server with authorization_endpoint, token_endpoint and response_types_supported ["code"].

  3. Fails

    Explicit readOnlyHint, destructiveHint and openWorldHint (ChatGPT)

    tool_open_world

    Blocks ChatGPT.

    Measured 61/61 tools miss an explicit hint: discover_tools, get_tool_schema, register_agent, store_artifact, submit_errand and 56 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 61/61 without title: discover_tools, get_tool_schema, register_agent, store_artifact, submit_errand and 56 more

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

  5. 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.

  6. Warning

    Tool descriptions

    tool_descriptions

    Measured 3 under 60 chars: list_memory, browse_type, browse_select

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

  7. Warning

    initialize latency

    latency

    Measured 1534 ms

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

14 checks passed, 6 did not run

Passed. Served over HTTPS, initialize over Streamable HTTP, Supported protocol version negotiated, JSON or SSE response Content-Type, JSON-RPC error for unknown method, serverInfo name and version, Server instructions, tools capability declared, Sign-in method the store supports (OAuth or none), Resource metadata "resource" equals the server URL, tools/list returns tools, inputSchema is an object schema, Tool names are valid and portable, readOnlyHint or destructiveHint on every tool.

Not run. 401 carries WWW-Authenticate resource_metadata, 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. These need an OAuth sign-in flow the check could not reach.

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 WingmanProtocol Agent Gateway

Markdown

[![McpStamp score](https://www.mcpstamp.com/badge?url=https%3A%2F%2Fagent.wingmanprotocol.com%2Fmcp)](https://www.mcpstamp.com/r/com-wingmanprotocol-agent-gateway/)

HTML

<a href="https://www.mcpstamp.com/r/com-wingmanprotocol-agent-gateway/"><img src="https://www.mcpstamp.com/badge?url=https%3A%2F%2Fagent.wingmanprotocol.com%2Fmcp" alt="McpStamp score" height="20"></a>
Registry entry

About this server

Durable memory, headless browser and research for agents. Pay per call: x402 USDC on Base or credits
Registry name
com.wingmanprotocol.agent/gateway
Remote URL
https://agent.wingmanprotocol.com/mcp
Version
1.7.1
Source
github.com/RIPRODUCTIONS/wingman-agent-gateway
Website
wingmanprotocol.com
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 C servers

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