Skip to content
MCPSTAMP
MCP server report

Mcp MCP server

com.googleapis.stitch/mcp

We checked this server on 2 November 2026 with McpStamp Check engine 1.2.0. It scored 85 of 100 (grade B), higher than 31.2% of the 33,003 registry servers that responded over HTTPS that day. Ready for Gemini and MCP Registry. Not ready for Claude and ChatGPT.

Measured facts

Score
85B
Sign-in
OAuth
Tools listed
16
Protocol version
2025-11-25
Stores

Store readiness

StoreStatusReason
Claude Connectors Directory Not ready Blocked by Human-readable title on every tool.
ChatGPT app directory Not ready Blocked by issuer equals the authorization_servers entry; token_endpoint_auth_methods_supported (ChatGPT), Explicit readOnlyHint, destructiveHint and openWorldHint (ChatGPT) and Human-readable title on every tool.
Gemini Connected Apps Ready No blocking check failed.
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

6 checks to fix

  1. Fails

    Explicit readOnlyHint, destructiveHint and openWorldHint (ChatGPT)

    tool_open_world

    Blocks ChatGPT.

    Measured 5/16 tools miss an explicit hint: list_projects, list_screens, get_screen, download_file, list_design_systems

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

  2. Fails

    Human-readable title on every tool

    tool_titles

    Blocks Claude and ChatGPT.

    Measured 16/16 without title: create_project, get_project, delete_project, list_projects, list_screens and 11 more

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

  3. Fails

    issuer equals the authorization_servers entry; token_endpoint_auth_methods_supported (ChatGPT)

    auth_chatgpt_metadata

    Blocks ChatGPT.

    Measured issuer "https://accounts.google.com" is not exactly the authorization_servers entry "https://accounts.google.com/"

    Use the exact metadata "issuer" string in the protected resource metadata authorization_servers list (no trailing-slash or case differences), and list token_endpoint_auth_methods_supported (for example ["none"] for public clients) in the au

  4. Fails

    Server instructions

    instructions

    Measured No instructions in the initialize result

    Add an "instructions" string to the initialize result: what the server covers, for whom, and its limits.

  5. Warning

    Client registration (DCR or Client ID Metadata Documents)

    auth_registration

    Measured No registration_endpoint and no client_id_metadata_document_supported

    Add a Dynamic Client Registration endpoint (RFC 7591) or set client_id_metadata_document_supported: true; otherwise every store needs a manually issued client id.

  6. Warning

    Tool descriptions

    tool_descriptions

    Measured 2 under 60 chars: list_screens, list_design_systems

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

20 checks passed, 1 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, GET answers SSE or 405, initialize latency, serverInfo name and version, tools capability declared, Sign-in method the store supports (OAuth or none), 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, PKCE S256 advertised, refresh_token grant advertised, 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. 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 Mcp

Markdown

[![McpStamp score](https://www.mcpstamp.com/badge?url=https%3A%2F%2Fstitch.googleapis.com%2Fmcp)](https://www.mcpstamp.com/r/com-googleapis-stitch-mcp/)

HTML

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

About this server

Interact with the Stitch API using natural language commands.
Registry name
com.googleapis.stitch/mcp
Remote URL
https://stitch.googleapis.com/mcp
Version
1.0.0
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 B servers

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