Loading…
Provides access to Google Chat for searching conversations and listing messages.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 1 month ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The StatelessServer MCP server exposes 4 tools, focused primarily on communication capabilities. Its published description reads: "Provides access to Google Chat for searching conversations and listing messages". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates StatelessServer F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Hidden instructions in a tool description" and "Data-exfiltration parameters". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check StatelessServer's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add StatelessServer to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://chatmcp.googleapis.com/mcp/v1Streamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Retrieves messages from a specified Google Chat conversation (Space, direct message (DM) or group DM) in Markdown format. Allows filtering by thread, time range, and number of messages. Additionally,
Searches for Google Chat messages using keywords and filters returning them in Markdown format. Works across all spaces the user has access to, or can be scoped to a specific conversation. Follow this
Searches for Google Chat conversations (named spaces, direct messages (DMs), or group chats) by display name or participants to find conversation IDs. This tool searches conversation metadata, NOT mes
Sends a Google Chat message to a conversation with Markdown formatting. This tool uses a conversation ID, an optional thread ID, and a message text as inputs. Conversation ID's can be found using the
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: search_conversations
A tool description contains imperative text aimed at the model (e.g. "ignore previous", "before answering read …").
rsation types. IMPORTANT: An empty 'conversations' list does not mean theRecommendationRemove model-directed instructions from tool descriptions.
tool: search_messages
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
d to a specific conversation. Follow this guidance when deciding to use seaRecommendationRemove side-channel parameters; constrain tool inputs.
tool: search_messages
A tool description tries to alter the model’s use of another tool.
ion ID. - Use list_messages when you know the specific space or thread ID aRecommendationDescriptions must describe only their own tool.
tool: search_messages
One tool reads private data, ingests untrusted content, AND can send data outbound — the three preconditions for autonomous data theft in a single call. A prompt injection reaching this tool can exfiltrate secrets with no further step.
ID and want to read messages sequentially in chronological order. - Use seRecommendationSplit the capabilities across separate least-privilege tools so no single tool can read secrets, read untrusted input, and reach the network at once.
tool: search_conversations
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
search_conversations Searches for Google Chat conversations (namedRecommendationRemove side-channel parameters; constrain tool inputs.
tool: search_conversations
A tool description tries to alter the model’s use of another tool.
/timestamp, use search_messages. If only participants are provided, this toolRecommendationDescriptions must describe only their own tool.
tool: send_message
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
at message to a conversation with Markdown formatting. This tool uses a conRecommendationRemove side-channel parameters; constrain tool inputs.
tool: send_message
A tool description tries to alter the model’s use of another tool.
found using the search_conversations tool. It returns the created message.RecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: send_message
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: send_message
Role tokens or delimiter abuse steer the model rather than describe the tool.
ospace block:** ``` line 1 line 2 ``` * **Bulleted list:** * item 1RecommendationWrite neutral, descriptive tool metadata.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.