Gives instructions about other tools
Model-facing text gives the AI model instructions about tools that this server does not provide (tool shadowing).
First seen · Last seen
Detected by Squatch rules from the server's metadata and protocol behavior. Latest completed scan: .
Model-facing text gives the AI model instructions about tools that this server does not provide (tool shadowing).
First seen · Last seen
Suggested fix: Describe only this server's own tools.
The remote server lists state-changing tools without requiring authentication.
First seen · Last seen
Suggested fix: Require MCP authorization for servers that expose state-changing tools.
The server's instructions field contains directives addressed to the AI model beyond describing how to use the server.
First seen · Last seen
Suggested fix: Limit server instructions to usage guidance for this server's own tools.
Model-facing text contains instructions addressed to the AI model rather than a description of the tool (for example to override prior instructions, to act before using tools, or to react to trigger phrases).
First seen · Last seen
Suggested fix: Describe what the tool does and its parameters. Do not include instructions to the model about other tools, the user or the conversation.
The tool runs code, commands or queries supplied at call time and does not declare a closed-world scope.
First seen · Last seen
Suggested fix: Narrow the tool to specific operations, or declare and enforce a closed-world sandbox.
A tool parameter asks the AI model to supply a password, token, key or similar credential, which the model can see and repeat.
First seen · Last seen
Suggested fix: Obtain credentials through server-side configuration or MCP authorization instead of tool arguments.
A tool parameter asks the AI model to supply a password, token, key or similar credential, which the model can see and repeat.
First seen · Last seen
Suggested fix: Obtain credentials through server-side configuration or MCP authorization instead of tool arguments.
The tool runs code, commands or queries supplied at call time and does not declare a closed-world scope.
First seen · Last seen
Suggested fix: Narrow the tool to specific operations, or declare and enforce a closed-world sandbox.
Model-facing text contains instructions addressed to the AI model rather than a description of the tool (for example to override prior instructions, to act before using tools, or to react to trigger phrases).
First seen · Last seen
Suggested fix: Describe what the tool does and its parameters. Do not include instructions to the model about other tools, the user or the conversation.
A tool that appears to delete data, change permissions or run code declares no tool annotations.
First seen · Last seen
Suggested fix: Declare readOnlyHint, destructiveHint, idempotentHint and openWorldHint so clients can request confirmation.
The tool's name and description do not state what it does.
First seen · Last seen
Suggested fix: Describe the action the tool performs, its target and its side effects.
The server failed one or more MCP protocol conformance checks.
First seen · Last seen
Suggested fix: Review the failed checks against the MCP specification.
A tool that appears to delete data, change permissions or run code declares no tool annotations.
First seen · Last seen
Suggested fix: Declare readOnlyHint, destructiveHint, idempotentHint and openWorldHint so clients can request confirmation.
A tool that appears to delete data, change permissions or run code declares no tool annotations.
First seen · Last seen
Suggested fix: Declare readOnlyHint, destructiveHint, idempotentHint and openWorldHint so clients can request confirmation.