mcp-shield
An MCP tool-definition security scanner that is insensitive to prompt-injection markers. Its interception counts on the benchmark are stable but low, which may indicate limited ability to detect real-world attack patterns.
Timeline (last 90 days)
On the MCPTox benchmark, the number of blocks by the five scanners on 218 retained test tools were: WARDEN 171, mcp-shield 41, truecopy 27, mcp-audit 25, and mcpsentry 8.
After adding an <IMPORTANT> prefix to the MCPTox tools, mcp-audit jumped from 25 to 222, truecopy from 27 to 141, mcpsentry from 8 to 136, WARDEN reached 225/225, while mcp-shield was 41 both before and after.
On the 14,933 real packages, the block rates of the five scanners from low to high were: truecopy 1.7% (252), WARDEN 2.5% (369), mcp-audit 6.2% (928), mcpsentry 9.7% (1,449), and mcp-shield 35.9% (5,354).
After manually reviewing the 996-package sample, of mcp-shield's 339 blocks only 1 held up (3 others were debatable); all 58 of mcp-audit's were invalid; of mcpsentry's 112, 1 held and 1 was debatable; all 17 of truecopy's were invalid; and of WARDEN's own 23 blocks, 0 should have blocked directly and 4 were debatable.
mcp-shield blocks whenever "token", "API key", "credentials", or ".." appears.
mcp-shield's MCP client directly rejects 26 tool lists because their inputSchema is not of type object, and then checks nothing in those lists.
All Facts (6)
On the MCPTox benchmark, the number of blocks by the five scanners on 218 retained test tools were: WARDEN 171, mcp-shield 41, truecopy 27, mcp-audit 25, and mcpsentry 8.
50%UnverifiedAfter adding an <IMPORTANT> prefix to the MCPTox tools, mcp-audit jumped from 25 to 222, truecopy from 27 to 141, mcpsentry from 8 to 136, WARDEN reached 225/225, while mcp-shield was 41 both before and after.
50%UnverifiedOn the 14,933 real packages, the block rates of the five scanners from low to high were: truecopy 1.7% (252), WARDEN 2.5% (369), mcp-audit 6.2% (928), mcpsentry 9.7% (1,449), and mcp-shield 35.9% (5,354).
50%UnverifiedAfter manually reviewing the 996-package sample, of mcp-shield's 339 blocks only 1 held up (3 others were debatable); all 58 of mcp-audit's were invalid; of mcpsentry's 112, 1 held and 1 was debatable; all 17 of truecopy's were invalid; and of WARDEN's own 23 blocks, 0 should have blocked directly and 4 were debatable.
50%Unverifiedmcp-shield blocks whenever "token", "API key", "credentials", or ".." appears.
50%Unverifiedmcp-shield's MCP client directly rejects 26 tool lists because their inputSchema is not of type object, and then checks nothing in those lists.
50%