AI agent security evaluation toolkit. MCPBench scores the tool calls your agent actually makes, using rogue MCP servers, poisoned tool descriptions, rug pulls, shadow servers and planted canaries. 30 scenarios across MCP01 to MCP05.
Cross-referenced across 55 tracked directories
#52237
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
10/23/2026
Created
1
GitHub Stars
10/23/2026
Last Commit
Recently added to the ecosystem
Score: 100/100
0 dependency vulnerabilities found
b959a1af-c170-4c4c-ad27-457ed2959de8
Search a vast catalog of books on Anna's Archive. Discover editions, formats, and metadata to quickly pinpoint the right copy. Download selected titles for fast, offline access.
...more59b9f352-8cdc-44d3-9dd9-db3bfa521880
No description available
planetabhi
A comprehensive local MCP server for Figma. Connect Figma with the Gemini CLI, Cursor, and Claude Desktop.