by PrismorSec · MCP Server · ★ 422
Prismor Runtime security hooks for Claude Code, Codex, and other AI coding agents. Blocks dangerous commands, prompt injection, prevents secret leaks and recommends safe supply chain packages Prismor can also be used in observe mode to see agent session activity and dangerous actions in a local self-serve dashboard which grows by time Website • Onboard with Skill <a href="https://github.com/ant
| Stars | 422 |
| Forks | 56 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 37.3/100 |
| Open Issues | 68 |
| Last Updated | 2026-10-19 |
| Created | 2026-02-20 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~4699k |
These tools work well together with prismor for enhanced workflows:
Explore other popular mcp server tools:
prismor is Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agno. It is categorized as a MCP Server with 422 GitHub stars.
prismor is primarily written in Python. It covers topics such as agent-control-plane, agent-security, agents.
You can find installation instructions and usage details in the prismor GitHub repository at github.com/PrismorSec/prismor. The project has 422 stars and 56 forks, indicating an active community.
prismor is released under the Apache-2.0 license, making it free to use and modify according to the license terms.