No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by PrismorSec · MCP Server · ★ 296
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is prismor safe to install? View the security audit →
Prismor formerly Immunity Agent Runtime security hooks for Claude Code, Cursor, and other AI coding agents.Blocks dangerous commands, prevents secret leaks, and stops prompt injection in real time. Website · Onboard with Skill · CLI Reference · Supply Chain · Sweep & Cloak
| Stars | 296 |
| Forks | 27 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 69.7506643833937/100 |
| Open Issues | 45 |
| Last Updated | 2026-08-19 |
| Created | 2026-02-20 |
| Platforms | claude-code, codex, mcp, python |
| Est. Tokens | ~17k |
These tools work well together with prismor for enhanced workflows:
Looking for a prismor alternative? If you're comparing prismor with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply cha
See what your AI agents can access. Scan MCP configs for exposed secrets, shadow APIs, and AI models. Generate
The antivirus for OpenClaw — approve dangerous actions, scan skills, block secret leaks, and keep humans in co
Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor,
AI-first security scanner. NEW in v2026.7: Claude Code compromise detection — vet .claude/ hooks, permissions
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 296 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 296 stars and 27 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.
The top alternatives to prismor on Agent Skills Hub include agent-security-scanner-mcp, agentseal, mcp-audit. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.