PR
Security and policy enforcement for AI coding agents
Prismor helps you control what coding agents can do before commands run. It combines a CLI, GitHub App, CI/build scanning, and MCP support for scanning dependencies, code, secrets, and agent actions.
Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric →
Enterprise
Open Source
Chrome Extension
Integrations
B2B
CLI
MCP Support
About
What It Is
What to Know
Key Features
Intercepts AI agent tool calls before execution
Blocks dangerous tool calls based on policy
Scans repositories locally or in CI with the CLI
Scans pull requests through a GitHub App
Finds vulnerabilities and secrets from an editor over MCP
Use Cases
Securing Claude Code, Cursor, or other coding agents in day-to-day development
Scanning pull requests for vulnerabilities before merge
Running repository scans in local development or CI pipelines
Agenticness
: Adaptive Collaborator
Proposes and executes multi-step plans with your approval.
High evidence
Last evaluated:
Aug 3, 2026
Dimension Breakdown
Action Capability
Autonomy
Planning
Adaptation
State & Memory
Reliability
Interoperability
Safety
Operator Sovereignty
Categories
Pricing
- Free / open source — full functionality available at no cost.
Details
AddedAugust 3, 2026
RefreshedAugust 18, 2026
Agenticness
Quick Facts
DeploymentHybrid (cloud + self-hosted)
AutonomyCopilot (human-in-loop)
Model supportSingle model
Open sourceYes
MCP supportYes
Team supportEnterprise
Pricing modelFree / open source
Interfacecli, gui, api
Sources
Last updated
August 19, 2026
Free daily brief
When Prismor changes its pricing, we catch it the next morning
We recrawl every tool in this directory daily. AI Insider is the 3-minute brief on what actually changed — pricing, features, score moves on our 36-point rubric — often before any press coverage. Sent daily. Skipped when nothing happened.
Comments
Nothing yet. Say the first thing.
Sign in to join the conversation.