1999AZZAR/project-guardian-mcp-server

An MCP server that acts as a central memory system and workflow guardian for AI agents, featuring knowledge graph capabilities and autonomous guidance prompts.

3Stars on the repository
6Mods indexed here, across every type
7d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

guardian-cache

01

1999AZZAR/project-guardian-mcp-server

Skill Codex

Store temporary agent state and cached API results in Redis using enforced mema: namespaces and TTL controls. Use when session data or expensive intermediate results must be shared across steps or sub-agents.

not rated 3 7d ago A 41 tokens original MIT

guardian-memory

02

1999AZZAR/project-guardian-mcp-server

Skill Codex

Maintain project context in Project Guardian's memory.db knowledge graph. Use during coding, debugging, planning, and project-management sessions to restore relevant context and record significant decisions, changes, tasks, and milestones.

not rated 3 7d ago A 43 tokens original MIT

guardian-security

03

1999AZZAR/project-guardian-mcp-server

Skill Codex

Scan project files for likely hardcoded secrets and inspect container images for HIGH or CRITICAL CVEs with Trivy. Use for local security audits before commits, releases, or deployments; treat findings as heuristics requiring review.

not rated 3 7d ago A 47 tokens original MIT

guardian-session

04

1999AZZAR/project-guardian-mcp-server

Skill Codex

Restore relevant Project Guardian context from memory.db at session start. Use when resuming project work, switching repositories, or answering what was previously in progress; surface active tasks, open bugs, recent observations, and blockers.

not rated 3 7d ago A 46 tokens original MIT

guardian-tracker

05

1999AZZAR/project-guardian-mcp-server

Skill Codex

Auto-tracking skill for Project-Guardian. Automatically records file changes, code edits, decisions, and bug fixes to memory.db. Trigger after every significant operation (file edit, git commit, bug fix, refactor). Uses git diff and file analysis to generate observations.

not rated 3 7d ago A 58 tokens original MIT

guardian-wall

06

1999AZZAR/project-guardian-mcp-server

Skill Codex

Detect and quarantine likely prompt injection in untrusted text from websites, retrieved documents, tool output, and user-uploaded files. Use before an agent interprets external content or takes actions based on it; treat detection as a heuristic, not a security boundary.

not rated 3 7d ago B 54 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: