prism-mcp — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

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 dcostenco · MCP Server · ★ 131

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is prism-mcp safe to install? View the security audit →

About prism-mcp

Prism Coder Persistent memory and reliable tool-routing for AI agents. (formerly Prism MCP) Prism Coder is a Model Context Protocol server that gives Claude, Cursor, and other AI tools long-term memory that survives across sessions — semantic search, cognitive routing, and a visual dashboard. It ships alongside the open-weight model fleet (1.7B-32B) for fast, offline tool-routing when you don't want a cloud round-trip. It runs fully local and free on SQLite + Ollama with no API keys. A paid subscription adds cloud sync, higher model tiers, and team features through the Synalux portal. Renamed in v14: the project is now Prism Coder to cover both the memory server and the model fleet. The npm package stays , so existing install URLs and entries kee

agent-memoryai-agentanti-sycophancycognitive-architecturehebbian-learninghipaalocal-firstlocal-llmmcpmcp-server

Quick Facts

Stars131
Forks22
LanguageTypeScript
CategoryMCP Server
Quality Score66.0808122910945/100
Open Issues11
Last Updated2026-04-28
Created2026-02-12
Platformsmcp, node
Est. Tokens~14213k

prism-mcp alternative? Top 6 similar tools

Looking for a prism-mcp alternative? If you're comparing prism-mcp 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.

  • Ori-Mnemos by aayoawoyemi · ⭐ 328

    Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.

  • Zikkaron by amanhij · ⭐ 62

    Biologically-inspired persistent memory engine for Claude Code. 26 cognitive subsystems, Hopfield networks, pr

  • mcp-local-rag by shinpr · ⭐ 405

    Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP o

  • omega-memory by omega-memory · ⭐ 219

    Persistent memory for AI coding agents

  • PolyMCP by poly-mcp · ⭐ 170

    Polymcp provides a simple and efficient way to interact with MCP servers using custom agents

  • vestige by samvallad33 · ⭐ 645

    The memory + security kernel for AI agents. Strata: a signed append-only log, receipts on every write, exact-h

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is prism-mcp?

prism-mcp is The Mind Palace for AI Agents - HIPAA-hardened Cognitive Architecture with on-device LLM (prism-coder:7b), Hebbian learning, ACT-R spreading activation, adversarial evaluation, persistent memory, mult. It is categorized as a MCP Server with 131 GitHub stars.

What programming language is prism-mcp written in?

prism-mcp is primarily written in TypeScript. It covers topics such as agent-memory, ai-agent, anti-sycophancy.

How do I install or use prism-mcp?

You can find installation instructions and usage details in the prism-mcp GitHub repository at github.com/dcostenco/prism-mcp. The project has 131 stars and 22 forks, indicating an active community.

What are the best alternatives to prism-mcp?

The top alternatives to prism-mcp on Agent Skills Hub include Ori-Mnemos, Zikkaron, mcp-local-rag. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools