ZBS Index What actually exists in applied AI, with the source next to it

mcp server

io.github.denial-web/agent-immune

AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening

Description as published by the maintainer. Source

  • version 0.2.2
  • active
  • memory and context
  • security

active — Most recent push to the repository was 2026-07-24. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
GitHub stars 0 Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. cumulative, all time GitHub
Last commit 2026-07-24 Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. point in time GitHub
Open issues 1 Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. as of fetch GitHub
Latest published version 0.2.2 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-04-07 When the registry record was last updated by its maintainer. point in time Model Context Protocol
License Apache-2.0 Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. as of fetch GitHub
First listed in the MCP Registry 2026-04-07 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
repository status active The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. as of fetch GitHub

Where to get it

Related, by what their authors tagged them

  • io.github.daedalus/mcp-external-memory — last commit 2026-04-21, shares semantic-memory
    An MCP server that gives LLMs persistent, searchable semantic memory
  • ai.marchward/mcp-server — last commit 2026-07-01, shares agent-governance, langchain
    Runtime authority for AI agents: credential mediation, spend cap, approval gates, audit log.
  • PromptSpeak Governance — last commit 2026-07-05, shares agent-governance
    Pre-execution governance for AI agents. Validates tool calls before they execute.
  • Aegis — AI Agent Governance — last commit 2026-05-05, shares ai-security, langchain, llm-security
    Policy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.
  • dev.safeprompt/mcp — last commit 2026-08-03, shares ai-security, llm-security, prompt-injection
    Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.
  • Bawbel Scanner — last commit 2026-07-05, shares ai-security, llm-security, prompt-injection
    Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.
  • Bawbel Scanner — last commit 2026-07-05, shares ai-security, llm-security, prompt-injection
    Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.
  • io.github.dl-eigenart/agentshield-mcp — last commit 2026-05-11, shares ai-security, llm-security, prompt-injection
    Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents.
  • Actenon Kernel — last commit 2026-07-26, shares langchain, llm-security
    Verify consequential AI actions before they execute.
  • ai.kernora/agent-sec — last commit 2026-07-31, shares ai-security, llm-security
    Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP.

These share tags the maintainers applied themselves, such as semantic-memory, agent-governance, langchain, ai-security. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

How the author describes it

Topics the maintainer set on GitHub: agent-governance, ai-agent, ai-security, langchain, llm-security, mcp, mcp-server, prompt-injection, semantic-memory, tool-security.

Bring your own setup

We take apart real AI setups every week and show what broke, what cost too much, and what the trace actually said. If you run agents on real work, that is where the useful conversation is.

Join ZBS AI Practice Lab

Sources

  1. denial-web/agent-immune on GitHub — GitHub, observed , trust tier 3.
  2. Official MCP Registry — Model Context Protocol, observed , trust tier 1.