Related Servers

No user-submitted related servers found.

Related Servers

• genpark-agent-prompt-injection

  alphaparkinc

  F

  license

  -Not graded

  quality

  B

  maintenance

  Enables autonomous agents and MCP-compatible clients to route inputs through a deterministic firewall that flags and sanitizes prompt injection, jailbreaks, system prompt exfiltration, and tool hijacking. It supports JSON-RPC stdio integration for tools like Claude Desktop, Cursor, and multi-agent frameworks.

  Updated a month ago (2026-09-28 10:54 UTC)

  7

  -

• gamai-trust

  gamai-io

  A

  license

  B

  quality

  A

  maintenance

  Enables agents to verify claims against tamper-evident evidence, check inputs for prompt injection, and record blocked attacks as reusable antibodies. It also exposes trust statistics and a self-contained demo over stdio, so refusal and unverified outcomes are surfaced as first-class results.

  Updated a day ago (2026-11-04 12:07 UTC)

  5

  1

  MIT
• 

  aperion-shieldofficial

  AperionAI

  F

  license

  A

  quality

  A

  maintenance

  Local guardrail proxy for AI coding agents. Wraps any MCP server (stdio or HTTP/SSE) and blocks destructive tool calls before they execute, with TOFU catalog pinning against rug pulls and tool-poisoning/result-injection scanning. Single Rust binary, Apache-2.0.

  Updated a month ago (2026-10-04 01:57 UTC)

  14

  13

  -

• agent immune

  denial-web

  A

  license

  -Not graded

  quality

  C

  maintenance

  Adaptive security for AI agents: assess inputs for prompt injection, scan outputs for credential/PII leaks, teach new attack patterns to semantic memory, harden prompts, and monitor metrics. Runs locally via MCP stdio.

  Updated 3 months ago (2026-07-24 08:09 UTC)

  41 PyPI

  Apache 2.0

• genpark-agent-prompt-injection

  Alpha-Park

  A

  license

  -Not graded

  quality

  B

  maintenance

  Lets MCP-compatible assistants vet inbound prompts and untrusted text for instruction-override manipulation, separator escapes, and concealed encodings before processing them. Additional inline controls cover spending limits, repetitive-plan interruption, unsafe host-action denial, and output sanitization without third-party libraries.

  Updated a month ago (2026-09-28 03:02 UTC)

  7

  MIT
• 

  zn-gateofficial

  usezn

  A

  license

  A

  quality

  A

  maintenance

  Local security layer for coding agents: keeps secret values out of what Claude Code, Codex CLI, Cursor and OpenCode send to their model, and checks untrusted text for prompt injection. MIT, runs on your machine, no account.

  Updated 2 days ago (2026-11-03 18:05 UTC)

  4

  4

  MIT