Agentguard

Q: How do I install Agentguard?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Q: Does Agentguard need an API key?

No required environment variable is listed on this record.

Q: What transport does Agentguard use?

Agentguard runs locally over stdio.

Q: When was Agentguard last checked?

Last checked 2026-10-28. Zero-trust security sidecar for AI agents - MIT, single Go binary, <5ms p99 overhead, protects Claude Code/Cursor/Codex/Gemini CLI/Windsurf

NikeGunn3stars

Zero-trust security sidecar for AI agents - MIT, single Go binary, <5ms p99 overhead, protects Claude Code/Cursor/Codex/Gemini CLI/Windsurf

Install Run on PlugMCP

GitHub Website

Run on PlugMCP

1# Agentguard

README.mdMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

Install from the publisher. Not a PlugMCP endpoint.

Run on PlugMCP

Host a copy with our keys and logs.

No packaged release in the registry yet. Follow the repository README.

RepositoryPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
License: MIT
Last checked: 2026-10-28

Stars: 3
Tools: —
Uptime: —

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install Agentguard?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Agentguard need an API key?

No required environment variable is listed on this record.

What transport does Agentguard use?

Agentguard runs locally over stdio.

When was Agentguard last checked?

Last checked 2026-10-28. Zero-trust security sidecar for AI agents - MIT, single Go binary, <5ms p99 overhead, protects Claude Code/Cursor/Codex/Gemini CLI/Windsurf

From the publisher

Documentation

AgentGuard

Zero-trust security sidecar for AI agents — Claude Code, Cursor, Codex, Gemini CLI, Windsurf, or anything that speaks MCP.

AgentGuard sits transparently between your AI agent and the tools it calls. Every JSON-RPC frame goes through a five-stage inspection pipeline that catches prompt injection, tool poisoning, rug pulls, runaway loops, and credential exfiltration before they reach your model — or your customers' data.

curl -fsSL https://agentguard.space/install | sh
agentguard init        # detects + patches every installed agent
agentguard dashboard   # opens http://127.0.0.1:7878

That's it. The next tool call your agent makes is now inspected.

See it

The local web dashboard — live tool-call feed, per-server trust scores, call-detail waterfall, command palette, dark/light:

dashboard

agentguard tail — live TUI feed of every call

tail

agentguard doctor — Homebrew-style health check

doctor

Want to regenerate or add the scan / install / agent-onboarding GIFs? See demo/README.md for the one-command render workflow.

Why

LLM agents trust their tools by default. A poisoned MCP server can rewrite its tool descriptions between sessions, embed prompt injections in responses, or quietly funnel your credentials to a webhook. Your IDE's approval prompt won't catch any of that — it just shows the human-readable intent. AgentGuard inspects the wire.

What you get

Single Go binary. No daemon, no Docker, no kernel modules.
Local-only. No account, no telemetry, no cloud. Your data stays on your machine.
<5 ms p99 overhead on the cheap inspection path (measured, enforced by CI gate).
Auto-detect + auto-wire for Claude Code, Cursor, Codex CLI, Gemini CLI, Windsurf. Backups are byte-identical; uninstall restores them exactly.
Live TUI (agentguard tail) and a polished web dashboard with SSE live updates and dark + light themes.
Replay historic traffic against new rule packs before rolling them out.
MIT licensed. Releases are cosign-signed via GitHub OIDC.

How it works

agent  ─▶  agentguard wrap  ─▶  MCP server
       ◀                    ◀
       │
       └─ five inspection stages:
          transport · schema · attestation · policy · scanner · ML
          plus a per-session circuit breaker

agentguard init rewrites every MCP entry in each agent's config so the agent spawns agentguard wrap -- <original command> instead of the upstream server directly. The agent doesn't notice. The server doesn't notice. The inspection happens in the middle.

Full architecture → Threat model →

Commands

Command	What
`agentguard init`	Detect agents, patch their configs.
`agentguard dashboard`	Local web UI at `127.0.0.1:7878`.
`agentguard tail`	Live TUI of tool calls.
`agentguard scan <cmd>`	Fire the attack corpus at an MCP server.
`agentguard doctor`	Homebrew-style health check.
`agentguard replay`	Re-run the pipeline against historic traffic.
`agentguard pack list/show/verify`	Manage rule packs.
`agentguard uninstall`	Restore every config byte-for-byte.

Status

Feature-complete for v1 launch (M5 done). Polish + signing pipeline landed in M6. See CHANGELOG.md for the full milestone log.

Contributing

Issues and PRs welcome. We're particularly interested in:

New rule packs for popular MCP servers
More agent detectors (Aider, Cline, Continue, etc.)
Additional prompt-injection corpora

See CONTRIBUTING.md.

License

MIT. See LICENSE.

Agentguard

NikeGunn3stars

Zero-trust security sidecar for AI agents - MIT, single Go binary, <5ms p99 overhead, protects Claude Code/Cursor/Codex/Gemini CLI/Windsurf

Install Run on PlugMCP

GitHub Website

Run on PlugMCP

1# Agentguard

README.mdMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

Install from the publisher. Not a PlugMCP endpoint.

Run on PlugMCP

Host a copy with our keys and logs.

No packaged release in the registry yet. Follow the repository README.

RepositoryPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
License: MIT
Last checked: 2026-10-28

Stars: 3
Tools: —
Uptime: —

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install Agentguard?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Agentguard need an API key?

No required environment variable is listed on this record.

What transport does Agentguard use?

Agentguard runs locally over stdio.

When was Agentguard last checked?

Last checked 2026-10-28. Zero-trust security sidecar for AI agents - MIT, single Go binary, <5ms p99 overhead, protects Claude Code/Cursor/Codex/Gemini CLI/Windsurf

From the publisher

Documentation

AgentGuard

Zero-trust security sidecar for AI agents — Claude Code, Cursor, Codex, Gemini CLI, Windsurf, or anything that speaks MCP.

curl -fsSL https://agentguard.space/install | sh
agentguard init        # detects + patches every installed agent
agentguard dashboard   # opens http://127.0.0.1:7878

That's it. The next tool call your agent makes is now inspected.

See it

The local web dashboard — live tool-call feed, per-server trust scores, call-detail waterfall, command palette, dark/light:

dashboard

agentguard tail — live TUI feed of every call

tail

agentguard doctor — Homebrew-style health check

doctor

Want to regenerate or add the scan / install / agent-onboarding GIFs? See demo/README.md for the one-command render workflow.

Why

What you get

Single Go binary. No daemon, no Docker, no kernel modules.
Local-only. No account, no telemetry, no cloud. Your data stays on your machine.
<5 ms p99 overhead on the cheap inspection path (measured, enforced by CI gate).
Auto-detect + auto-wire for Claude Code, Cursor, Codex CLI, Gemini CLI, Windsurf. Backups are byte-identical; uninstall restores them exactly.
Live TUI (agentguard tail) and a polished web dashboard with SSE live updates and dark + light themes.
Replay historic traffic against new rule packs before rolling them out.
MIT licensed. Releases are cosign-signed via GitHub OIDC.

How it works

agent  ─▶  agentguard wrap  ─▶  MCP server
       ◀                    ◀
       │
       └─ five inspection stages:
          transport · schema · attestation · policy · scanner · ML
          plus a per-session circuit breaker

Full architecture → Threat model →

Commands

Command	What
`agentguard init`	Detect agents, patch their configs.
`agentguard dashboard`	Local web UI at `127.0.0.1:7878`.
`agentguard tail`	Live TUI of tool calls.
`agentguard scan <cmd>`	Fire the attack corpus at an MCP server.
`agentguard doctor`	Homebrew-style health check.
`agentguard replay`	Re-run the pipeline against historic traffic.
`agentguard pack list/show/verify`	Manage rule packs.
`agentguard uninstall`	Restore every config byte-for-byte.

Status

Feature-complete for v1 launch (M5 done). Polish + signing pipeline landed in M6. See CHANGELOG.md for the full milestone log.

Contributing

Issues and PRs welcome. We're particularly interested in:

New rule packs for popular MCP servers
More agent detectors (Aider, Cline, Continue, etc.)
Additional prompt-injection corpora

See CONTRIBUTING.md.

License

MIT. See LICENSE.

Add this server

Host a copy with our keys and logs.

Server facts

Tools

Questions

How do I install Agentguard?

Does Agentguard need an API key?

What transport does Agentguard use?

When was Agentguard last checked?

Documentation

AgentGuard

See it

Why

What you get

How it works

Commands

Status

Contributing

License

Sponsors

Add this server

Host a copy with our keys and logs.

Server facts

Tools

Questions

How do I install Agentguard?

Does Agentguard need an API key?

What transport does Agentguard use?

When was Agentguard last checked?

Documentation

AgentGuard

See it

Why

What you get

How it works

Commands

Status

Contributing

License

Sponsors