A

AgentPlaybooks

ai.agentplaybooks/agentplaybooks · v0.9.1 · MCP server

by ai.agentplaybooksScan grade: GoodOfficial MCP registry · source scanned

Vendor-neutral home for portable agents: skills, MCP tools, memory, canvas, and secret proxy.

InstallSourceClaim this MCP server
Follow0
Trust ScoreNot ratedSecurity scan82Components1
Protect this install with HOL Guard

Guard checks the skills and MCP servers a plugin adds on your machine and asks you before a risky action runs. The scores above are free, and no plan changes them.

Is AgentPlaybooks a fit?

From the plugin's manifest and HOL's scan. Anything the plugin does not declare is shown as not declared.

Works with

  • MCP
  • 1 MCP server

Before you install

Sign-in
Not declared
Declared access
Not declared
License
Not declared

Check before relying on it

  • Some security checks did not finish: Cisco skill scan. See the evidence
  • 79 high or critical findings from the scan. See the evidence
  • The publisher has not verified ownership on HOL.
  • No license declared in the manifest.

What is AgentPlaybooks?

AgentPlaybooks is a published mcp server plugin for AI coding agents in the MCP ecosystem, developed by ai.agentplaybooks and distributed through the HOL AI plugin registry. Vendor-neutral home for portable agents: skills, MCP tools, memory, canvas, and secret proxy.

Canonical slug
ai.agentplaybooks/agentplaybooks
Version
v0.9.1 · updated Oct 29, 2026

Registry snapshot

Owner verification
Not verified
Scanner
HOL plugin scanner
Security result
Needs review
Digest verified
No

Trust and security

Provenance

Plugin root
.
Source repo
https://github.com/matebenyovszky/agentplaybooks
Source commit
3a950621f28c…
Publisher verified
No
Owner verified
Not owner verified

Security posture

See how the Trust Score is computed
Needs review
Security result
82
Security score
79
High findings
Provider
codex-plugin-scanner
Grade
B · Good
Version
3.24.2
codex:hol-plugin-scanner-bWMhU1 / agentplaybooks / cisco-skill-scanner: failedcodex:hol-plugin-scanner-bWMhU1 / agentplaybooks / cisco-mcp-scanner: skipped

[claude:.] Claude Plugin

22/22

5 checks

[claude:.] Security

9/16

6 checks

[claude:.] Operational Security

15/20

5 checks

[claude:.] Code Quality

10/10

2 checks

[claude:packages/cli] Claude Plugin

18/18

5 checks

[claude:packages/cli] Security

6/16

6 checks

[claude:packages/cli] Operational Security

3/6

5 checks

[claude:packages/cli] Code Quality

10/10

2 checks

[claude:plugins/agentplaybooks] Claude Plugin

18/18

5 checks

[claude:plugins/agentplaybooks] Security

13/16

6 checks

[claude:plugins/agentplaybooks] Operational Security

N/A

5 checks · not applicable

[claude:plugins/agentplaybooks] Code Quality

10/10

2 checks

[codex:.] Repository Marketplace

15/15

3 checks

[codex:.] Repository Operational Security

15/20

5 checks

[codex:.] agentplaybooks · Manifest Validation

28/31

9 checks

[codex:.] agentplaybooks · Security

6/16

9 checks

[codex:.] agentplaybooks · Best Practices

12/15

5 checks

[codex:.] agentplaybooks · Skill Security

5/5

4 checks

[codex:.] agentplaybooks · Code Quality

10/10

2 checks

Findings

highsecurityHARDCODED_SECRET

Potential secret material was detected in .github/workflows/self-host-mtls.yml.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in packages/cli/test/adapters.test.js.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in packages/cli/test/adopt.test.js.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in packages/cli/test/audit.test.js.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in packages/cli/test/auth-command.test.js.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in packages/cli/test/connection.test.js.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in packages/cli/test/hermes-bundle.test.js.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in packages/cli/test/hermes-memory.test.js.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in packages/cli/test/hermes-setup.test.js.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in packages/cli/test/instructions.test.js.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in packages/cli/test/line-endings.test.js.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in packages/cli/test/mcp-round-trip.test.js.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in packages/cli/test/mcp-stdio.test.js.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in packages/cli/test/remote.test.js.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in packages/cli/test/secrets.test.js.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in packages/cli/test/skill-files.test.js.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in packages/cli/test/sync.test.js.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in packages/python-secrets/tests/test_client.py.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in public/blog/clawdbot-mcp-deep-integration.hu.md.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in public/docs/platform-integrations.md.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in scripts/self-host/restore-drill.sh.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in src/app/api/_shared/federation-secrets.test.ts.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in src/app/api/_shared/federation-secrets.ts.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in src/components/playbook/SecretManager.tsx.

Remove the secret from source control and load it securely at runtime.

highsecurityHARDCODED_SECRET

Potential secret material was detected in src/lib/connection-catalogue.ts.

Remove the secret from source control and load it securely at runtime.

Install guidance

Install in MCP

Connect the bundled MCP server shipped in the repository .mcp.json file.

MCP docs
  1. 1

    Clone the repository

    shell
  2. 2

    Register the server in your MCP client

    Claude Code reads a project .mcp.json file and asks you to approve its servers when you open the folder. Other clients keep their own MCP configuration, so copy the server entry from .mcp.json into that client. If this repository configures its server differently, follow the MCP setup the publisher documents.

  3. 3

    Verify the server

    Check the MCP server list in your client. The server declared in .mcp.json should report as connected. In Claude Code, run /mcp to see it.

Did setup work in MCP?

No setup reports for MCP yet. Self-reported by signed-in visitors. Copying a command is not counted, and most installs are never reported.

Attested installs: Fewer than 10 attested installs of this plugin in week 2026-W43, so no number is shown. Counted from opt-in HOL Guard install reports, once per machine and runtime, and never mixed with the answers above. How install reports work.

Loading reviews

Plugin manifest

{
  "source": "official-mcp-registry",
  "evidenceState": "scanned_source",
  "registryName": "ai.agentplaybooks/agentplaybooks",
  "publishedAt": "2026-10-29T11:41:31.731745Z",
  "packages": [],
  "remotes": [
    {
      "type": "streamable-http",
      "url": "https://agentplaybooks.ai/api/mcp/manage"
    }
  ],
  "sourceScannedAt": "2026-10-30T01:08:09.694Z",
  "sourceScanCommit": "3a950621f28c3b4fe1e7bafc3c5352fe09559d7f"
}

File inventory

File inventory is unavailable for this plugin right now.

AgentPlaybooks — Frequently asked questions

What is AgentPlaybooks?
AgentPlaybooks is an AI plugin in the HOL registry. Vendor-neutral home for portable agents: skills, MCP tools, memory, canvas, and secret proxy.
How do I install AgentPlaybooks?
Install AgentPlaybooks in your harness: MCP — git clone https://github.com/matebenyovszky/agentplaybooks. Full step-by-step guidance is on the HOL plugin page.
How do I install AgentPlaybooks in MCP?
To install AgentPlaybooks in MCP, start with git clone https://github.com/matebenyovszky/agentplaybooks. The complete step-by-step install guide for MCP is on the HOL plugin page.
Who publishes AgentPlaybooks?
AgentPlaybooks is published by ai.agentplaybooks and listed on HOL.

Directory acceptance

Listed in 0 of 5 directory lists

Read from the list each directory publishes on GitHub. Being listed means the directory accepted the plugin; it is not a HOL security rating.

Lists last read . HOL re-reads them every day.

Submitting it? Check it against each directory's rules

Install signal

HOL cannot see every install. These are separate signals from different sources, so they are not added together. Counts under each floor show as <N.

Install commands issued here
<5
HOL Guard install commands issued from this listing, last 28 days.
Opt-in install reports
<10
Machines that reported installing it through HOL Guard in week 2026-W43. Reporting is opt-in, so most installs are not counted.
HOL Guard workspaces
<5
Workspaces that approved it or include it in an approved-plugin feed, as of today.

Related plugins

Ordered by Trust Score. Listings cannot pay for these positions. Check each one fits your task before switching from AgentPlaybooks.

Alternatives in MCP server

See all MCP server plugins