verify-mcp-allowlist
v0.4.0Gate MCP server configuration as protected content. A shell write to .mcp.json is refused unless every mcpServers entry on the line, parsed as JSON, matches a name+source pair on the allowlist -- an unlisted name blocks, and an allowed name whose command/args/url changed blocks too. `claude mcp add|add-json` is checked the same way (add-from-claude-desktop cannot be verified and is refused). The allowlist ships inside this guard's own script, protected like every policy's implementations/ source -- edit only with 'chock: approved-config-change'. The shell guard reads Claude Code's .mcp.json, best-effort (PreToolUse fails open on a crash; a write with no visible content fails closed). A script gate at commit and tool use parses every written MCP config (.mcp.json, .cursor/mcp.json, .vscode/mcp.json, claude_desktop_config.json, .gemini/settings.json, .codex/config.toml) against the same allowlist; only servers the change adds or alters are refused, at commit and tool use. No pragma. [Session-enforced in Codex by a PreToolUse hook: a matched command is denied before it runs (witnessed blocking on Codex Desktop, Windows, 2026-08-24; the deny is returned as hook JSON, not an exit code, which Codex's Windows shell wrapper mangles). Codex requires a one-time trust review per hook -- the plugin is ADVISORY until you approve its hook, and a plugin update voids that trust until re-approved. The hook needs git and a Python 3.11+ (python3, python or py) on PATH; with no working Python it exits 2 rather than allowing, and any other failure of the HOOK (missing git, a timeout, an unexpected exit) fails OPEN. A failure of the GUARD it runs is a DENY here, because Codex rejects the confirmation prompt the other clients get. Repo-wide enforcement at commit time and in CI still needs `chock sync`.]
By chock-coreLicense: Apache-2.00 GitHub starsUpdated 6 days ago
Directory evidence
- Runtimes
- Codex
- Parsed components
- 1 skill or MCP entry
- Source updated
- Sep 30, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install verify-mcp-allowlist for Codex
codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add verify-mcp-allowlist@agent-plugin-marketplacePaste and run these commands in a terminal with Codex. They add and refresh the PluginsMP catalog, then install this plugin.
Compatibility: the page URL and API slug “verify-mcp-allowlist-3” remain stable.
- Codex:
verify-mcp-allowlist-3@agent-plugin-marketplace→verify-mcp-allowlist@agent-plugin-marketplace
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/open-coder-ai/chock-codex-pluginsClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is codex/verify-mcp-allowlist/.
Plugin files
├── .codex-plugin/plugin.json└── skills/verify-mcp-allowlist/SKILL.md
Included Skills1
Gate MCP server configuration as protected content. A shell write to .mcp.json is refused unless every mcpServers entry on the line, parsed as JSON, matches a name+source pair on the allowlist -- an unlisted name blocks, and an allowed name whose command/args/url changed blocks too. `claude mcp add|add-json` is checked the same way (add-from-claude-desktop cannot be verified and is refused). The allowlist ships inside this guard's own script, protected like every policy's implementations/ source -- edit only with 'chock: approved-config-change'. The shell guard reads Claude Code's .mcp.json, best-effort (PreToolUse fails open on a crash; a write with no visible content fails closed). A script gate at commit and tool use parses every written MCP config (.mcp.json, .cursor/mcp.json, .vscode/mcp.json, claude_desktop_config.json, .gemini/settings.json, .codex/config.toml) against the same allowlist; only servers the change adds or alters are refused, at commit and tool use. No pragma.
Plugin manifests1
{
"name": "verify-mcp-allowlist",
"version": "0.4.0",
"description": "Gate MCP server configuration as protected content. A shell write to .mcp.json is refused unless every mcpServers entry on the line, parsed as JSON, matches a name+source pair on the allowlist -- an unlisted name blocks, and an allowed name whose command/args/url changed blocks too. `claude mcp add|add-json` is checked the same way (add-from-claude-desktop cannot be verified and is refused). The allowlist ships inside this guard's own script, protected like every policy's implementations/ source -- edit only with 'chock: approved-config-change'. The shell guard reads Claude Code's .mcp.json, best-effort (PreToolUse fails open on a crash; a write with no visible content fails closed). A script gate at commit and tool use parses every written MCP config (.mcp.json, .cursor/mcp.json, .vscode/mcp.json, claude_desktop_config.json, .gemini/settings.json, .codex/config.toml) against the same allowlist; only servers the change adds or alters are refused, at commit and tool use. No pragma. [Session-enforced in Codex by a PreToolUse hook: a matched command is denied before it runs (witnessed blocking on Codex Desktop, Windows, 2026-08-24; the deny is returned as hook JSON, not an exit code, which Codex's Windows shell wrapper mangles). Codex requires a one-time trust review per hook -- the plugin is ADVISORY until you approve its hook, and a plugin update voids that trust until re-approved. The hook needs git and a Python 3.11+ (python3, python or py) on PATH; with no working Python it exits 2 rather than allowing, and any other failure of the HOOK (missing git, a timeout, an unexpected exit) fails OPEN. A failure of the GUARD it runs is a DENY here, because Codex rejects the confirmation prompt the other clients get. Repo-wide enforcement at commit time and in CI still needs `chock sync`.]",
"author": {
"name": "chock-core"
},
"repository": "https://github.com/open-coder-ai/chock-catalog",
"license": "Apache-2.0",
"keywords": [
"chock",
"policy-as-code",
"rule",
"advise",
"{'control': 'asi04', 'coverage': 'partial', 'note': \"blocks an unverified mcp server entering .mcp.json from the shell -- the mechanizable slice of asi04's 'unverified mcp servers' framing; provenance and signature verification beyond allowlist membership stay with the advisory owasp-asi04-agentic-supply-chain policy\"}"
],
"interface": {
"displayName": "Verify MCP Allowlist",
"shortDescription": "Gate MCP server configuration as protected content.",
"composerIcon": "./assets/icon.svg"
},
"skills": "./skills",
"hooks": "./hooks/hooks.json"
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[verify-mcp-allowlist on Agent Plugins Marketplace](https://pluginsmp.com/plugins/verify-mcp-allowlist-3)