MCP OpenClaw Extensions

Name: MCP OpenClaw Extensions
Author: romainsantoli-web

by romainsantoli-webversion 3.3.0i★ –iRuns on your computer

Registry nameio.github.romainsantoli-web/mcp-openclaw

Install

Overview

Description from the maker (original English)

138-tool MCP server for AI agent firms: security, A2A, Hebbian memory, fleet mgmt

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

User voiceiNo reviews yetReviews open together with accounts in a later step
Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
UsageiVery new↓ 28/wk · ★ –

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

Connection: Runs on your computer
Transport: stdio
Category: Cybersecurity

Install

Pick the AI app you use, then copy the settings.

Before you install

Basic checks: 1 of 1 passed
Runs on your computer with your user’s permissions (files, network, apps).
The registry lists no key to fill in.

You need

PyPIPython’s uv installed (for the uvx command)

Which app do you use?

ClaudeClaude CodeCursorVS CodeChatGPT

Pick your app above. We remember it, so next time the button says “Install in …”.

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "openclaw": {
      "command": "uvx",
      "args": [
        "mcp-openclaw-extensions"
      ]
    }
  }
}

Run this in your terminal

claude mcp add openclaw -- uvx mcp-openclaw-extensions

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "openclaw": {
      "command": "uvx",
      "args": [
        "mcp-openclaw-extensions"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "openclaw": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-openclaw-extensions"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026

✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account romainsantoli-web, which owns the repo
… Not checked yet
Still maintained
We have not read this repo from GitHub yet
… Not checked yet
Has a licence
We have not read this repo from GitHub yet
– Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
– Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
… Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Cybersecurityi

More stars than 0% of the other 1004 servers in this category
Published to the registry more recently than 6% of the other 1004 servers in this category
Basic checks equal to or better than 100% of the other 1004 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is MCP OpenClaw Extensions safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (3.3.0) reached the registry 8 months ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.

What can I use instead?

In the same category: VMware NSX Security, Unicode Security MCP, Osv MCP

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

VMware NSX Security

VMware NSX security: DFW policies and exclusions, groups, tags, Traceflow, IDPS — 22 MCP tools.

by vmware-skillsVery new↓ 204/wkUpdated today

Runs on your computer

Install

Unicode Security MCP

Local checks for Unicode confusables, mixed scripts, invisible controls, and suspicious identifiers.

by mrfentmenVery new↓ 50/wkUpdated today

Runs on your computer

Install

Osv MCP

MCP server for OSV open source vulnerability data and package security checks.

by mrfentmenVery new↓ 64/wkUpdated today

Runs on your computer

Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

firm-mcp-server

Python MCP server (port 8012) that bridges VS Code Copilot agents to the

[Firm](https://github.com/the server) Gateway ecosystem.

Companion to setup-vs-agent-firm.

Tools (138)

Module	Tool	Description	Gaps
vs_bridge	`vs_context_push`	Push VS Code context → Firm session	—
vs_bridge	`vs_context_pull`	Pull Firm session state → VS Code	—
vs_bridge	`vs_session_link`	Associate workspace path ↔ session ID	—
vs_bridge	`vs_session_status`	Bridge health check	—
gateway_fleet	`firm_gateway_fleet_status`	Parallel health-check all instances	—
gateway_fleet	`firm_gateway_fleet_add`	Register a Gateway instance	—
gateway_fleet	`firm_gateway_fleet_remove`	Remove a Gateway instance	—
gateway_fleet	`firm_gateway_fleet_broadcast`	Broadcast to all instances	—
gateway_fleet	`firm_gateway_fleet_sync`	Sync config+skills to all instances	—
gateway_fleet	`firm_gateway_fleet_list`	List instances	—
delivery_export	`firm_export_github_pr`	Create draft PR on GitHub	—
delivery_export	`firm_export_jira_ticket`	Create Jira ticket (ADF)	—
delivery_export	`firm_export_linear_issue`	Create Linear issue (GraphQL)	—
delivery_export	`firm_export_slack_digest`	Post Slack digest (Block Kit)	—
delivery_export	`firm_export_document`	Write local Markdown deliverable	—
delivery_export	`firm_export_auto`	Auto-route by `delivery_format`	—
security_audit	`firm_security_scan`	Scan files for SQL injection + XSS patterns	C1
security_audit	`firm_sandbox_audit`	Detect `sandbox.mode: off` → CRITICAL	C2
security_audit	`firm_session_config_check`	Detect ephemeral SESSION_SECRET in .env/compose	C3
security_audit	`firm_rate_limit_check`	Detect Funnel without rate limiter → CRITICAL	H8
acp_bridge	`acp_session_persist`	Persist ACP session to `~/.firm/acp_sessions.json`	C4
acp_bridge	`acp_session_restore`	Restore persisted ACP session by run_id	C4
acp_bridge	`acp_session_list_active`	List ACP sessions active in last N hours	C4
acp_bridge	`fleet_session_inject_env`	Inject env vars to spawned sessions (allowlist)	H3
acp_bridge	`fleet_cron_schedule`	Schedule cron with sandbox enforcement	H4
acp_bridge	`firm_workspace_lock`	Advisory file lock with owner tracking (`fcntl`)	H5
acp_bridge	`firm_acpx_version_check`	ACPX plugin version pin (≥0.1.15) + streaming mode check	3.1
reliability_probe	`firm_gateway_probe`	WS probe with backoff — detects close 1006, returns `launchctl`	H6/H7
reliability_probe	`firm_doc_sync_check`	Detect version drift in docs vs package.json	M5
reliability_probe	`firm_channel_audit`	Detect zombie channel SDK deps (LINE, Baileys…)	M1
reliability_probe	`firm_adr_generate`	Generate MADR + commit path for architecture decisions	M6
gateway_hardening	`firm_gateway_auth_check`	Verify Gateway auth config — CRITICAL if Funnel without password	H2
gateway_hardening	`firm_credentials_check`	Check Baileys/channel credential integrity and freshness	M3
gateway_hardening	`firm_webhook_sig_check`	Verify HMAC signing secrets for all inbound webhook channels	M4
gateway_hardening	`firm_log_config_check`	Detect debug/trace logging and missing redactPatterns	M7
gateway_hardening	`firm_workspace_integrity_check`	Validate ~/.firm/workspace (AGENTS.md, SOUL.md, staleness)	M8
runtime_audit	`firm_node_version_check`	Verify Node.js ≥ 22.12.0 (CVE-2025-59466, CVE-2026-21636)	C5
runtime_audit	`firm_secrets_workflow_check`	Detect hardcoded secrets in config.json (migrate to `firm secrets`)	C6
runtime_audit	`firm_http_headers_check`	Verify HTTP security headers (HSTS, X-Content-Type-Options, Referrer-Policy)	H9
runtime_audit	`firm_nodes_commands_check`	Detect dangerous gateway.nodes.allowCommands override	H10
runtime_audit	`firm_trusted_proxy_check`	Verify trusted-proxy config coherence (bind + trustedProxies + auth mode)	H11
runtime_audit	`firm_session_disk_budget_check`	Verify session.maintenance.maxDiskBytes / highWaterBytes configured	M15
runtime_audit	`firm_dm_allowlist_check`	Detect dmPolicy=allowlist with empty allowFrom (fail-closed) across 9 channels	M16
advanced_security	`firm_secrets_lifecycle_check`	Verify External Secrets lifecycle (audit/configure/apply/reload)	C7
advanced_security	`firm_channel_auth_canon_check`	Verify channel auth path canonicalization (encoded traversal)	C8
advanced_security	`firm_exec_approval_freeze_check`	Verify exec approval plan immutability (symlink cwd rebind)	C9
advanced_security	`firm_hook_session_routing_check`	Verify hook session-key routing hardening	H12
advanced_security	`firm_config_include_check`	Verify $include hardlink escape + file-size guardrails	H13
advanced_security	`firm_config_prototype_check`	Detect prototype pollution (proto, constructor, prototype) in config	H14
advanced_security	`firm_safe_bins_profile_check`	Verify safeBins entries have explicit profiles	H15
advanced_security	`firm_group_policy_default_check`	Verify group policy default is fail-closed (allowlist)	H16
config_migration	`firm_shell_env_check`	Verify shell env sanitization (LD_PRELOAD, DYLD_*, ZDOTDIR)	H17
config_migration	`firm_plugin_integrity_check`	Verify plugin install integrity/pin + drift detection	H18
config_migration	`firm_token_separation_check`	Verify hooks.token ≠ gateway.auth.token	H19
config_migration	`firm_otel_redaction_check`	Verify OTEL secret redaction in diagnostics export	M17
config_migration	`firm_rpc_rate_limit_check`	Verify control-plane RPC rate limiting config	M21
observability	`firm_observability_pipeline`	Ingest JSONL traces into SQLite for offline analysis	T1
observability	`firm_ci_pipeline_check`	Validate CI workflow completeness (lint, test, secrets)	T6
memory_audit	`firm_pgvector_memory_check`	Verify pgvector config (HNSW index, dimensions, distance metrics)	T3
memory_audit	`firm_knowledge_graph_check`	Audit knowledge graph integrity (orphan nodes, cycles, TTL)	T9

| compliance_me

Only the beginning is shown; read the rest in the repo

MCP OpenClaw Extensions

Overview

PopNx MCP’s three pillars

What you can do with it

Install

Before you install

What it can do

Basic checksi

Maker matches the repo

Still maintained

Has a licence

Endpoint responds

Sign-in with OAuth

No hidden instructions in tool descriptions

Compared with others in Cybersecurityi

Common questions

Alternatives

VMware NSX Security

Unicode Security MCP

Osv MCP

README from the maker

firm-mcp-server

Tools (138)