Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add AIWerk/openclaw-mcp-bridge --skill manage-mcp-serversgit clone --depth 1 https://github.com/AIWerk/openclaw-mcp-bridgeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aiwerk/openclaw-mcp-bridge/manage-mcp-servers)<a href="https://agentmods.dev/skills/aiwerk/openclaw-mcp-bridge/manage-mcp-servers"><img src="https://agentmods.dev/badge/skills/aiwerk/openclaw-mcp-bridge/manage-mcp-servers/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aiwerk/openclaw-mcp-bridge/manage-mcp-servers"><img src="https://agentmods.dev/badge/skills/aiwerk/openclaw-mcp-bridge/manage-mcp-servers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.01222 |
| Opus 5 | $0.00025 | $0.00611 |
| Sonnet 5 | $0.00010 | $0.00244 |
| Haiku 4.5 | $0.00005 | $0.00122 |
Grade A, and why
manage-mcp-servers scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Blocked: `curl|bash`, `curl|sh`, `wget|bash`, `sudo`, piped remote execution How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
manage-mcp-servers
Use this skill for any MCP server management task: install, remove, list, status, troubleshoot.
Trigger Conditions
Activate when requests mention:
- adding/installing a new MCP server
- removing/uninstalling an MCP server
- listing available or installed servers
- checking MCP server status or health
- troubleshooting MCP connection errors
- "what MCP servers do I have?"
Key Paths
PLUGIN_DIR=~/.openclaw/extensions/openclaw-mcp-bridge
SCRIPT=$PLUGIN_DIR/scripts/install-server.sh
SERVERS=$PLUGIN_DIR/servers/
CONFIG=~/.openclaw/openclaw.json
ENV=~/.openclaw/.env
Actions
List available servers (catalog)
ls $PLUGIN_DIR/servers/
Or use the MCP tool:
mcp(action="status")
List installed servers
mcp(action="status")
Shows connected servers with tool counts.
Install a server
If in catalog:
bash $PLUGIN_DIR/scripts/install-server.sh <name>
This handles: backup, config update, env var prompts, gateway restart.
If NOT in catalog: Follow the "Add new server" flow below.
Remove a server
bash $PLUGIN_DIR/scripts/install-server.sh <name> --remove
This handles:
- Backup of openclaw.json
- Remove server entry from config
- Remove env var from .env (if applicable)
- Prompt for gateway restart
Check server health
mcp(server="<name>", action="list")
If this returns tools, the server is healthy. If it fails:
- Check if the server process is running
- Check env vars are set in ~/.openclaw/.env
- Check gateway logs:
journalctl --user -u openclaw-gateway.service -n 50
Add New Server Flow (not in catalog)
1. Verify source
Confirm target: GitHub URL, npm package, PyPI package, Docker image, or remote endpoint.
2. Build config from docs
- Read README; extract: name, description, transport, command/url, args, env, auth.
- Transport heuristics:
npx/node/python/docker run -i->stdio- URL + SSE ->
sse - Single HTTP endpoint ->
streamable-http
- If unsure about transport/command/args: ask, don't guess.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 172 lines · 50 tokens per session scan A 534c15ab925c
manage-mcp-servers is a skill published in the GitHub repository AIWerk/openclaw-mcp-bridge (11 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 1,222 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
skillsync-mcp
Search, scan, install, and manage Claude Code skills with built-in security scanning. Every installation is gated behind a 60+ pattern threat scan.
openclaw-mcp-bridge
You have access to external tools via MCP (Model Context Protocol) servers.
osint-recon
A knowledge guide for open-source intelligence, or OSINT: collecting information from publicly available sources. It covers servers, websites, domains, and, when appropriate, people.
crypto-toolkit
A toolkit for encoding, decoding, hashing, and encrypting data in formats such as Base64, hexadecimal, URLs, JWTs, AES, RSA, and common ciphers.
secknowledge-skill
A knowledge base for testing the security of websites, software, and AI systems, including agents and language models.
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.