{"id":"13f9b091-f9c4-48c5-a6b0-7f37c939a8a5","shortId":"YpHBJu","kind":"skill","title":"Govern agent skills, MCP servers, prompts, and tool calls with DefenseClaw","tagline":"Use DefenseClaw as an operator-controlled admission, runtime guardrail, sandbox, and audit layer before untrusted agent capabilities run.","description":"# Govern agent skills, MCP servers, prompts, and tool calls with DefenseClaw\n\nUse DefenseClaw as an operator-controlled admission, runtime guardrail, sandbox, and audit layer before untrusted agent capabilities run.\n\n## Prerequisites\n\nDefenseClaw CLI, Go gateway sidecar, policy rules, optional OpenClaw plugin, optional OTLP/Splunk/webhook sinks\n\n## Installation\n\nUse the upstream install or setup path that matches your environment:\n- make build\n- make test\n- make lint\n\nRequirements and caveats from upstream:\n- <a href=\"https://www.python.org/downloads/\"><img alt=\"Python 3.10+\" src=\"https://img.shields.io/badge/python-3.10%2B-blue.svg\" /></a>\n- DefenseClaw combines a Python operator CLI, a Go gateway sidecar, and an OpenClaw TypeScript plugin. Together they enforce a simple operating rule: untrusted agent capabilities are scanned, governed, logged, and block...\n- | [CLI Reference](docs/CLI.md) | Python CLI commands and operator workflows |\n\nBasic usage or getting-started notes:\n- | Skills, MCP servers, plugins, and generated code before they run | Prompts, completions, tool calls, and sandbox activity at runtime | SQLite audit history, JSONL, OTLP, Splunk, webhooks, and TUI views |\n- **Admission control** - scan skills, MCP servers, plugins, and code before they run.\n- | [Quick Start](docs/QUICKSTART.md) | First successful local setup and scan flow |\n\n- Source: https://github.com/cisco-ai-defense/defenseclaw\n- Extracted from upstream docs: https://raw.githubusercontent.com/cisco-ai-defense/defenseclaw/HEAD/README.md\n\n## Documentation\n\n- https://cisco-ai-defense.github.io/docs/defenseclaw\n\n## Source\n\n- [Agent Skill Exchange](https://agentskillexchange.com/skills/govern-agent-skills-mcp-servers-prompts-and-tool-calls-with-defenseclaw/)","tags":["govern","agent","skills","mcp","servers","prompts","and","tool","calls","with","defenseclaw","agentskillexchange"],"capabilities":["skill","source-agentskillexchange","skill-govern-agent-skills-mcp-servers-prompts-and-tool-calls-with-defenseclaw","topic-agent-skills","topic-ai-agents","topic-ai-tools","topic-awesome-list","topic-claude-code","topic-codex","topic-cursor","topic-llm","topic-mcp","topic-npx-skills","topic-openclaw","topic-skills-catalog"],"categories":["skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/agentskillexchange/skills/govern-agent-skills-mcp-servers-prompts-and-tool-calls-with-defenseclaw","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add agentskillexchange/skills","source_repo":"https://github.com/agentskillexchange/skills","install_from":"skills.sh"}},"qualityScore":"0.454","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 8 github stars · SKILL.md body (1,761 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T19:10:44.679Z","embedding":null,"createdAt":"2026-05-18T13:16:54.817Z","updatedAt":"2026-05-18T19:10:44.679Z","lastSeenAt":"2026-05-18T19:10:44.679Z","tsv":"'/cisco-ai-defense/defenseclaw':199 '/cisco-ai-defense/defenseclaw/head/readme.md':206 '/docs/defenseclaw':210 '/skills/govern-agent-skills-mcp-servers-prompts-and-tool-calls-with-defenseclaw/)':217 'activ':161 'admiss':19,49,174 'agent':2,28,32,58,121,212 'agentskillexchange.com':216 'agentskillexchange.com/skills/govern-agent-skills-mcp-servers-prompts-and-tool-calls-with-defenseclaw/)':215 'audit':24,54,165 'basic':138 'block':128 'build':88 'call':9,39,158 'capabl':29,59,122 'caveat':95 'cisco-ai-defense.github.io':209 'cisco-ai-defense.github.io/docs/defenseclaw':208 'cli':63,103,129,133 'code':151,182 'combin':99 'command':134 'complet':156 'control':18,48,175 'defenseclaw':11,13,41,43,62,98 'doc':203 'docs/cli.md':131 'docs/quickstart.md':188 'document':207 'enforc':115 'environ':86 'exchang':214 'extract':200 'first':189 'flow':195 'gateway':65,106 'generat':150 'get':142 'getting-start':141 'github.com':198 'github.com/cisco-ai-defense/defenseclaw':197 'go':64,105 'govern':1,31,125 'guardrail':21,51 'histori':166 'instal':75,79 'jsonl':167 'layer':25,55 'lint':92 'local':191 'log':126 'make':87,89,91 'match':84 'mcp':4,34,146,178 'note':144 'openclaw':70,110 'oper':17,47,102,118,136 'operator-control':16,46 'option':69,72 'otlp':168 'otlp/splunk/webhook':73 'path':82 'plugin':71,112,148,180 'polici':67 'prerequisit':61 'prompt':6,36,155 'python':101,132 'quick':186 'raw.githubusercontent.com':205 'raw.githubusercontent.com/cisco-ai-defense/defenseclaw/head/readme.md':204 'refer':130 'requir':93 'rule':68,119 'run':30,60,154,185 'runtim':20,50,163 'sandbox':22,52,160 'scan':124,176,194 'server':5,35,147,179 'setup':81,192 'sidecar':66,107 'simpl':117 'sink':74 'skill':3,33,145,177,213 'skill-govern-agent-skills-mcp-servers-prompts-and-tool-calls-with-defenseclaw' 'sourc':196,211 'source-agentskillexchange' 'splunk':169 'sqlite':164 'start':143,187 'success':190 'test':90 'togeth':113 'tool':8,38,157 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-tools' 'topic-awesome-list' 'topic-claude-code' 'topic-codex' 'topic-cursor' 'topic-llm' 'topic-mcp' 'topic-npx-skills' 'topic-openclaw' 'topic-skills-catalog' 'tui':172 'typescript':111 'untrust':27,57,120 'upstream':78,97,202 'usag':139 'use':12,42,76 'view':173 'webhook':170 'workflow':137","prices":[{"id":"6fbf545b-8b99-40df-8ac8-cb29b468035b","listingId":"13f9b091-f9c4-48c5-a6b0-7f37c939a8a5","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"agentskillexchange","category":"skills","install_from":"skills.sh"},"createdAt":"2026-05-18T13:16:54.817Z"}],"sources":[{"listingId":"13f9b091-f9c4-48c5-a6b0-7f37c939a8a5","source":"github","sourceId":"agentskillexchange/skills/govern-agent-skills-mcp-servers-prompts-and-tool-calls-with-defenseclaw","sourceUrl":"https://github.com/agentskillexchange/skills/tree/main/skills/govern-agent-skills-mcp-servers-prompts-and-tool-calls-with-defenseclaw","isPrimary":false,"firstSeenAt":"2026-05-18T13:16:54.817Z","lastSeenAt":"2026-05-18T19:10:44.679Z"}],"details":{"listingId":"13f9b091-f9c4-48c5-a6b0-7f37c939a8a5","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"agentskillexchange","slug":"govern-agent-skills-mcp-servers-prompts-and-tool-calls-with-defenseclaw","github":{"repo":"agentskillexchange/skills","stars":8,"topics":["agent-skills","ai-agents","ai-tools","awesome-list","claude-code","codex","cursor","llm","mcp","npx-skills","openclaw","skills-catalog"],"license":"mit","html_url":"https://github.com/agentskillexchange/skills","pushed_at":"2026-05-18T19:02:17Z","description":"The open catalog of AI agent skills — 2,000+ security-scanned skills for Claude Code, Cursor, Codex, and more.","skill_md_sha":"fc07f6c7b87822a4f503716419d9bf49b1fbcebd","skill_md_path":"skills/govern-agent-skills-mcp-servers-prompts-and-tool-calls-with-defenseclaw/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/agentskillexchange/skills/tree/main/skills/govern-agent-skills-mcp-servers-prompts-and-tool-calls-with-defenseclaw"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"Govern agent skills, MCP servers, prompts, and tool calls with DefenseClaw","description":"Use DefenseClaw as an operator-controlled admission, runtime guardrail, sandbox, and audit layer before untrusted agent capabilities run."},"skills_sh_url":"https://skills.sh/agentskillexchange/skills/govern-agent-skills-mcp-servers-prompts-and-tool-calls-with-defenseclaw"},"updatedAt":"2026-05-18T19:10:44.679Z"}}