Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add CrowdStrike/crowdstrike-mcp-skills/plugin install crowdstrike-mcpWrote 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/crowdstrike/crowdstrike-mcp-skills/setup)<a href="https://agentmods.dev/skills/crowdstrike/crowdstrike-mcp-skills/setup"><img src="https://agentmods.dev/badge/skills/crowdstrike/crowdstrike-mcp-skills/setup/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/crowdstrike/crowdstrike-mcp-skills/setup"><img src="https://agentmods.dev/badge/skills/crowdstrike/crowdstrike-mcp-skills/setup.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 | $0.00047 | $0.00750 |
| Opus 5.5 | $0.00019 | $0.00300 |
| Sonnet 5.5 | $0.00009 | $0.00150 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
crowdstrike-mcp:setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
- Verifying the required environment variables are set
- Running
mcp-server-setup.shto exchange credentials, detect the user's Falcon region, and write a.mcp.jsonfile in the plugin's directory - Confirming successful installation
The skill should be conversational but efficient — a single user message
(/crowdstrike-mcp:setup) should complete the entire flow without unnecessary
back-and-forth unless credentials are missing.
Environment check:
- FALCON_CLIENT_ID set: !
[[ -n "${FALCON_CLIENT_ID:-}" ]] && echo "YES" || echo "NO" - FALCON_CLIENT_SECRET set: !
[[ -n "${FALCON_CLIENT_SECRET:-}" ]] && echo "YES" || echo "NO" - FALCON_MEMBER_CID set: !
[[ -n "${FALCON_MEMBER_CID:-}" ]] && echo "YES (${FALCON_MEMBER_CID})" || echo "NO (optional)"
Existing .mcp.json: ![[ -f "${CLAUDE_PLUGIN_ROOT}/.mcp.json" ]] && echo "EXISTS" || echo "NOT FOUND"
Scripts:
- ${CLAUDE_PLUGIN_ROOT}/scripts/mcp-server-setup.sh
- ${CLAUDE_PLUGIN_ROOT}/scripts/crowdstrike-oauth2token.sh
Step 1: Check credentials
Read the context block above.
If FALCON_CLIENT_ID or FALCON_CLIENT_SECRET is "NO":
Stop and tell the user exactly what to do:
To use the CrowdStrike MCP server, you must first export your Falcon API credentials:
export FALCON_CLIENT_ID="<your client ID>"
export FALCON_CLIENT_SECRET="<your client secret>"
Optional — required only for MSSP / Flight Control tenants:
export FALCON_MEMBER_CID="<member CID>"
You can obtain API credentials in the Falcon console under
API Clients & Keys > Create API Client.
Once exported, re-run /crowdstrike-mcp:setup.
Do not proceed further.
If both variables are set: continue to Step 2.
Step 2: Run mcp-server-setup.sh
Execute the setup script:
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT}" "${CLAUDE_PLUGIN_ROOT}/scripts/mcp-server-setup.sh"
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.
- 2mo ago First seen · 96 lines · 47 tokens per session scan A 9c2d5ed5ff99
crowdstrike-mcp:setup is a skill published in the GitHub repository CrowdStrike/crowdstrike-mcp-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 750 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
crowdstrike-mcp:setup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| crowdstrike-mcp:setupCrowdStrike/crowdstrike-mcp-skills | Skill | 14 | 2mo ago | MIT | A | 47 | Claude Code |
| reviewSethGammon/Citadel | Skill | 927 | yesterday | MIT | A | 17 | Claude Code |
| generate-clipDojoCodingLabs/remotion-superpowers | Skill | 157 | 8d ago | MIT | A | 32 | Claude Code |
| extract-resumesuxrobGM/jobpilot | Skill | 109 | yesterday | MIT | A | 32 | Claude Code |
| wenlan-handoffwenlan-app/wenlan | Skill | 93 | yesterday | Apache-2.0 | A | 43 | Claude Code, Codex |
| pr-reviewnitinjain999/platform-skills | Skill | 71 | yesterday | Apache-2.0 | A | 81 | Claude Code |
| read-literaturefirecrawl/firecrawl-claude-plugin | Skill | 255 | 4d ago | MIT | A | 101 | Claude Code |