Audit connected MCP servers for token overhead, redundancy, and security. Use when sessions feel slow or before adding new MCPs.
git clone https://github.com/rohitg00/pro-workflow.git--- name: mcp-audit description: Audit connected MCP servers for token overhead, redundancy, and security. Use when sessions feel slow or before adding new MCPs. user-invocable: true --- # MCP Audit Analyze MCP server overhead and recommend cleanup. ## Trigger Use when: - Sessions feel slow or expensive - Adding a new MCP server - Context fills up quickly - Reviewing project configuration ## Key Insight Each MCP server adds ALL its tool descriptions to every API request. A server with 20 tools adds ~2K-4K tokens per request, regardless of whether you use those tools. ## Audit Steps ### Step 1: List Active Servers Check all MCP configurations: ```bash cat .claude/settings.json 2>/dev/null | grep -A 50 "mcpServers" cat ~/.claude/settings.json 2>/dev/null | grep -A 50 "mcpServers" ``` ### Step 2: Count Tools Per Server For each server, estimate token overhead: - 1-5 tools: ~200-500 tokens (low overhead) - 6-15 tools: ~500-1500 tokens (moderate) - 16-30 tools: ~1500-3000 tokens (high) - 30+ tools: ~3000+ tokens (excessive — consider tool filtering) ### Step 3: Check Usage Questions to ask: - Which servers were actually used this session? - Which servers haven't been used in 7+ days? - Are there servers with overlapping functionality? - Are there servers only needed for specific tasks? ### Step 4: Recommend Actions **Disable** servers that: - Haven't been used in 7+ days - Overlap with another active server - Are project-specific but you're in a different project **Keep** servers that: - Are used every session (filesystem, git) - Provide unique capabilities needed for current work - Have low tool count (<5 tools) ## Output ```text MCP AUDIT Active servers: [N] Total tools: [N] Estimated overhead: ~[N]K tokens per request Server Analysis: [name] — [N] tools, ~[N] tokens Status: KEEP / DISABLE / REVIEW Reason: [why] Recommendations: Disable: [list] Keep: [list] Review: [list] Projected savings: ~[N]K tokens per request (~$X.XX per session) ``` ## Thresholds - Total servers: <10 (ideal), 10-15 (monitor), >15 (reduce) - Total tools: <80 (ideal), 80-120 (monitor), >120 (reduce) - Per-server: <15 tools (ok), 15-30 (filter), >30 (split or disable) ## Rules - Never disable servers without user confirmation - Estimate token savings for each recommendation - Consider task context — a server might be unused today but critical tomorrow - Check for `disabledMcpjsonServers` to avoid re-recommending already-disabled servers
["Open your MCP management interface (e.g., `claude://mcp` or `chatgpt://mcp`).","Run the audit command: `audit --session [SESSION_NAME] --concern [SPECIFIC_CONCERN]`.","Review the report for **token overhead** (unused servers), **redundancy** (duplicate functionality), and **security risks** (outdated protocols).","Prioritize fixes based on the report’s recommendations. Start with security risks, then redundancy, then overhead.","After implementing changes, re-run the audit to verify improvements. Use `--compare` to track token savings over time."]
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/rohitg00/pro-workflow/tree/main/skills/mcp-auditCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Audit the MCP servers connected to [SESSION_NAME] for token overhead, redundancy, and security risks. Focus on [SPECIFIC_CONCERN: e.g., unused servers, high token consumption, or outdated configurations]. Provide a prioritized list of recommendations with estimated token savings and security improvements.
### MCP Audit Report for 'ResearchSession_2024-05-15' **Connected Servers:** 1. **FileSystem MCP** (v1.2.0) - Active, 1.2M tokens consumed this session 2. **BrowserTool MCP** (v0.9.5) - Active, 850K tokens consumed 3. **DatabaseQuery MCP** (v2.1.1) - Active, 450K tokens consumed 4. **LegacyWebSearch MCP** (v0.4.3) - **Inactive** (last used 3 days ago) 5. **DeprecatedAPI MCP** (v1.0.0) - **Security Risk**: Uses HTTP instead of HTTPS **Key Findings:** - **Token Overhead:** The LegacyWebSearch server (inactive) is still consuming 50K tokens per session due to background polling. Removing it would save ~150K tokens/month. - **Redundancy:** BrowserTool and DatabaseQuery both handle web requests, but BrowserTool is more efficient (30% fewer tokens for similar tasks). - **Security Risks:** DeprecatedAPI uses HTTP and lacks authentication, exposing session data. Upgrading to v2.0.0 (HTTPS + OAuth) is critical. **Recommendations:** 1. **Remove LegacyWebSearch** (Saves ~150K tokens/month, reduces clutter) 2. **Replace DatabaseQuery with BrowserTool** for web-related tasks (Saves ~120K tokens/session) 3. **Upgrade DeprecatedAPI** to v2.0.0 (Fixes security vulnerability) 4. **Update FileSystem MCP** to v1.3.0 (Patch for a known token leak bug) **Estimated Impact:** - Token savings: ~270K/month - Security improvements: 2 critical risks resolved - Session speed: ~15% faster (fewer active servers)
skills-collection
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan