Skip to main content
hc
Submit
skillsSource-backedReview first Safety ✓ Privacy ✓

MCP Client Config Audit Capability Pack Skill

Expert MCP client config audit capability pack for reviewing Claude Code MCP server entries, scope placement, tool approval settings, env var secrets, and startup context load before enabling servers in production repositories.

by kiannidev·added 2026-06-14·
Claude CodeCodexWindsurfGeminiCursorCLI
HarnessClaude CodeCodexWindsurfGeminiCursorCLI
Level:expertType:capability-packVerified:validated
Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

  • MCP config files can contain API keys, OAuth client secrets, and bearer tokens that must never be committed to git or pasted into public issues.
  • Enabling write or execute MCP tools in shared repositories expands the blast radius for every contributor using Claude Code in that repo.
  • Project-scoped servers affect all collaborators; user-scoped servers follow individual accounts across repositories unless restricted.
  • Removing an MCP server from config does not automatically revoke OAuth tokens issued to remote vendors.
  • This skill recommends config changes; it must not edit MCP settings or rotate secrets without explicit user approval.

Privacy notes

  • MCP config audits often expose internal service URLs, database hostnames, staging environment names, and account identifiers.
  • Tool schema listings loaded at startup can reveal internal API surface area if copied into public support threads.
  • Shared `.mcp.json` files checked into repositories may leak secrets through git history even after redaction in the current commit.
  • Public audit summaries should describe scope and risk categories, not live credentials or full server manifests.

Prerequisites

  • Redacted access to project `.mcp.json`, user MCP settings, or enterprise MCP policy for the workspace under review.
  • A list of MCP servers currently configured and the repositories or teams that depend on them.
  • Permission to inspect Claude Code startup behavior with `/context` or equivalent MCP tool listings.
  • Platform or security stakeholder available to approve config changes affecting production repositories.

Schema details

Install type
package
Reading time
9 min
Difficulty score
80
Troubleshooting
Yes
Breaking changes
No
Source repository stats
Scope
Source repo
Package metadata
Skill and platform metadata
Skill type
capability-pack
Skill level
expert
Verification
validated
Verified at
2026-06-14
Retrieval sources
https://code.claude.com/docs/en/mcphttps://code.claude.com/docs/en/skillshttps://code.claude.com/docs/en/features-overviewhttps://code.claude.com/docs/en/debug-your-confighttps://github.com/anthropics/claude-codehttps://developers.google.com/search/docs/fundamentals/creating-helpful-content
Tested platforms
ClaudeClaude CodeCodexCursorWindsurfGeneric AGENTS
PlatformSupportInstall path
claude-codeNative.claude/skills/<skill-name>/SKILL.md
codexNative.agents/skills/<skill-name>/SKILL.md
windsurfNative.windsurf/skills/<skill-name>/SKILL.md
geminiNative.gemini/skills/<skill-name>/SKILL.md or .agents/skills/<skill-name>/SKILL.md
cursorAdapter.cursor/rules/<skill-name>.mdc
cliManualAGENTS.md or tool-specific context file
Full copyable content
# Trigger
"Apply the MCP client config audit capability pack for this workspace."

# Required output
1) MCP config inventory by scope (project, user, enterprise)
2) Server transport, auth, and secret-handling assessment
3) Tool approval and write-tool exposure review
4) Startup context and token-cost impact summary
5) Privacy-safe remediation plan

About this resource

Knowledge Freshness

This capability pack is grounded in Claude Code MCP, skills, features overview, and configuration debugging documentation verified on 2026-06-14. MCP config file locations, approval controls, and enterprise policy options can change; prefer live official docs over remembered paths or flags.

Retrieval Sources

Source Verification Notes

Verified against official Claude Code MCP and configuration documentation and the public Anthropic claude-code repository on 2026-06-14:

  • Claude Code reads MCP server definitions from project, user, and enterprise configuration layers; project settings affect all repo collaborators.
  • MCP tool names and schemas load into context at session start, increasing token usage even before any tool is invoked.
  • Claude Code supports tool approval requirements and scoping controls that should gate destructive or production-impacting MCP actions.
  • Environment variables referenced in MCP launch commands are a common secret leakage path when configs are committed or shared in screenshots.
  • Debug and config inspection workflows documented for Claude Code apply to verifying which MCP servers are active in a given workspace.

Scope Note

This is not a substitute for vendor trust review of remote MCP servers. Use it as a reusable client-side audit workflow for Claude Code MCP configuration before enabling servers in shared or production repositories.

Core Workflow

  1. Inventory active MCP servers by scope: project .mcp.json, user settings, enterprise policy, and any checked-in examples or templates.
  2. Classify each server as local stdio, remote SSE, or streamable HTTP and note the authentication method and secret storage location.
  3. Scan for secret leakage: API keys in repo files, env vars with overly broad permissions, and committed OAuth client secrets in git history.
  4. Review tool surface: list available tools, mark write/execute/admin actions, and compare against workflows the team actually needs.
  5. Review approval settings: confirm destructive tools require explicit approval and that auto-approved read tools do not return excessive sensitive data.
  6. Measure startup impact: use /context or equivalent to estimate MCP schema contribution to session load and remove unused servers.
  7. Check scope fit: move personal servers from project config to user scope or remove servers that every collaborator inherits unnecessarily.
  8. Validate enterprise overrides: confirm org policy allows the server, transport, and OAuth domains under review.
  9. Produce a remediation plan with ordered changes, rollback steps, and secret rotation requirements.

Capability Scope

  • MCP config inventory across project, user, and enterprise scope.
  • Transport, auth, and secret-handling review.
  • Tool approval and write-tool exposure assessment.
  • Startup context and token-cost impact summary.
  • Remediation and rollback planning.
  • Privacy-safe config audit reporting.

Compatibility

Native

  • Claude Code / Claude: use as an Agent Skill when onboarding a repository, reviewing shared MCP settings, or preparing a platform hygiene audit.

Manual Adaptation

  • Codex, Cursor, Windsurf, and Generic AGENTS workflows: use the workflow as a deterministic MCP config checklist in platform runbooks.

Required Inputs

  • Redacted MCP config files or settings export for the workspace under review.
  • List of repositories, teams, and workflows depending on each MCP server.
  • Current tool approval policy and any enterprise MCP restrictions.
  • /context breakdown or equivalent MCP startup load observation if available.

Production Rules

  • Never commit live secrets in .mcp.json or launch command env blocks.
  • Prefer project scope only for servers the whole team needs; keep personal integrations in user scope.
  • Require approval for write, delete, execute, and deploy-class MCP tools.
  • Remove unused MCP servers before optimizing prompts or skills.
  • Rotate credentials after removing a server from config or sharing audit logs.
  • Redact URLs, tokens, and internal hostnames in public summaries.
  • Pair this audit with a remote-server trust review for third-party vendors.

Review Matrix

Finding Risk Remediation
Secret in git-tracked config Critical Rotate secret; move to env or secret store
Write tool auto-approved High Enable approval gate or remove tool
Unused server at startup Medium Remove from config to reduce context load
Personal server in project scope Medium Move to user scope or document team need
Remote server without trust review High Run remote-server trust review first
Broad OAuth token in user scope High Revoke token; re-consent with least privilege

Output Contract

  1. MCP config inventory by scope.
  2. Transport, auth, and secret-handling assessment.
  3. Tool approval and write-tool exposure review.
  4. Startup context and token-cost impact summary.
  5. Ordered remediation and rollback plan.
  6. Privacy-safe summary suitable for platform review or team comms.

Duplicate Check

Checked content/skills, content/guides, generated catalog text, and open pull requests for MCP client config audit, Claude Code .mcp.json review, and MCP startup context workflows. Official docs cover MCP setup, but no skills entry provides a reusable client config audit capability pack with remediation matrix and output contract. Complements remote-server trust review without duplicating vendor OAuth analysis.

Editorial Disclosure

Submitted as an independent source-backed HeyClaude content entry by kiannidev. It is based on public Claude Code documentation, the public Anthropic claude-code repository, and Google Search Central helpful-content guidance. No paid placement, referral link, affiliate link, or vendor sponsorship is used.

#mcp#client-config#audit#claude-code#capability-pack

Source citations

Add this badge to your README

Show that MCP Client Config Audit Capability Pack Skill is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/skills/mcp-client-config-audit-capability-pack.svg)](https://heyclau.de/entry/skills/mcp-client-config-audit-capability-pack)

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.