cloudflare-mcp: Agent for Claude Code

.github/agents/skeleton-services-mcp.agent.md

Cloudflare MCP Configurator is an agent for Claude Code from LesterAJohn/cloudflare-mcp. It costs 42 tokens per session (1,157 once invoked), scanned A, original, MIT.

A workspace-specific implementation guide for adapting a code repository into a Cloudflare MCP solution. MCP is a standard way for AI agents to call tools, while Cloudflare provides web and infrastructure services.

In plain words
What is it for?
Use it when configuring Cloudflare API tools, Vault token storage, Postgres configuration, stdio or HTTP connections, admin-protected changes, tests, or documentation.
Why use it?
Cloudflare integrations involve authentication, user-specific tokens, stored configuration, API coverage, and permission checks. This guide keeps those parts aligned with the repository’s documented design.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

This is LesterAJohn/cloudflare-mcp's own configuration. It tells Claude Code how to work on cloudflare-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cloudflare-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to LesterAJohn/cloudflare-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/LesterAJohn/cloudflare-mcp/main/.github/agents/skeleton-services-mcp.agent.md
Clone the repo
git clone --depth 1 https://github.com/LesterAJohn/cloudflare-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for Cloudflare MCP Configurator

README.md
[![agentmods](https://agentmods.dev/badge/agents/lesterajohn/cloudflare-mcp/skeleton-services-mcp.svg)](https://agentmods.dev/agents/lesterajohn/cloudflare-mcp/skeleton-services-mcp)
Your own site
<a href="https://agentmods.dev/agents/lesterajohn/cloudflare-mcp/skeleton-services-mcp"><img src="https://agentmods.dev/badge/agents/lesterajohn/cloudflare-mcp/skeleton-services-mcp.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,157 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.01157
Opus 5 $0.00021 $0.00579
Sonnet 5 $0.00008 $0.00231
Haiku 4.5 $0.00004 $0.00116

Measured 6d ago against content hash 676ad2cb75c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Cloudflare MCP Configurator 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 6d 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.

.github/agents/skeleton-services-mcp.agent.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a workspace-scoped implementation agent for this repository.

Primary goal: Keep the Cloudflare MCP solution aligned with the Cloudflare API docs while preserving secure MCP patterns.

Required solution constraints:

  • Multi-user support is mandatory.
  • User tokens are multi-user and stored in Vault.
  • Configuration must be persisted in Postgres.
  • Mutating tools must honor MCP_ADMIN_AUTH_KEY when configured.

Documentation links to treat as source of truth:

Current solution capabilities to preserve:

  • Dual MCP transports: stdio and HTTP.
  • HTTP auth modes: token, oauth2, or both.
  • Vault-backed multi-user Cloudflare token storage with default-user fallback.
  • Dedicated Cloudflare tools for connection info, scope info, token management, config management, schema discovery, and DNS/account workflows.
  • Generic cloudflare_api_request coverage for all Cloudflare API endpoints.
  • Postgres-backed multi-user config model with default user scope.
  • Admin-gated mutating tools and generic mutating requests.
  • Cloudflare API docs discovery and query-suggestion tools with LLM-facing guidance.
  • Vault Raft persistence in local and production compose stacks.
  • App-only external deployment mode (docker-compose.external.yml) for existing Vault and Postgres services.
  • APP_NAME as the single naming source for derived Vault token paths and Postgres config tables.

Always start by reviewing:

Documentation freshness requirements:

  1. Re-read linked docs before planning changes that touch transports, auth, token model, or config model.
  2. If implementation behavior changes, update the relevant linked docs in the same change.
  3. Before finalizing, ensure tool catalog, env variables, and test coverage notes in README.md match the code.

Required implementation workflow:

  1. Identify requested Cloudflare capability and map it into read-only vs mutating operations.
  2. Add or extend environment configuration in src/config/env.js with validation.
  3. Implement or extend the Cloudflare service adapter in src/services with clear boundaries and API docs discovery support.
  4. Register MCP tools in src/mcp/server.js using existing error handling wrappers.
  5. Enforce authorizationKey checks for mutating operations.
  6. Preserve sensitive output controls and avoid returning raw secrets by default.
  7. Update runtime wiring in src/index.js and src/http/index.js when new dependencies are required.
  8. Preserve transport behavior for stdio/http/both and avoid regressions in HTTP security controls.
  9. Keep Vault for secrets and Postgres for configuration unless explicitly requested otherwise.
  10. Add tests in tests/*.test.js for success paths, auth failures, redaction behavior, and transport-level behavior when touched.
  11. For config changes, maintain multi-user scoping with default user fallback.
  12. For token-related changes, maintain default-user fallback semantics in Vault token selection.
  13. If dedicated Cloudflare token, config, or DNS operations are requested, expose them as MCP tools with strict authorization and safe output.
  14. Update README.md so new tools and environment variables are documented.
  15. Run npm test before finishing and summarize changes with file paths.
  16. If compose or Vault startup behavior changes, preserve vault-unseal-key-init dependency ordering and document any new env variables.
  17. If external services are supported, document the app-only compose path and required VAULT_* and POSTGRES_* env vars.
  18. If app naming changes, derive Vault token paths and Postgres config tables from APP_NAME and avoid separate naming knobs in docs.

Read the full file on GitHub · 89 lines

Changes

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.

  1. 6d ago First seen · 89 lines · 42 tokens per session scan A 676ad2cb75c3

Subscribe to this mod's changes

Cloudflare MCP Configurator is an agent published in the GitHub repository LesterAJohn/cloudflare-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,157 once invoked, about $0.0002 per session on Opus 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.

Related

Other agents, from other repositories

aws-architecture-review-expert

Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…

giuseppe-trisciuoglio/developer-kit · 76 tokens

azure-architect

Designs Azure cloud architecture, optimizes costs, and implements security best practices. Use when designing Azure infrastructure, selecting Azure services, or optimizing Azure deployments.

armanzeroeight/fastagent-plugins · 35 tokens

deployment-verifier

Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.

asysta-act/agent-flow · 24 tokens

database-migration

Database migration and modernization specialist. USE FOR: planning database migrations, designing migration strategies, validating data integrity. DO NOT USE FOR: operational database management, routine backups.

ivegamsft/basecoat · 37 tokens

llm2bedrock-report-generator

Synthesize all prior phase results into a final Markdown migration report — model mapping, eval scores, code diffs, cost comparison, next steps. Writes MIGRATIONREPORT .md and returns a structured report object.

awslabs/startups · 52 tokens

staff-sre

Production reliability specialist. Use PROACTIVELY for incident response, production readiness reviews, SLO enforcement, capacity planning, and any production concern. First responder for incidents.

caiaffa/claude-code-ultimate-engineering-system · 38 tokens