Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/agentfront/frontmcp/frontmcp-deploymentnpx skills add agentfront/frontmcp --skill frontmcp-deploymentgit clone --depth 1 https://github.com/agentfront/frontmcpWrote 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/agentfront/frontmcp/frontmcp-deployment)<a href="https://agentmods.dev/skills/agentfront/frontmcp/frontmcp-deployment"><img src="https://agentmods.dev/badge/skills/agentfront/frontmcp/frontmcp-deployment.svg" alt="Measured on agentmods" 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 | $0.00210 | $0.04656 |
| Opus 5 | $0.00105 | $0.02328 |
| Sonnet 5 | $0.00042 | $0.00931 |
| Haiku 4.5 | $0.00021 | $0.00466 |
Grade A, and why
frontmcp-deployment 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 4d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FrontMCP Deployment Router
Entry point for deploying and building FrontMCP servers. This skill helps you choose the right deployment target or build format based on your infrastructure requirements.
When to Use This Skill
Must Use
- Choosing between deployment targets (Node vs Vercel vs Lambda vs Cloudflare) for a new project
- Deciding on a build format (server vs CLI vs browser vs SDK) for distribution
- Planning infrastructure and need to understand trade-offs between deployment options
Recommended
- Comparing serverless platforms for cost, cold-start, and feature support
- Understanding which transport protocol and storage provider each target requires
- Migrating from one deployment target to another
Skip When
- You already know your deployment target (go directly to
deploy-to-node,deploy-to-vercel, etc.) - You need to configure server settings, not deploy (see
frontmcp-config) - You need to build components, not ship them (see
frontmcp-development)
Decision: Use this skill when you need to figure out WHERE to deploy. Open the matching reference under
references/directly when you already know.
Prerequisites
- A working FrontMCP server with at least one
@Appand one@Tool(seefrontmcp-development) - Server configuration completed (see
frontmcp-config) - Tests passing locally (see
frontmcp-testing)
Steps
- Review the Scenario Routing Table and Target Comparison below to choose a deployment target
- Run
frontmcp build --target <target>to produce the build output - Follow the specific deployment reference (e.g.,
references/deploy-to-node.md,references/deploy-to-vercel.md) for platform instructions - Verify with the Post-Deployment checklist at the end of this skill
Scenario Routing Table
| Scenario | Reference | Description |
|---|---|---|
| Long-running server on VPS, Docker, or bare metal | deploy-to-node |
Node.js with stdio or HTTP transport, PM2/Docker for process management |
| Serverless with zero config and Vercel KV | deploy-to-vercel |
Vercel Functions with Streamable HTTP, Vercel KV for storage |
| AWS serverless with API Gateway | deploy-to-lambda |
Lambda + API Gateway with Streamable HTTP, DynamoDB or ElastiCache |
| Edge computing with global distribution | deploy-to-cloudflare |
Cloudflare Workers with KV or Durable Objects for storage |
| Hosted FrontMCP (v1.3 skills-only model) | deploy-to-cloudflare-skills-only |
Cloudflare Worker as the MCP control plane; OpenAPI is capability inventory; agent uses 4 meta-tools + AgentScript; hot-reload via GitHub Action |
Author frontmcp.deploy.yaml |
deploy-manifest-yaml |
v1 schema reference: runtime, server, specs, skills, tags, classification, bindings, signing, auth, secrets, environments |
| Standalone executable binary for distribution | build-for-cli |
Single-binary CLI with stdio transport, embedded storage |
| Run MCP in a web browser | build-for-browser |
Browser-compatible bundle with in-memory transport |
| Embed MCP into an existing Node.js application | build-for-sdk |
Library build for programmatic usage without standalone server |
| Write a Dockerfile for Node.js deployment | deploy-to-node-dockerfile |
Dockerfile configuration for Node.js deployment |
| Configure Vercel-specific settings (vercel.json) | deploy-to-vercel-config |
Vercel-specific configuration (vercel.json) |
| Connect MCP clients (Claude, Cursor, VS Code) | mcp-client-integration |
Configure .mcp.json for stdio, HTTP, or Unix socket transport |
Serve or consume MCP protocol 2026-07-28 |
protocol-versions |
Stateless requests, server/discover, mirrored headers, MRTR, tasks extension, and the McpStatelessClient |
What ships with it
42 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/build-for-browser/browser-build-with-custom-entry.md 1.8 KB
- examples/build-for-browser/browser-crypto-and-storage.md 3.3 KB
- examples/build-for-browser/react-provider-setup.md 2.7 KB
- examples/build-for-cli/cli-binary-build.md 1.8 KB
- examples/build-for-cli/unix-socket-daemon.md 2.2 KB
- examples/build-for-mcpb/mcpb-bundle-build.md 3.2 KB
- examples/build-for-sdk/connect-openai.md 2.2 KB
- examples/build-for-sdk/create-flat-config.md 2.3 KB
- examples/build-for-sdk/multi-platform-connect.md 3.3 KB
- examples/deploy-to-cloudflare/basic-worker-deploy.md 2.3 KB
- examples/deploy-to-cloudflare/worker-custom-domain.md 2.9 KB
- examples/deploy-to-cloudflare/worker-with-kv-storage.md 2.6 KB
- examples/deploy-to-lambda/cdk-deployment.md 3.1 KB
- examples/deploy-to-lambda/lambda-handler-with-cors.md 3.3 KB
- examples/deploy-to-lambda/sam-template-basic.md 2.7 KB
- examples/deploy-to-node-dockerfile/basic-multistage-dockerfile.md 1.9 KB
- examples/deploy-to-node-dockerfile/secure-nonroot-dockerfile.md 2.4 KB
- examples/deploy-to-node/docker-compose-with-redis.md 2.5 KB
- examples/deploy-to-node/pm2-with-nginx.md 2.1 KB
- examples/deploy-to-node/resource-limits.md 2.4 KB
- examples/deploy-to-vercel-config/minimal-vercel-config.md 2.2 KB
- examples/deploy-to-vercel-config/vercel-config-with-security-headers.md 2.7 KB
- examples/deploy-to-vercel/vercel-mcp-endpoint-test.md 2.7 KB
- examples/deploy-to-vercel/vercel-with-kv.md 2.5 KB
- examples/deploy-to-vercel/vercel-with-skills-cache.md 2.4 KB
- examples/mcp-client-integration/http-remote.md 2.7 KB
- examples/mcp-client-integration/stdio-binary-with-env.md 2.7 KB
- examples/mcp-client-integration/stdio-npx.md 2.0 KB
- references/build-for-browser.md 9.4 KB
- references/build-for-cli.md 8.4 KB
- references/build-for-mcpb.md 12 KB
- references/build-for-sdk.md 11 KB
- references/deploy-manifest-yaml.md 10 KB
- references/deploy-to-cloudflare-skills-only.md 10.0 KB
- references/deploy-to-cloudflare.md 15 KB
- references/deploy-to-lambda.md 15 KB
- references/deploy-to-node-dockerfile.md 3.8 KB
- references/deploy-to-node.md 11 KB
- references/deploy-to-vercel-config.md 4.4 KB
- references/deploy-to-vercel.md 12 KB
- references/mcp-client-integration.md 15 KB
- references/protocol-versions.md 8.4 KB
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.
- 4d ago First seen · 260 lines · 210 tokens per session scan A 1afcb19327e3
frontmcp-deployment is a skill published in the GitHub repository agentfront/frontmcp (146 stars, last pushed 2d ago), licensed Apache-2.0. It adds 210 tokens to every session and 4,656 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
mac-use
Control macOS GUI apps visually — take screenshots, click, scroll, type. Use when the user asks to interact with any Mac desktop application's graphical interface.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
playwright
Use when the task requires capturing or automating a real browser from the terminal.
2-repro-issue
Reproduce a single LinkedIn-MCP issue locally on the current branch against the real authenticated LinkedIn session at /.linkedin-mcp/profile/, using the MCP streamable-http server. Captures the exact failure mode (tool output, error, missing data) and maps it back to the scraper code path. Use when the user says…