Server data from the Official MCP Registry
Deploy serverless TypeScript on Val Town: HTTP vals, cron, SQLite, email, OAuth.
Deploy serverless TypeScript on Val Town: HTTP vals, cron, SQLite, email, OAuth.
Remote endpoints: streamable-http: https://api.val.town/v3/mcp
Valid MCP server (1 strong, 1 medium validity signals). 1 known CVE in dependencies Imported from the Official MCP Registry.
Endpoint verified · Requires authentication · 2 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Remote Plugin
No local installation needed. Your AI client connects to the remote endpoint directly.
Add this to your MCP configuration to connect:
{
"mcpServers": {
"town-val-mcp": {
"url": "https://api.val.town/v3/mcp"
}
}
}From the project's GitHub README.
Installs the Val Town MCP server and Skills for Claude Code, Codex, and Cursor.
Skills are markdown files with platform guidance for building on Val Town. Used by Val Town's own tools (Townie, the MCP server) and by AI coding agents. Skills include HTTP vals, crons, SQLite, email, OAuth, frontend, and API integrations.
Installing the plugin makes platform skills available to your agent and registers
the hosted Val Town MCP server (https://api.val.town/v3/mcp). On first use of
an MCP tool, the agent runs the OAuth flow in your browser.
Install the Val Town plugin by running:
claude plugin install valtown@claude-plugins-official
codex CLIFirst, run:
codex plugin marketplace add val-town/plugins
Then fire up codex and run:
/plugins
Search for Val Town, hit install, and it'll take you through the OAuth path.
https://github.com/val-town/plugins and select "Add marketplace"In Cursor, run:
/add-plugin valtown
Or in Cursor Settings, copy-paste https://github.com/val-town/plugins in the search box and select "Add to Cursor."
Skills live in plugin/skills/<name>/SKILL.md with YAML frontmatter:
---
name: http-endpoints
description: Use when building an HTTP val — a web endpoint, API route, webhook...
triggers: [http, endpoint, webhook, api, request, response]
---
# HTTP Endpoints
...guide body...
name (required) — must match the directory name; lowercase, hyphens, ≤64 chars.description (required) — written as "Use when…"; this is how Claude decides
to load the skill. ≤1024 chars.triggers (optional) — keyword hints that boost searchSkills ranking;
ignored by Claude Code's native loader.Keep content audience-neutral: only platform knowledge true for every consumer. No product-flow or chat-only advice.
Then build:
npm install
npm run build # generate src/generated/skills.ts, then tsc
npm test # build + smoke tests
npm run generate validates every skill against both our schema and Claude
Code's frontmatter constraints — a skill that wouldn't load in Claude Code
fails the build.
This package is the source of truth for skill content. The Val Town app and MCP
server consume it as a dependency rather than holding their own copy. See
docs/SKILLS_PLUGIN.md in the main repo for the full design.
This repository uses Changesets for publishing. See their documentation for more information.
npx @changesets/cli
and fill out the interactive prompts to describe the changes. This will generate
a new changeset in the .changesets directory.release.yml GitHub action
to create a new release PR.The official Claude plugin marketplace pulls from .plugins/marketplace.json.
Codex reads the native marketplace at .agents/plugins/marketplace.json (and
falls back to the Claude .claude-plugin/marketplace.json for compatibility).
Cursor reads .cursor-plugin/marketplace.json and the per-plugin plugin/.cursor-plugin/plugin.json.
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.