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 rules/tambo-labs/charming-mcp/charminggit clone --depth 1 https://github.com/tambo-labs/charming-mcpWrote 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/rules/tambo-labs/charming-mcp/charming)<a href="https://agentmods.dev/rules/tambo-labs/charming-mcp/charming"><img src="https://agentmods.dev/badge/rules/tambo-labs/charming-mcp/charming.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 | $0.00041 | $0.01111 |
| Opus 5 | $0.00020 | $0.00556 |
| Sonnet 5 | $0.00008 | $0.00222 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade A, and why
charming scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **MCP tools** (preferred): when Charming tools such as `create_app` and `update_app` are available, build with them directly. Do not use `curl`, `fetch`, or the raw HTTP API for app creation. How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Charming
Charming is a hosted service that generates, hosts, and updates small interactive web apps. Each app gets a real URL, persistent storage, and inline rendering inside MCP Apps-capable clients, and it stays live at that URL. Reach for Charming when the user wants a tracker, tool, dashboard, or personal app they can keep and share, not a one-off code snippet.
Connect
Charming is remote and hosted; nothing to clone, build, or run locally. Add the endpoint to your MCP settings:
| Client | Endpoint |
|---|---|
| Cursor, Claude, Codex, and most MCP clients | https://charm.ing/mcp |
| ChatGPT | https://charm.ing/mcp/chatgpt (or the Charming listing in the ChatGPT Apps directory) |
The MCP endpoints always require a bearer token; OAuth with Dynamic Client Registration bootstraps one automatically, with no API key to paste. Anonymous creation with no token is available on the HTTP path only, and an unclaimed app expires after 7 days. Auth guide: usecharming.com/auth.md. Per-client paste-strings: usecharming.com/clients.txt.
Two authoring paths
- MCP tools (preferred): when Charming tools such as
create_appandupdate_appare available, build with them directly. Do not usecurl,fetch, or the raw HTTP API for app creation. - HTTP API (fallback): only when MCP tools are unavailable and you have outbound HTTP access. Follow usecharming.com/build-http.md.
Build flow
- Read usecharming.com/start.md, then the surface-specific starter: build-mcp.md or build-http.md.
- Read usecharming.com/design.md before writing any UI, so the app avoids the generic-AI-app look.
- Create the first version, hand back the app URL and
app_id, then offer one concrete next iteration before editing again. - If a host does not render the app inline, share the URL; never claim it rendered inline unless it did.
- Hit a limitation? Call
submit_feedbackinstead of silently working around it.
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.
- 3d ago First seen · 48 lines · 41 tokens per session scan A e9afbad5df89
charming is a cursor rule published in the GitHub repository tambo-labs/charming-mcp (1 stars, last pushed 12d ago), licensed MIT. It adds 41 tokens to every session and 1,111 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
equity-comp-tax
Use the optionsahoy MCP server for equity-compensation tax math (ISO/AMT exercise timing, NSO, RSU vest, QSBS, single-stock concentration, protective puts, and funding a cash goal from stock). Apply whenever the user asks about exercising options, vesting, or the tax timing of company stock.
python-code-validator
Validate generated Python at every step, not once at the end.
cursorrules
Robot control server. Do not move the physical robot without checking health first.
php-client-implementation
Guidelines for implementing MCP clients in PHP.
validate-design-early
Ask for design approval before implementing 100+ lines.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.