chatgpt-app-typescript-template

Starter template for building an MCP Apps (Model Context Protocol) application with a Node.js/Express MCP server and React-based widget resources. Includes an example “echo” tool with Zod input validation, resource/widget registration, UI capability negotiation, inline/PIP/fullscreen display mode support, and local dev/testing tooling (Storybook, Vitest) plus Docker support. Also documents how to expose the MCP endpoint publicly for hosts such as ChatGPT via Pomerium SSH tunnel and how to connect via the host’s connector UI.

Evaluated Mar 30, 2026 (21d ago)
Homepage ↗ Repo ↗ DevTools mcp mcp-apps model-context-protocol react typescript express widgets identity-aware-proxy pomerium template devtools docker
⚙ Agent Friendliness
63
/ 100
Can an agent use this?
🔒 Security
46
/ 100
Is it safe for agents?
⚡ Reliability
34
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
82
Error Messages
0
Auth Simplicity
55
Rate Limits
20

🔒 Security

TLS Enforcement
80
Auth Strength
30
Scope Granularity
30
Dep. Hygiene
45
Secret Handling
50

From the provided README, HTTPS/TLS usage is implied via tunneling/production URL guidance but not explicitly guaranteed for the MCP server itself. Application-level auth/scopes for /mcp are not described. Tool input validation via Zod is demonstrated in the example, which can reduce certain classes of malformed-input issues, but no detailed guidance is provided on authn/authz, rate limiting, SSRF/URL safety, or secure secret management practices. Dependency hygiene and CVE status cannot be determined from the partial manifest content provided.

⚡ Reliability

Uptime/SLA
0
Version Stability
40
Breaking Changes
40
Error Recovery
55
AF Security Reliability

Best When

You want a well-structured baseline to implement MCP tools + React widget resources, and you’re comfortable running and securing your own backend deployment endpoint (e.g., HTTPS behind a proxy).

Avoid When

You need turnkey authentication/authorization, rate limiting, and security controls with clear documented guarantees from the template alone; or you cannot expose a public HTTPS endpoint for the host to connect to /mcp.

Use Cases

  • Build a new MCP Apps server with typed tool schemas
  • Create React widgets that bind to MCP tool results and host context (theme, display mode, container dimensions)
  • Provide UI-capable resources for MCP hosts with fallback to text-only
  • Prototype and test MCP tools locally with an MCP inspector and Storybook
  • Use as production-ready scaffolding with linting/testing/build scripts and Docker

Not For

  • Directly using it as a standalone hosted SaaS API (it’s a template you run/deploy)
  • Production deployments that require a documented, opinionated security/authentication model out-of-the-box for all host interactions (not specified in README)
  • Use cases needing documented REST/GraphQL/OpenAPI web APIs or complex pagination/webhook patterns

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
Yes
Webhooks
No

Authentication

Methods: Pomerium OAuth flow (for establishing SSH tunnel to expose local endpoint for testing)
OAuth: Yes Scopes: No

README describes using Pomerium SSH tunneling to expose localhost to a public URL; it does not specify application-level auth for the /mcp endpoint itself. AuthZ/authN expectations for production host access are not documented in the provided README content.

Pricing

Free tier: No
Requires CC: No

No pricing because this is a template repo rather than a hosted service.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • This is a template; it’s not a managed service. Hosts must connect to your deployed /mcp endpoint, so runtime behavior depends on how you implement/secure tools.
  • For widget operation, hosts decide and enforce display mode; code should treat the returned mode as source-of-truth.
  • UI resource negotiation may fall back to text-only for non-UI clients; ensure tools still return usable non-UI content.
  • No documented retry/idempotency semantics for tool calls in the provided README excerpt.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for chatgpt-app-typescript-template.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered