HAPI MCP Server
HAPI MCP exposes OpenAPI specifications as MCP tools dynamically using the la-rebelion hapimcp project and MCP Registry package ai.com.mcp/hapi-mcp.
Open the source and read safety notes before installing.
Safety notes
- HAPI exposes live API operations as MCP tools—inherited auth, rate limits, and write scope apply.
- Mount only trusted OpenAPI specs; malicious operations become callable tools.
- Protect Authorization headers; registry metadata marks them as secrets.
Privacy notes
- Tool calls may send API payloads, account metadata, and response bodies to the MCP client.
- Self-hosted Docker deployments keep traffic on your infrastructure; review OpenAPI response schemas for PII.
Prerequisites
- OpenAPI specification file or project configured for HAPI CLI serve mode.
- Docker available for the OCI package docker.io/hapimcp/hapi-cli.
- Review of which API operations become MCP tools before enabling write methods.
Schema details
- Install type
- cli
- Troubleshooting
- No
- Scope
- Source repo
- Estimated setup
- 20 minutes
- Difficulty
- intermediate
Full copyable content
{
"mcpServers": {
"hapi": {
"url": "https://YOUR_HAPI_HOST:3030/mcp",
"type": "http"
}
}
}About this resource
Overview
HAPI MCP converts OpenAPI catalogs into MCP tools without rewriting backend services.
The project README and MCP Registry entry ai.com.mcp/hapi-mcp document Docker-based
hapi-cli serve workflows and streamable HTTP transport.
Installation
Docker (registry package)
docker run -p 3030:3030 -v ~/.hapi:/app/.hapi docker.io/hapimcp/hapi-cli:0.6.0 serve YOUR_PROJECT
Point MCP clients at the documented /mcp HTTP endpoint with required Authorization headers.
Source Verification Notes
Verified on 2026-06-17:
- GitHub repository la-rebelion/hapimcp README describes OpenAPI-in, MCP-tools-out workflow.
- MCP Registry lists
ai.com.mcp/hapi-mcpwith OCI package docker.io/hapimcp/hapi-cli:0.6.0. - Registry transport type is streamable-http with secret Authorization header guidance.
Duplicate Check
No existing content/mcp/ entry documents HAPI OpenAPI-to-MCP tooling.
Editorial Disclosure
Community MCP listing by kiannidev from public README and MCP Registry metadata. No affiliate links.
Source citations
Add this badge to your README
How it compares
HAPI MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
| Field | HAPI MCP Server HAPI MCP exposes OpenAPI specifications as MCP tools dynamically using the la-rebelion hapimcp project and MCP Registry package ai.com.mcp/hapi-mcp. Open dossier | After Effects MCP Server MCP server for controlling Adobe After Effects through a local Node bridge and ScriptUI panel for compositions, layers, keyframes, expressions, masks, and effects. Open dossier | AI Game Developer Unity MCP Server Unity MCP server, plugin, CLI, and skill generator for controlling Unity Editor and runtime projects from MCP clients through built-in game-dev tools. Open dossier | Alpaca MCP Server Official Alpaca MCP server for Trading API workflows, including account and portfolio data, orders, positions, watchlists, assets, stocks, crypto, options, news, corporate actions, and market data. Open dossier |
|---|---|---|---|---|
| Trust | ||||
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Category | mcp | mcp | mcp | mcp |
| Source | source-backed | source-backed | source-backed | source-backed |
| Author | HAPI MCP | Dakkshin | Ivan Murzak | Alpaca |
| Added | 2026-06-17 | 2026-06-06 | 2026-06-06 | 2026-06-06 |
| Platforms | Claude CodeCursorClaude Desktop | Claude CodeClaude Desktop | Claude CodeClaude Desktop | Claude CodeClaude Desktop |
| Source repo | — | — | — | — |
| Safety notes | ✓HAPI exposes live API operations as MCP tools—inherited auth, rate limits, and write scope apply. Mount only trusted OpenAPI specs; malicious operations become callable tools. Protect Authorization headers; registry metadata marks them as secrets. | ✓After Effects MCP queues predefined commands to a local bridge directory and relies on an open After Effects ScriptUI panel to execute them. The bridge can create compositions, text layers, shape layers, solid layers, cameras, null objects, masks, keyframes, expressions, effects, and layer property changes. Layer duplication, layer deletion, expression changes, masks, timing edits, and batch property updates can materially alter an After Effects project. The install script may copy files into Adobe application folders and may require elevated privileges on some systems. Enabling After Effects scripting permissions can let scripts write files and access network resources, so keep the bridge limited to trusted projects. Use only the predefined script list exposed by the MCP server; do not modify it to accept arbitrary scripts unless that risk is understood. | ✓AI Game Developer can create, move, copy, modify, and delete Unity assets, scenes, GameObjects, components, scripts, packages, and generated project files. Tools include dynamic C# script execution, C# reflection method lookup and calls, package installation/removal, Unity test execution, editor state changes, play mode control, screenshots, and profiler access. The MCP server supports streamable HTTP and stdio; HTTP deployments should require a bearer token and stay bound to trusted interfaces. Server variables include optional authorization and webhook settings; webhook endpoints can receive tool, prompt, resource, connection, and authorization events. Unity runtime connections can expose compiled game state or in-game behavior to an MCP client, not just editor-only project data. Use source control, backups, tool filtering, and explicit review before allowing destructive tools such as asset deletion, package removal, script execution, or reflection calls. | ✓Alpaca MCP Server can expose account balances, buying power, positions, orders, activities, watchlists, assets, market data, news, corporate actions, stocks, crypto, options data, and trading tools to the MCP client. Trading tools can place stock, ETF, crypto, and option orders, cancel orders, close positions, liquidate portfolios, replace orders, and exercise or mark do-not-exercise option contracts. Paper trading is the default documented mode; setting `ALPACA_PAPER_TRADE=false` points trading calls at live Alpaca accounts and can result in real financial losses. Require explicit human approval before any order placement, cancellation, liquidation, option exercise, live-account change, or strategy involving leverage, margin, extended hours, crypto, or options. Use `ALPACA_TOOLSETS` to restrict the server to read-only or data-only toolsets when trading tools are not needed. The upstream order override code warns that read timeouts may happen after an order was sent; users should check open orders before retrying to avoid duplicate trades. |
| Privacy notes | ✓Tool calls may send API payloads, account metadata, and response bodies to the MCP client. Self-hosted Docker deployments keep traffic on your infrastructure; review OpenAPI response schemas for PII. | ✓Tool calls and results can expose composition names, project structure, layer names, layer properties, timing, expressions, effect names, masks, and local bridge file paths. Project contents may include client work, unreleased media, brand assets, filenames, text layers, and animation details. The command and result files in the local bridge directory can persist recent instructions and After Effects output. MCP client logs and model context may retain prompts, layer names, generated expressions, and project metadata. | ✓Tool calls may expose Unity project paths, asset names, scene hierarchy, serialized object data, scripts, logs, screenshots, profiler metrics, test output, package metadata, and runtime state. MCP config files and Unity plugin config can contain server URLs, connection modes, bearer tokens, authorization settings, enabled tool IDs, and cloud or local endpoint details. Optional webhooks can receive tool, prompt, resource, connection, authorization, and token-bearing request data. Screenshots from Game View, Scene View, cameras, or isolated GameObjects may include proprietary artwork, level design, UI, debug overlays, or unreleased game content. Generated skills and AI-client configuration files can reveal available tools, project structure, installed packages, and local workflow assumptions. | ✓Alpaca API keys, secret keys, account IDs, balances, buying power, portfolio history, activities, positions, orders, watchlists, option contracts, crypto holdings, and trade history can be exposed to the MCP client. Prompts and responses may include private trading strategy, portfolio allocation, order intent, symbols, quantities, prices, client order IDs, and market data queries. MCP clients, model providers, terminal history, logs, and chat transcripts may retain financial data and trading instructions. Upstream documentation states the server sends an Alpaca MCP user agent string for API calls; review Alpaca privacy and disclosure materials for account data handling. |
| Prerequisites |
|
|
|
|
| Install | | | | |
| Config | | | | |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Signals
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.