How do I use bedengan-apps?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@bedengan-apps Upload this folder as a new app to Bedengan App Hub." That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

de en es ja ko ru zh

bedengan-apps

by daffaoir

Overview Schema Source Related Servers Discussions Admin

TypeScript

Local

Bedengan Apps MCP

The only way now to publish or update apps on Bedengan App Hub (https://apps.wisatabedengan.com) — via an AI coding tool (e.g. Antigravity), not through the web page anymore.

How to use it daily, in short: once installed (one time only, see below), just ask the AI "please upload this folder as a new app" or "update app X with the latest code". The rest — checking the project, fixing anything missing, then sending — is done automatically. No manual admin approval anymore: once it passes the checks, the app is immediately live.

This is not a new path to the VPS. This server only calls the same hub API using your own account token — it never touches Docker or the server directly.

Install once on your laptop

Download this folder. If you're not used to git clone, just click the green "Code" → "Download ZIP" button on this repo's GitHub page, then extract it to any folder on your laptop (e.g. Documents/bedengan-apps-mcp).
Request an API token from the admin, or create one yourself if you already have an account: go to https://apps.wisatabedengan.com → the "API Token" button → Create / Update API Token. The code that appears is only shown once — note it down before closing the window.
Open a terminal in the extracted folder, then run:
```
npm install
npm run build
npm run init
```
npm run init will ask for the hub URL (press Enter to use the default, https://apps.wisatabedengan.com) and the token from step 2. It is stored in ~/.bedengan-apps/config.json on your own laptop — it is never included in any project zip, and must not be shared with anyone else.

Related MCP server: Deploy MCP

Connect to Antigravity

Add it to Antigravity's MCP server settings (look for the "MCP Servers" menu in its settings):

{
  "mcpServers": {
    "bedengan-apps": {
      "command": "node",
      "args": ["/path/absolut/ke/folder-hasil-ekstrak/dist/index.js"]
    }
  }
}

Replace the path above with the location of dist/index.js inside the folder where you extracted/installed it (step 1 above) — a full path, not relative. After saving, restart Antigravity — its AI can now use the tools below.

What happens when you ask to "upload this folder"

The AI checks the project (validate_project) — it verifies the app type is detected, no secret files (.env, API keys) are included in the zip, and the structure is complete.
If something needs fixing, the AI fixes just that part of the code, then re-checks — repeating until it's clean. You don't need to intervene unless the AI is truly confused.
Once clean, it actually sends it (submit_app for a new app, update_app for updating one that's already live).
No one needs to approve. Within moments the app is accessible at https://<chosen-subdomain>.apps.wisatabedengan.com.

Available tools

Tool	Function
`validate_project`	Check a local folder (without sending anything) — app type detected, structure warnings, and "hard" errors that would cause rejection if not fixed first. Always called first, automatically, before the two tools below.
`submit_app`	Publish a new app. Passes the checks = immediately live on the requested subdomain.
`update_app`	Update an app that is already live and belongs to your own account with the latest code. The old version is automatically saved (can be restored via the web dashboard if the new version turns out to be problematic).
`check_status`	Check the status of a submission and its build progress.
`list_my_apps`	View all apps & submissions belonging to your own account — including the `appId` needed by `update_app`.

If the AI coding tool you use supports "MCP prompts", there is also a ready-to-use flow called siapkan_dan_terbitkan that wraps steps 1-4 above into a single command. If it's not supported, that's fine — the AI still knows the correct order from each tool's description.

If rejected

The rejection message always states what needs to be fixed, for example:

"Automatically rejected -- there are indications of secrets being uploaded: .env file was included in the zip" → remove/exclude .env from the project being sent (see the "Automatically excluded" section below), then try again.
"App type not recognized" → usually the main file is not where expected (e.g. index.html/app.py/package.json is not in the outermost folder) or there is no start script. Ask the AI to fix the structure: static web needs index.html at the root, Python needs app.py + requirements.txt, Node needs package.json with a "start" script that reads process.env.PORT and listens on 0.0.0.0.
"Your Python/Node app quota is full" → delete one old app you no longer use via the web dashboard first, then try again.

Storing data that needs to persist (databases, user uploads, etc.)

If the app stores its own data (e.g. a payroll database, user uploads, input results) and that data must remain even when the app is later updated via update_app, store everything in the ./data/ folder at the project root (relative to the folder where package.json/app.py/index.html is located). That folder is the only part of the app that is NOT replaced when the code is updated — other parts (code, node_modules, etc.) are fully replaced on every successful submit_app/update_app.

If the project already has real data in the ./data/ folder when first uploaded (e.g. a colleague moved an app that was already in use from their own laptop, complete with its contents) — that data is carried along and remains on the server from the start, no need to move it manually again.

Automatically excluded when packaging the ZIP

node_modules, .git, __pycache__, .venv/venv, .DS_Store, .next, .cache. To exclude others, create a .bedenganignore file at the root of the project folder — one relative folder/file name per line (not full globs like .gitignore, just the exact name).

If the token leaks

Revoke it yourself via the web dashboard (the "API Token" button → "Revoke API Token") or ask the admin to revoke it from the admin panel — login passwords and web sessions are not affected. Create a new token, run npm run init again.

Available Tools

5 tools

check_statusCek status pengajuanA

Lihat status sebuah pengajuan (menunggu/disetujui/ditolak) dan progres build-nya kalau sudah disetujui.

ParametersJSON Schema

Name	Required	Description	Default
`requestId`	Yes	ID pengajuan, didapat dari balasan submit_app.

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the behavioral burden. It discloses that the tool is a read-only status lookup, enumerates the possible statuses, and notes the conditional build-progress behavior for approved requests. This is adequate for a low-risk check operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One concise, front-loaded sentence with no filler. Every part adds useful information: what is checked, the possible statuses, and the conditional progress detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter status-check tool, the description covers the core behavior and expected result categories. There is no output schema, but the description's mention of statuses and build progress provides sufficient guidance for an agent to call and interpret the tool without missing critical context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the single parameter requestId is already documented as coming from submit_app's reply. The tool description adds no additional parameter-level meaning, so the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Lihat') and resource ('sebuah pengajuan'), and clarifies the exact scope: status values (menunggu/disetujui/ditolak) plus build progress when approved. This clearly separates it from sibling tools like submit_app or update_app, which are about creating or modifying submissions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The tool is clearly positioned as the status lookup after a submission exists, and the requestId parameter description says it comes from submit_app's reply. It does not explicitly name alternatives or exclusions, but the context is clear enough for an agent to know when to call it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_my_appsDaftar aplikasi & pengajuan sayaA

Lihat semua aplikasi yang sudah tayang dan pengajuan yang masih berjalan milik akun ini.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden of behavioral disclosure. 'Lihat' signals a read-only listing and the status qualifiers ('sudah tayang', 'masih berjalan') add filter semantics. However, it does not mention pagination, sorting, authorization, or what happens when there are no results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence with no filler. Every phrase adds scope or status information, and the list-like structure matches the tool's purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple zero-parameter design and no output schema, the description sufficiently states what the tool returns conceptually: the account's published apps and ongoing submissions. It could be more complete by noting read-only guarantees or result set behavior, but nothing critical is missing for basic invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and schema coverage is 100%, so there are no parameter semantics to document. The baseline for a zero-parameter tool is 4, and the description does not need to compensate for any schema gaps.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Lihat' (view) and names the resource precisely: all published apps ('aplikasi yang sudah tayang') and ongoing submissions ('pengajuan yang masih berjalan') belonging to the current account. This separates it from the sibling tools, which validate, submit, check status, or update rather than list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly implies the appropriate context: use when the agent needs an overview of the current account's published apps and in-progress submissions. It does not explicitly name sibling alternatives or exclusions, so it stops short of full routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

submit_appTerbitkan aplikasi baru ke Bedengan App HubA

Panggil validate_project LEBIH DULU dan pastikan hasilnya "ok": true. Kirim folder proyek lokal sebagai aplikasi BARU. Tidak ada admin yang meninjau lagi -- kalau lolos pemeriksaan (struktur & pemindaian rahasia), aplikasinya LANGSUNG LIVE di subdomain yang diminta dalam beberapa saat, bukan menunggu persetujuan. Kalau ditolak, pesan errornya selalu menyebutkan apa yang harus diperbaiki -- perbaiki lalu panggil validate_project lagi sebelum mencoba submit_app lagi. Untuk aplikasi yang SUDAH live sebelumnya, pakai update_app, BUKAN submit_app lagi (subdomain yang sudah dipakai akan ditolak).

ParametersJSON Schema

Name	Required	Description
`name`	Yes	Nama aplikasi.
`path`	Yes	Folder proyek lokal, path absolut.
`notes`	No	Catatan tambahan, opsional (tidak dibaca admin -- tidak ada lagi).
`subdomain`	Yes	Subdomain yang diinginkan (huruf kecil, angka, tanda hubung saja), mis. "kalkulator-tenda".
`department`	No	Departemen/tim pengaju, opsional.

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It reveals that publication is immediate with no admin review, that apps pass through structure and secret scanning, that rejection errors always explain what to fix, and that duplicate subdomains are rejected. It does not mention authentication or the exact success response, but the core behavior is clearly disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Every sentence earns its place: the first gives the prerequisite, the second clarifies new-app-only submission, the third explains rejection handling, and the fourth distinguishes update_app. There is no filler, and the information is logically ordered.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 5 parameters, no output schema, and no annotations, this description covers the prerequisite, validation flow, immediate publication behavior, error recovery, and sibling distinction. The main gap is that it does not describe what a successful submit_app call returns, which would be useful given there is no output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides 100% parameter description coverage, so the baseline is 3. The description adds some contextual meaning—such as treating 'path' as the local project folder and 'subdomain' as the requested, unused subdomain—but it does not substantially improve on the schema's parameter explanations.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that submit_app publishes a new local project as a brand-new app to Bedengan App Hub, using a specific verb and resource. It also distinguishes itself from update_app by explicitly saying already-live apps must use update_app instead, so there is no confusion with siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit usage guidance: call validate_project first and ensure its result is 'ok': true, use submit_app only for new apps, and use update_app for apps that are already live. It also warns that an already-used subdomain will be rejected, preventing an obvious misuse.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

update_appPerbarui aplikasi yang sudah liveA

Panggil validate_project LEBIH DULU dan pastikan hasilnya "ok": true. Timpa aplikasi yang SUDAH live milik akun ini sendiri dengan kode terbaru di folder lokal. Lolos pemeriksaan = LANGSUNG live menggantikan versi lama, tanpa siapa pun meninjau. Versi lama otomatis tersimpan (bisa dikembalikan lewat dashboard web kalau versi baru ternyata bermasalah). Dapatkan appId dari list_my_apps.

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes	Folder proyek lokal, path absolut.
`appId`	Yes	ID aplikasi yang akan diperbarui, didapat dari list_my_apps.

TDQS

A4.3/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

There are no annotations, so the description carries the full disclosure burden. It reveals that passing validation immediately replaces the live version with no review, that the old version is automatically saved, and that rollback is possible via the web dashboard. This gives the agent a clear picture of the destructive yet recoverable behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the mandatory prerequisite, then states the core action, and then explains the deployment and rollback consequences. Every sentence contributes useful information, though the phrasing is slightly dense.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter tool with no output schema, the description covers the required prerequisite, the effect, and the recovery path. It does not describe the return value of update_app itself, but that is not essential for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with both path and appId already described. The description reinforces that appId comes from list_my_apps and that path refers to the local folder, but it adds no substantially new semantic detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: it overwrites an already-live app owned by this account with new code from a local folder. It clearly distinguishes this from a new submission by emphasizing 'SUDAH live' and by tying prerequisites to validate_project and list_my_apps.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly instructs that validate_project must be called first and its result must be 'ok': true, and that appId comes from list_my_apps. It does not explicitly name submit_app as an alternative or state when not to use this tool, but the 'already live' scope strongly implies the boundary.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

validate_projectValidasi proyek Bedengan AppsA

WAJIB dipanggil LEBIH DULU, setiap kali, sebelum submit_app atau update_app -- tidak ada admin yang meninjau lagi, jadi ini satu-satunya kesempatan menangkap kesalahan sebelum aplikasinya live. Bungkus folder proyek lokal jadi ZIP dan validasi lewat Bedengan App Hub, TANPA mengajukan apa pun (tidak masuk antrean, tidak tercatat di database). Balasannya berisi jenis aplikasi yang terdeteksi (static/python/node/spa), peringatan struktur (mis. node_modules ikut ter-zip -- boleh diabaikan), dan "kesalahan" keras (mis. .env atau pola rahasia ikut ter-zip, entry point tidak ditemukan -- ini yang akan membuat submit_app/update_app DITOLAK). Kalau ada "kesalahan", perbaiki HANYA hal yang disebutkan di proyek lokal (jangan mengubah bagian lain yang tidak terkait), panggil tool ini lagi sampai "ok": true, baru lanjut ke submit_app/update_app.

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes	Folder proyek lokal, path absolut.

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden and does it well. It discloses that the tool does not submit, queue, or record anything, and it describes the response contents: detected app type, ignorable warnings, and hard errors that cause rejection. It also clarifies the consequences of errors on later submit/update calls.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Although the description is long, every sentence earns its place: mandatory call order, side-effect transparency, response schema, error handling, and the retry loop. The critical instruction is front-loaded ('WAJIB dipanggil LEBIH DULU'), and examples are used efficiently to clarify warning versus error severity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given there is no output schema, the description compensates by describing exactly what the response will contain and how to interpret it. It also explains the tool's non-mutating behavior, the consequences of hard errors, and the exact follow-up path. Nothing essential for correctly invoking and acting on this tool is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already fully describes the only parameter, `path`, as an absolute local project folder path. The description adds context that this folder will be zipped and validated, but it does not introduce new parameter-specific constraints or format details. Baseline 3 is appropriate given 100% schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action: zip a local project folder and validate it through Bedengan App Hub without submitting anything. It also clearly distinguishes this from submit_app/update_app by saying it never queues or records anything, so the agent knows exactly what the tool is for.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly mandates when to use the tool: always before submit_app or update_app, and even explains why ('tidak ada admin yang meninjau lagi'). It also gives the retry workflow: fix only mentioned issues, revalidate until 'ok': true, only then proceed. This is strong, actionable usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

5 tool updatesv0.1.0Aug 28, 2026
- First observedcheck_status
- First observedlist_my_apps
- First observedsubmit_app
- First observedupdate_app
- First observedvalidate_project

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.4/5.0

Scored 2026-08-28 01:05 across 5 tools

Disambiguation4/5

Each tool has a reasonably distinct role: validation, creation, updating, status lookup, and listing. The only mild overlap is between check_status and list_my_apps, since both expose submission/app state, but one is single-item-oriented and the other is an overview.

Naming Consistency5/5

Tool names consistently follow a verb_noun pattern: validate_project, submit_app, check_status, update_app, list_my_apps. The style is uniform and predictable, making it easy to anticipate what each tool does.

Tool Count5/5

Five tools is well-scoped for an app deployment workflow: validate, create, update, check status, and list apps. Each tool earns its place and there is no unnecessary redundancy or bloat.

Completeness4/5

The core lifecycle is covered: validate before deploy, submit new apps, update existing apps, check status, and list owned apps. A delete or rollback tool is missing, but rollback is explicitly handled through the web dashboard, so the gap is minor.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Air Pipe B
io.airpipe
Build, validate, deploy — HTTP APIs, cron jobs, webhooks and MCP tools — from your AI client.
Developer Tools CI/CD & DevOps App Automation
191
YekuOAuth
dev.yeku
deploy the software your AI builds you
CI/CD & DevOps Developer Tools
1
MeroFoundryOAuth
com.merofoundry
Build and publish full-stack apps from your coding agent: models, rules, pages, auth, per-app MCP.
Coding Agents Developer Tools
1
JustDeployOAuth
ai.justdeploy
Deploy and manage your apps, databases, storage, and scheduled jobs from your AI agent
Cloud Platforms CI/CD & DevOps App Automation
2

Related MCP Servers

golive-mcp
CI/CD & DevOps Version Control
abbylester1
A
license
Not graded
quality
A
maintenance
Enables AI agents to deploy code to any hosting provider by creating PRs, building, and verifying health checks, all from a single natural language command.
Updated 23 days ago (2026-08-28 13:40 UTC)
1
MIT
Deploy MCP
CI/CD & DevOps Cloud Platforms Developer Tools
Tusharjain-19
A
license
Not graded
quality
B
maintenance
Enables AI coding assistants to deploy websites directly to Vercel from the IDE, automating framework detection, build validation, and secure environment variable synchronization, with live status updates.
Updated 13 days ago (2026-09-07 04:55 UTC)
1
MIT
@betadrop/mcpofficial
CI/CD & DevOps Developer Tools Testing & QA Tools
betadrop-app
A
license
A
quality
A
maintenance
Enables AI coding assistants to distribute iOS and Android builds to BetaDrop testers, manage share links, track releases, and manage API tokens entirely through natural language prompts.
Updated 9 days ago (2026-09-11 07:27 UTC)
11
421 npm
MIT
Somewhere MCP
Developer Tools Cloud Platforms Agent Orchestration
Somewhere-Tech
A
license
Not graded
quality
B
maintenance
Enables AI assistants to build, deploy, and inspect apps through a hosted backend service, including reading platform docs, deploying raw source, inspecting logs, verifying live pages in browsers, and managing project tasks.
Updated 5 days ago (2026-09-15 15:41 UTC)
MIT

Bedengan Apps MCP

Install once on your laptop

Connect to Antigravity

What happens when you ask to "upload this folder"

Available tools

If rejected

Storing data that needs to persist (databases, user uploads, etc.)

Automatically excluded when packaging the ZIP

If the token leaks

Available Tools

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

@betadrop/mcpofficial