About Kompressr
Kompressr's MCP server lets agents upload files, monitor processing, list assets and create private delivery links. It also supports explicit permanent deletion, with access controlled by API key permissions.
Key features
- 01Upload files from paths or URLs
- 02Poll or wait for processing status
- 03List and filter project uploads
- 04Generate expiring private links
- 05Delete assets individually or in batches
Use cases
- 01Upload an asset and wait until it is ready
- 02Share a processed file through a private link
- 03Review project uploads by status or visibility
- 04Remove selected assets from a project
MCP support
The server exposes Kompressr file operations as MCP tools, including upload, status, listing, private-link generation and deletion. API key permissions govern actions; delete access is excluded by default for scoped keys.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
10Saved tool list · updated 4d ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| string | Yes | ||
| password | string | Yes |
Details
From the project README@kompressr/mcp-server
Kompressr tools for MCP agents: upload files, wait for processing, generate private links, paginate uploads and permanently delete explicit asset IDs. File operations use the separate @kompressr/sdk package. Applications can use that SDK directly without starting MCP.
Requires Node.js 22 or later. For a desktop client that supports MCPB extensions, download a Kompressr MCP bundle from GitHub Releases and follow the desktop installation guide.
Setup
Create a Kompressr account and start the 30-day image-upload trial or choose a paid plan. In Dashboard → Projects, open the project and choose API Keys. Keep project/master keys on trusted machines; use scoped keys for individual application or agent runtimes. The project UUID is needed only for listing uploads.
Configure an MCP client to run the package:
{
"mcpServers": {
"kompressr": {
"command": "npx",
"args": ["-y", "@kompressr/[email protected]"],
"env": {
"KOMPRESSR_API_KEY": "YOUR_PROJECT_OR_SCOPED_KEY",
"KOMPRESSR_PROJECT_ID": "YOUR_PROJECT_UUID"
}
}
}
}
KOMPRESSR_PROJECT_ID is required for upload listing; upload/status/signing/deletion need only the key. For source builds, follow CONTRIBUTING.md, then configure node with the absolute path to this package's built dist/index.js.
Configuration and migration
| Setting | Meaning |
|---|---|
KOMPRESSR_API_KEY | Opaque project/master or scoped key; API permissions remain authoritative |
KOMPRESSR_PROJECT_ID | Project UUID, required by list_assets |
KOMPRESSR_API_URL | Management origin, default https://kompressr.com |
KOMPRESSR_UPLOAD_BASE_URL | Upload-body origin override |
KOMPRESSR_REMOTE_ALLOWED_HOSTS | Comma-separated hostnames explicitly allowed to serve private/local remote-source addresses |
Production defaults to https://kompressr.com for management and https://uploads.kompressr.com for upload bodies. For another deployment, supply KOMPRESSR_API_URL and KOMPRESSR_UPLOAD_BASE_URL from private runtime configuration. Custom management origins use the same upload origin unless overridden. Origins must use HTTP(S) without credentials, paths, queries or fragments.
Saved configuration remains ~/.kompressr/config.json:
{
"api_key": "YOUR_KEY",
"project_id": "YOUR_PROJECT_UUID",
"api_url": "https://kompressr.com",
"upload_url": "https://uploads.kompressr.com"
}
Environment settings override saved values. A different environment key does not inherit the saved project or endpoint, which prevents mixing accounts; supply those explicitly for custom origins. A changed management origin re-derives uploads unless an upload override is provided. Old saved https://api.kompressr.com values migrate in memory to production. New saves use atomic replacement and permissions 0700 for the directory, 0600 for the file; existing files are not rewritten merely by loading. Keep keys and configuration out of source control.
File workflow
- Call
upload_assetwith exactly onefile_pathorfile_url. Save the returned numericasset_id. - Call
wait_for_assetorget_asset_status. Acceptance and a pending URL do not mean the file is ready; use the current processed response only for active assets. - Share a public processed URL, or authorize the private recipient in your app and call
generate_private_urlfor a fresh expiring link. - On wait timeout, resume with the saved ID. Do not upload again to recover from a polling timeout.
The 30-day free trial includes 100 image uploads total, shared across API, SDKs, MCP and dashboard. This allowance does not renew monthly. Formats, size, video quality and private delivery remain plan/project dependent. The SDK sends all multipart options before the file, as required by the streaming API.
Tools
Missing/blank filenames in historical status/list records remain valid; listing displays “Unnamed file” without changing response metadata.
All file tools return readable text, a JSON text block and structuredContent; failures set isError. Numeric IDs must be positive safe integers (single-ID tools also accept numeric strings).
| Tool | Parameters and behavior |
|---|---|
upload_asset | Exactly one file_path / file_url; optional quality (480p, 720p, 1080p, 4k), visibility (public/private), private_url_expires_in (60–604800 seconds), data (up to five scalar fields; keys 64/string values 512 UTF-8 bytes, encoded multipart JSON 4096 bytes). Returns acceptance and ready. |
get_asset_status | asset_id; processing, visibility, deletion state, byte sizes, savings and readiness. |
wait_for_asset | asset_id, optional timeout_ms (1–120000, default 120000); bounded polling. Timeout/error retains the ID. MCP request cancellation stops the wait, not the server job. Private readiness requires a fresh signing call. |
list_assets | Optional page (default 1), limit (1–100, default 20), visibility, external_id, status (pending, processing, processed, failed, unprocessable), deletion_status (active, deleting, deleted, legacy_deleted), string data filters. Lists uploads in the configured project and returns next_page. |
generate_private_url | asset_id, optional expires_in (60–604800 seconds, default 3600), variant (webp/avif, default webp). Application must first authorize access. Expiry does not delete the asset. |
get_asset_deletion_status | asset_id; processing/deletion state and recorded storage credits. Completed removal does not prove all caches are cleared. |
delete_asset | asset_id; permanent deletion, no undo/cancellation. Acceptance starts background cleanup. Requires deletion permission. |
bulk_delete_assets | asset_ids (1–100 explicit numeric IDs); per-item outcomes and counts. HTTP success can contain failed items. No delete-all selection. |
register | email, password (minimum 8 characters); creates an account and sends verification email. Refuses a configured runtime. |
verify_email | token; verifies email and saves credentials if issued. Refuses a configured runtime; never returns raw keys in tool output. Trial or paid-plan limits still apply. |
Processing status and deletion status are separate. Permanent deletion removes files later; cached, downloaded and offline copies may remain. Retrying the same old ID cannot delete a replacement with a new ID. Bulk deletion preserves partial failure and does not automatically expand or retry a selection. storage_credited_mb is recorded storage credit in MB, not a cash refund. Other size fields are bytes.
Read tools carry read-only annotations; deletion tools carry destructive annotations. Annotations describe behavior; server authorization and the MCP client's approval controls enforce access.
Keys, errors and remote files
Use a scoped key for one customer/agent runtime. The server enforces identity, allowed file types/visibility and action scopes. Default scopes exclude delete; provisioning must opt into it. Scoped keys cannot call platform administration or URL Prepend/source optimization. Provision identities and keys from your trusted backend with the SDK's client.platform group or the existing platform APIs. No master-key administration tools are added to MCP.
Safe GET requests retry network/429/502/503/504 failures at most twice within a 30-second request deadline and respect Retry-After. Uploads default to a 10-minute deadline; writes are never automatically replayed. Structured errors preserve code, kind, HTTP status and, where relevant, assetId/mayHaveSucceeded. A dispatched write interrupted or returning malformed JSON/data may have succeeded; inspect the outcome before repeating it. Arbitrary errors and raw gateway bodies are not exposed.
file_url downloads on the MCP machine, then uploads a local temporary file. MCP cancellation/disconnection, including stdin EOF, aborts the transfer and is checked again before starting the upload. Before dispatch no asset is created; after dispatch a server-accepted upload cannot be rolled back by client cancellation. It streams to disk with a 2 GiB transport ceiling, five-minute download deadline and at most five redirects. HTTPS cannot downgrade to HTTP. Numeric CIDR checks admit ordinary global IPv6 unicast and conservatively exclude IETF protocol, transition and documentation ranges, including their compressed forms. Each destination resolves to validated allowed addresses used for the connection; private/local destinations require exact hostnames in KOMPRESSR_REMOTE_ALLOWED_HOSTS. Redirect targets are checked again. Sources use no Kompressr credentials. Temporary files are restricted and cleaned up on success/failure. The transport ceiling does not override your plan or disk capacity; remote download and upload have separate deadlines. Server-side URL import is not part of this SDK/MCP integration.
See CHANGELOG.md and the contribution guide. Local HTTP/protocol checks do not certify deployed authentication, processing or CDN behavior. The source verification commands use local fixtures and do not publish packages.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.