Dropl MCP vs MCP Server
A side-by-side look at the Dropl MCP and MCP Server MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Dropl MCP for multimedia process work as a local process; choose MCP Server for multimedia process as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Dropl MCP when
- You need dedicated capabilities in the Multimedia Process domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
DROPL_API_KEY. - You want tools like
whoami, list_sites, create_site.
Choose MCP Server when
- You need dedicated capabilities in the Multimedia Process domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You have the keys it needs:
WAVESPEED_API_KEY. - You want tools like
list_models, get_model_schema, run_model.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Multimedia Process | Multimedia Process |
| Quality signal | 61/100 · Good | 67/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | API key required |
| Pricing | Not declared | BYOK (pay the provider) |
| Required env vars | DROPL_API_KEY | WAVESPEED_API_KEY |
| Verified owner | Community listing | Community listing |
| GitHub stars | 1 | 34 |
| Directory activity | 1 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 38 | 11 |
| Full listing | View Dropl MCP | View MCP Server |
Tools & capabilities
Dropl MCP tools 38
whoamiShows the connected Dropl account, user, role, and API key (name, prefix, scopes, site restriction) plus the web app URL. Use it first in a session to confirm which account you're acting on, or when another tool reports a sign-in or permission error. Needs a saved sign-in or DROPL_API_KEY; it never returns the full key.list_sitesLists the client sites (one per client website) this connection can reach, with their domains and the plan's site allowance. Use it before creating anything, to find the site id for the client the user means and avoid duplicate sites. Keys restricted to some sites only see those sites.create_siteCreates a client site: the home for one client website's showcases, videos, collections, and feedback. Use it when the client has no site yet; check list_sites first to avoid duplicates. Only call after showing the plan to the user and getting explicit confirmation. Counts toward the plan's site allowance; safe to retry, since the same name and domain return the same site.list_showcasesLists a client site's showcases (embeddable photo and video galleries), newest first, with their type (gallery or projects) and item and project counts. Use it to reuse an existing gallery or portfolio instead of creating a duplicate, or to find a showcase id. Paged: pass nextCursor to get more.create_showcaseCreates a showcase: an embeddable photo/video gallery the client can update from their phone. Use it when the user wants a gallery, portfolio, project photos, or a section the client can update themselves. Requires a site id from list_sites or create_site. Only call after showing the plan to the user and getting explicit confirmation. Use type: "projects" for a portfolio where each project gets its own page, photos, and details (then create_project for each); the type can't change once the showcase has items. Turn on showCategoryFilters when items or projects will be grouped into categories. Safe to retry with the same arguments.get_showcaseSummarizes a showcase: type, settings, item counts by status (processing/ready/failed) and kind, project counts and details (projects showcases), categories with counts, photos without alt text, and failed items. Use it to check that an upload finished processing or to review a gallery before changing it. It returns counts, not items: use list_showcase_items for ids, alt text, and categories, or list_projects for projects.list_showcase_itemsPages through a showcase's items in display order: id, kind, status, file name, the local path it was uploaded from, alt text, and categories. Use it to find item ids for update_items or tag_items, or photos that still need alt text (missingAlt: true). Up to 200 items per call; local paths only appear for files uploaded from this machine.update_itemsSets alt text and adds/removes categories on many showcase items in one call. Use it after an upload to fix alt text or categories by id (files[].id from upload_photos / upload_videos, library video ids, or ids from list_showcase_items) instead of uploading again. Up to 1000 items per call; category names that don't exist yet are created. Alt text: Write concise, descriptive alt text: what the photo shows (e.g. "Cedar deck with glass railing at dusk"), without "image of" or "photo of". Leave it empty for purely decorative photos. Show the user the alt text you plan to write before saving a large batch.update_showcaseChanges a showcase's title, layout, grid fit, category filter tabs, or items per page. Use it when the user wants the gallery to look or page differently; embeds pick up the change without new code. Pass only the settings to change; at least one is required.create_categoryAdds a category (a filter tab) to a showcase. Use it to group items, e.g. one category per project type or source folder, before tagging them; upload and tagging tools also create missing categories by name. If one with the same name or slug exists, it's returned instead of creating a duplicate.tag_itemsAdds and/or removes the same categories on many showcase items (photos or videos) at once. Use it to put uploaded items into filter tabs, with itemIds from upload_photos / upload_videos (files[].id; library video ids work too) or list_showcase_items. Up to 1000 items per call; category names that don't exist yet are created. For per-item changes or alt text, use update_items.upload_photosUploads local photos (JPEG, PNG, WebP, AVIF, HEIC; up to 20 MB each) into a showcase, straight to storage. Use it to turn a folder of project photos into a client-editable gallery: pass files, folders (recursive by default), and globs via paths, and per-photo alt text and categories via files. Skips hidden files and validates file contents. Run with dryRun: true first and show the result to the user; Only call after showing the plan to the user and getting explicit confirmation. Resumable: re-running with the same arguments skips files already uploaded (and still applies changed alt text and categories). categoryFromFolder tags each photo with its top-level folder's name; categories tags every photo (both created if missing). In a projects showcase, pass project: the photos join the end of that project (categories belong to the project there, not to photos); the same file can go into several projects. Returns files: each local path with its showcase item id and status, for update_items and tag_items. Alt text: Write concise, descriptive alt text: what the photo shows (e.g. "Cedar deck with glass railing at dusk"), without "image of" or "photo of". Leave it empty for purely decorative photos.- +26 more on the listing page
MCP Server tools 11
list_modelsSearch the live WaveSpeed model catalog (image, video, audio, 3D). Returns model IDs usable with run_model. Do not invent model IDs — always pick one returned by this tool.get_model_schemaGet a model's real input schema (required fields, properties, defaults). Call this before run_model so inputs match what the model actually accepts.run_modelRun any WaveSpeed model. input keys come from get_model_schema; unknown keys are rejected before submission. Local files: pass "@./path" string values — they are uploaded and replaced with hosted URLs (bare paths are NOT uploaded). Returns the prediction id right away (done=false); call get_prediction with that id and wait_seconds until done=true to get the output URLs. The task keeps running on the server. Pass wait_seconds here to wait for a quick model in the same call.get_priceEstimate the cost of a run before executing it (no charge). Provide the same input you would pass to run_model — pricing often depends on inputs like duration or resolution, and a quote made without them can be lower than the real charge.get_balanceShow the WaveSpeed account credit balance, with the link to top up.list_predictionsList past predictions (run history), newest window first. Defaults to the last 24 hours; pass since/until (ISO or YYYY-MM-DD) for other ranges. Use get_prediction with an id for one task in full.list_billingsList itemized charges and refunds (billing records). Requires an API key with Billing access.get_usageUsage statistics: spend, request counts, daily series and per-model breakdown. Defaults to the last 7 days. Requires an API key with Billing access.delete_predictionsDelete finished predictions from this account's run history, up to 100 at a time. They stop appearing in list_predictions and get_prediction, and this tool cannot bring them back. Runs that are still going are left alone, and only the key's own organization's records are deleted. Ask the user first, and pass confirm: true only after they agreed to delete these ids.upload_fileUpload a local file to WaveSpeed and get its hosted URL (identical bytes reuse the same upload for 24h). Usually unnecessary — run_model handles "@./path" inputs itself.get_predictionFetch the status and outputs of a past or in-flight prediction by id — use to pick up a run that returned done=false. Pass wait_seconds to keep waiting for it to finish.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Dropl MCP
{
"mcpServers": {
"dropl-mcp": {
"command": "npx",
"args": [
"-y",
"@dropl/mcp"
],
"env": {
"DROPL_API_KEY": "YOUR_DROPL_API_KEY_HERE"
}
}
}
}
MCP Server
{
"mcpServers": {
"mcp-215": {
"command": "npx",
"args": [
"-y",
"fetch"
],
"env": {
"WAVESPEED_API_KEY": "YOUR_WAVESPEED_API_KEY_HERE"
}
}
}
}
Frequently asked questions
Dropl MCP is categorized under Multimedia Process and uses a local stdio subprocess. MCP Server belongs to Multimedia Process and uses a local stdio subprocess. Pick Dropl MCP for multimedia process work and MCP Server for multimedia process.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Dropl MCP has no declared pricing — check the project's own site. MCP Server is bring-your-own-key: usage is billed by the API provider you supply a key for. Auth: api key required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add dropl-mcp and mcp-215 as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Dropl MCP has a quality signal of 61/100 (Good) with 1 views, 0 installs and 1 GitHub stars. MCP Server has 67/100 (Great) with 1 views, 0 installs and 34 GitHub stars.