Version 1.0 · changeable at any time from the footer.
MCP server
Ask for a gallery review, a workflow readout or a fresh set of images in Claude, Cursor or Claude Code. Beemm Vision answers with cards you can act on — and every credit is decided by the server, never by the assistant.
The remote connector you add on claude.ai in one click reads projects, workflows, models, balance, jobs and gallery, and generates images and video. Generating spends your credits, capped at 200 images and 50 clips a day, and 20 in any ten minutes so a looping agent cannot run away with them.
The local server adds what the remote one leaves out: image editing, batches and workflow runs. It spends credits — always at the amount the server quotes first. Local install is open to early-access teams.
Paste the address. Sign in when your client asks. That is the whole setup.
https://app.beemmvision.com/mcp
Gallery, workflows, models, balance, job status — and image and video generation.
Copy one, paste it into your agent. Each one works with the connector as it ships today.
Generate an image in my Beemm Vision project “<name>”: <subject>, in <style>. Tell me what it will cost, start it, and give me the job id.
Show me my 8 latest Beemm Vision generations as a grid, then tell me which project each one belongs to and what it cost.
List my Beemm Vision workflows in project “<name>”, open the most recently updated one, and explain node by node what it does and which models it calls.
Check my Beemm Vision balance, list my last 10 jobs and runs, and summarise what consumed credits, grouped by model.
Plan four variants of “<subject>” on four different image models in one batch, show me the cost first, then generate them.
Take the image I just generated and animate it — 6 seconds, 720p — after showing me exactly what it will cost.
Duplicate my workflow “<name>”, add an upscale node after the last image node, connect it, and run it.
Generated from the server itself, so this table cannot drift from what actually runs.
| Tool | What it does | Where | Credits |
|---|---|---|---|
| beemm_whoami | Reports which Beemm Vision account this MCP server is acting as, when that session expires, whether it carries an App Check attestation (required by most backend endpoints), and which backend it talks to. | claude.ai + local | free |
| beemm_login | Signs the user in again WITHOUT a terminal. | local only | free |
| beemm_selftest | Runs the full Beemm Vision chain end to end in one call — credential, session expiry, which backend is configured and why, a real read against that backend, and whether any data is actually readable — and returns one line per check with the cause AND the remedy for anything that failed. | claude.ai + local | free |
| beemm_list_projects | Lists the Beemm Vision projects you can access, most recently updated first, each labelled PERSONAL or ORGANISATION. | claude.ai + local | free |
| beemm_list_workflows | Lists the workflows of one project, most recently updated first. | claude.ai + local | free |
| beemm_get_workflow | Returns a workflow's nodes and edges, PROJECTED AND BOUNDED so it fits in context: per node its id, type, label and position; per input its key, value type, whether it is fed by an edge or typed in, and a ~200-character preview. | claude.ai + local | free |
| beemm_get_balance | Returns your PERSONAL credit balance. | claude.ai + local | free |
| beemm_list_models | Lists the image and video models this account can actually run, with what each one supports: aspect ratios, resolutions, durations, whether it takes input images, whether it can generate audio. | claude.ai + local | free |
| beemm_list_node_types | Lists every node type a workflow can hold, with what beemm_patch_workflow will accept for each: its category, its input handles (the toHandle an edge can reach) and output handles (the fromHandle an edge can leave from), its input keys with their default values, and its default size. | claude.ai + local | free |
| beemm_generate_workflow | Asks Samy, the Beemm Vision agent, to design a node workflow from a plain-language intent. | local only | spends |
| beemm_plan_generationrenders a card | Shows the user a card with the exact image request — prompt, model, aspect ratio, resolution, reference images — and a button that starts it. | claude.ai + local | free |
| beemm_plan_batchrenders a card | Shows the user ONE card listing up to 24 image requests — each with its prompt, model, aspect ratio, resolution and reference images — the total the backend would charge, and a single button that starts them all. | local only | free |
| beemm_generate_imagerenders a card | Generates an image and, by default, waits for it and returns the URL in the same call. | claude.ai + local | spends |
| beemm_generate_image_batchrenders a card | Generates up to 24 images in ONE call — typically the same prompt across different models, or several variations of one idea — and, by default, waits for all of them. | local only | spends |
| beemm_generate_videorenders a card | Generates a video clip and, by default, waits for it and returns the URL in the same call. | claude.ai + local | spends |
| beemm_check_jobrenders a card | Follows ONE generation job, identified by a job id you already have: status, the credits the SERVER charged, and — once finished — the media URL. | claude.ai + local | free |
| beemm_check_jobsrenders a card | Re-reads SEVERAL generation jobs of one batch in a single call and answers in the batch shape (one entry per job, in the order given, plus the total the server charged so far). | claude.ai + local | free |
| beemm_wait_for_jobrenders a card | Polls ONE generation job, identified by a job id you already have, until it finishes — with backoff and a HARD 240-second ceiling. | local only | free |
| beemm_list_jobs | Lists your most recent generation jobs and workflow runs, newest first, with their ids and statuses. | claude.ai + local | free |
| beemm_list_galleryrenders a card | SHOWS the media an account already holds, as a single GRID of thumbnails, newest first, with their URLs. | claude.ai + local | free |
| beemm_run_workflow | Executes an existing workflow on the server and returns immediately with a run id. | local only | spends |
| beemm_get_run | Reads a workflow run: its status, how many nodes are done, the credits the SERVER charged, and the output of each finished node (media URL, or text). | claude.ai + local | free |
| beemm_wait_for_run | Polls a workflow run until it finishes, with backoff and a HARD 300-second ceiling. | local only | free |
| beemm_create_workflow | Creates a NEW, EMPTY workflow — no nodes, no edges — ready for beemm_patch_workflow to build a graph in. | claude.ai + local | writes |
| beemm_duplicate_workflow | Copies an existing workflow into a NEW project of its own — one workflow per project is the app's model, so the copy gets its own card on the Workflows page, with workflow id "default". | claude.ai + local | writes |
| beemm_patch_workflow | Edits a saved workflow: add, update and remove nodes, connect and disconnect them. | claude.ai + local | writes |
| beemm_upload_asset | Turns a local file into a URL the generation backend can fetch, for use as a reference image or any other asset input. | local only | free |
| beemm_upscale_image | Enlarges an image 2× or 4×, keeping the framing. | local only | spends |
| beemm_remove_background | Removes the background and returns a PNG with real transparency, at the source resolution. | local only | spends |
| beemm_inpaint_image | Changes ONLY the area a mask marks, and leaves the rest of the pixels alone. | local only | spends |
| beemm_expand_image | Keeps the picture at its exact size and paints NEW surroundings around it — the way to turn a portrait crop into a banner without stretching or cropping anything. | local only | spends |
| beemm_open_in_agent | Opens a workflow in YOUR OWN browser tab, signed in as the user, with the page's live tools armed — what the « Open in agent » button does in the web app, without the user clicking. | claude.ai + local | free |
32 tools · snapshot 2026-09-08
See also the model catalogue.