Your land, seen from space. Your sites, seen by your cameras. Your work, seen through your crews
This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
This server may ask you to sign in when your AI client connects.
Last probed Nov 3, 2026 · api.machinevision.cloud
30tools discovered
For AI agents — MCPBundles Directory API
For MCP client apps (human connect):
MCP connect URL: https://api.machinevision.cloud/mcp
Skill page: https://www.mcpbundles.com/skills/machinevision-mcp-94cdd39091
Explore capabilities (30)
read 11
write 4
other 10
Showing 25 of 30
Showing 25 of 30 tools from the public preview. Connect the server to inspect the full live tool list.
List7
Create4
Get4
Add2
Set2
Other capabilities6
List Templates
read
list_templates
Browse the template gallery: six ready-made vision task definitions (content moderation, product segmentation, receipt OCR, defect inspection, catalog QA, listing pipeline). No auth required.
List Templates — Browse the template gallery: six ready-made vision task definitions (content moderation, product segmentation, receipt OCR, defect inspection, catalog QA, listing pipeline). No auth required.
Create Task From Template — Instantiate a gallery template as a runnable task in your workspace.
List Tasks — List the vision tasks defined in your workspace.
Get Task — Fetch one task definition, including its instruction and inference config.
Create Task — Define a new vision task in natural language. task_type is one of: visual_inspection, anomaly_detection, object_detection, segmentation, classification, ocr, visual_qa, pose_estimation, measurement.
Inspect Image — Run a task against an image URL and get the structured result (verdict, regions, classes, text, or segments depending on the task type). Pass idempotency_key to make retries safe.
List Contexts — List visual contexts (curated reference-image sets that lift task accuracy).
Add Context Item — Add a labeled reference image to a visual context. This is how accuracy is tuned: no retraining, just curated examples.
Get Usage — Monthly usage and remaining free tier for the authenticated workspace.
Create Eval Set — Create an eval set for a task: a labeled collection of images with expected results, used to regression-test instruction changes.
Add Eval Item — Add an image with an expected result to an eval set. Set only the expectations you care about: expected_verdict, expected_class, full_text_contains, min/max_regions.
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
What is the machinevision.cloud — Agentic visual monitoring MCP server?
Your land, seen from space. Your sites, seen by your cameras. Your work, seen through your crews
How do I connect machinevision.cloud — Agentic visual monitoring to my AI agent?
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
Operate this server?
Request removal if you do not want machinevision.cloud — Agentic visual monitoring listed here, or claim the listing if you want to manage it on MCPBundles.
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms · Request removal
More in developer tools
Other MCP servers in this category from the directory index
Evaluate Task — Run a task against an eval set (async). Returns a running report; poll get_evaluation for accuracy, per-item diffs, cost and latency.
Get Evaluation — Fetch an evaluation report by eval_run_id (status, accuracy, per-item mismatches).
Generate Context Items — Data Studio: generate synthetic reference images from a prompt (optionally editing a seed item) into a visual context. Asynchronous: returns a generation job (202) — poll get_generation until completed. Items arrive as needs_review with full provenance.
Get Generation — Poll a Data Studio generation job (status, created item ids, usage).
Set Webhook Action — Give a task an outbound webhook action (replaces its action list with this one). Payloads are HMAC-signed: X-MVC-Signature = 'sha256=' + HMAC_SHA256(secret, '{X-MVC-Timestamp}.{raw_body}'). The generated secret is in the returned task's actions[0].secret.
Set Review Policy — Route uncertain or failing results to the human review queue: on_fail flags FAILs, confidence_below flags results whose lowest confidence is under the threshold.
List Reviews — List open review cases (results flagged by review policies, waiting on a human).
Resolve Review — Resolve a review case: decision 'approve' confirms the agent's verdict; 'override' corrects it (corrected_verdict required, e.g. PASS).
Save Review Example — Save a resolved review's image as a labeled training example in a visual context — the flywheel: the agent learns from the correction.
List Deliveries — List a task's webhook delivery attempts (status codes, timestamps, target URLs).
Submit To Inbox — Queue an image for unattended processing (202): results flow to the task's webhook actions and review queue instead of the response. Accepts camera-style source metadata.
List Inbox — List a task's inbox submissions with status, verdict, and per-step trace.
Create Source — Register a source (where images come from) on an agent. kind 'capture_endpoint' returns a public white-label phone-capture URL; 'camera' binds inbox pushes whose source.source_id matches camera.source_key (or polls camera.snapshot_url on an interval); 'satellite_aoi' watches satellite.bbox daily. The free tier includes one source; more require a card (402 CARD_REQUIRED).
List Sources — List registered sources with health (waiting/watching/ok/silent), observation counts, and capture URLs.
Showing the first 25 tools — full list and schemas: Directory API.
How many tools does machinevision.cloud — Agentic visual monitoring provide?
MCPBundles probed 30 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
What authentication does machinevision.cloud — Agentic visual monitoring require?
machinevision.cloud — Agentic visual monitoring may require signing in to the provider before tools can run. Connect through MCPBundles or your MCP client and complete any provider login when prompted.
Don't want this listed?
Request removal from the MCPBundles directory. We stop publishing this listing on mcpbundles.com.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.