"Information about cursors (general use or specific context)" matching MCP servers:

Enables an agent to process local video files and then read, search and inspect the results: timestamped transcripts, on-screen text and key frames as images. Everything runs locally, so an agent can answer questions like how to perform a task shown in a screencast or meeting recording.

Local MCP server for Gateway-managed computer use that exposes computer.* tools with desktop control, OCR, and user-visible safety overlays.

Give your AI assistant eyes and ears — analyze any video, audio, or image, entirely on your machine.

MCP server that gives AI chat real vision by reading images, files, logs, and zip archives via local OCR in any language, with privacy-first processing.

A self-hosted MCP server that enables AI agents to see and control a Windows PC through screenshots, built-in Arabic/English OCR, mouse, keyboard, clipboard, and application launching, with code-enforced consent and audit logging.

Compress OCR-heavy PDFs into dense packed images so agents can work with long visual documents.

Enables Codex to run image generation and inspection as durable, resumable local jobs whose media bytes stay behind the MCP boundary. Returns only bounded text handoffs, hashes, relative references, and Job IDs, optionally using an offline mock or the OpenAI Image/Responses APIs.

Enables Codex image generation and inspection workflows to run as durable local jobs while keeping provider media bytes outside the public MCP boundary and returning only bounded text handoffs, hashes, relative references, and Job IDs. It supports idempotent submission, restart recovery, an offline mock provider, and optional OpenAI-backed generation or inspection with artifacts written to configured workspace paths.

Enables Codex to run durable, context-bounded image generation and inspection jobs through local MCP tools, returning compact text results, hashes, relative references, and Job IDs instead of media bytes.

Enables text-only coding models to read images, PDFs, presentations, spreadsheets, and other non-text files through a single analyze_media tool, combining local document extraction, OCR, and optional vision models with clear evidence labeling.

Enables Codex to run context-bounded image generation and inspection as durable local jobs, returning bounded text handoffs, hashes, relative references, and Job IDs while keeping provider-returned media bytes outside the MCP boundary.

A durable local MCP server that runs image generation and inspection as persisted jobs, keeping provider-returned media bytes behind the MCP boundary while returning only bounded text handoffs, hashes, relative references, and Job IDs. This keeps image-heavy Codex workflows context-bounded, idempotent, and resumable, with offline mock or optional OpenAI providers.

Enables Codex to run durable, context-bounded image generation and inspection jobs that return only bounded text handoffs, hashes, relative references, and Job IDs instead of media bytes. Supports idempotent submission, restart reconciliation, and optional OpenAI-backed generation and inspection.

Runs image generation and inspection as durable, idempotent local jobs that Codex submits and polls by Job ID, keeping provider-returned media bytes behind the MCP boundary. Returns only bounded text handoffs, hashes, and relative artifact references so image-heavy Codex workflows stay responsive, resumable, and context-bounded.

Enables Codex to run image generation and inspection as durable, resumable local jobs whose provider-returned media bytes stay behind the MCP boundary. Callers receive only bounded text handoffs, hashes, relative references, and Job IDs instead of pixels, keeping image-heavy workflows context-bounded.

Enables Codex to run context-bounded image generation and inspection as durable local jobs, returning only bounded text handoffs, hashes, relative references, and job IDs while keeping media bytes behind the MCP boundary.

Enables Codex to run image generation and inspection as durable, idempotent local jobs that return only bounded text handoffs, hashes, relative references, and Job IDs while keeping provider media bytes behind the MCP boundary. This keeps image-heavy workflows context-bounded, restart-safe, and resumable across multiple concurrent Codex tasks.

Enables Codex to run image generation and inspection as durable, context-bounded local jobs, returning only bounded text handoffs, hashes, relative references, and Job IDs while keeping provider media bytes outside the public MCP boundary.

Runs image generation and inspection as durable, idempotent local jobs through bounded MCP tools, so Codex can create and analyze image-heavy assets without media bytes entering the task context. Returns only compact text handoffs, hashes, relative references, and Job IDs, with offline mock or opt-in OpenAI providers.

Enables Codex to run image generation and inspection as durable, resumable local jobs while keeping provider-returned media bytes outside the MCP boundary. Returns only bounded text handoffs, hashes, relative artifact references, and Job IDs so image-heavy workflows stay context-bounded.

Enables Codex to run context-bounded image generation and inspection as durable local jobs, returning only bounded text handoffs, hashes, relative references, and Job IDs while keeping media bytes outside the task context.

Enables Codex workflows to submit context-bounded image generation and inspection as durable local jobs, keeping provider-returned media bytes outside the MCP result boundary and returning only bounded text handoffs, hashes, relative references, and Job IDs.

Enables Codex to run image generation and inspection as durable, restart-safe local jobs while keeping provider-returned media behind the tool boundary, returning only bounded text handoffs, hashes, relative artifact references, and Job IDs. This keeps image-heavy workflows context-bounded, resumable, and free of image bytes or base64 data in the public results.

Enables Codex to run image generation and inspection as persisted local jobs, returning bounded text results, hashes, relative references, and Job IDs while keeping provider-returned media bytes out of public MCP results. It also supports idempotent submission, restart reconciliation, and optional OpenAI-backed generation or inspection.

Enables detection of AI-generated content in images, videos, audio, and text via the AI or Not API. Supports media analysis tools for deepfakes, synthetic voices, and AI-written text.

This MCP server enables Codex to run image generation and inspection as durable local jobs, returning bounded text handoffs, hashes, relative references, and job IDs instead of media bytes.

Enables LLM clients to access crop yield predictions from RGB imagery, topic-based PDF literature, and soil lab/moisture CSV data.

Lets Codex run image generation and inspection as persisted local jobs while keeping provider-returned media out of public MCP results and returning only compact text handoffs, hashes, references, and Job IDs.

Enables Codex to run image generation and inspection as durable local jobs while returning only bounded text handoffs, hashes, relative references, and Job IDs instead of media bytes.

Enables users to run context-bounded image generation and inspection as durable local jobs that return bounded text handoffs, hashes, relative references, and Job IDs instead of media bytes.