"OCR agent" matching MCP servers:

MCP server for Agent Room, enabling AI agents to join shared meeting rooms and collaborate with humans via tools like room_listen and room_task_*.

A dual-mode MCP server for integrating Feishu/Lark project management, enabling task CRUD, advanced filtering, and seamless integration with AI assistants and automation workflows.

Enables Claude to interact with Jira, Salesforce, and n8n through MCP tools, allowing automated reading of Jira stories, deploying Salesforce metadata, and triggering n8n workflows.

Enables AI coding agents to coordinate through a local, pull-only message board by registering sessions, posting updates, proposing and accepting tasks, holding leases, and reading or acknowledging updates under scoped human authorization.

MCP server that connects AI assistants to Instructure Canvas LMS, enabling teachers and administrators to manage courses, assignments, grades, and more through natural language.

Exposes GitHub issue and pull-request triage capabilities to any MCP client: fetching repository context, classifying and prioritizing requests, finding duplicates, and applying labels, comments, assignments, closures, or reopenings. All writes are policy-gated, dry-run by default, and destructive actions require explicit two-step human confirmation.

Provides tools for managing tasks, searching docs, and running a heuristic quality gate to check agent output for common issues before human review.

An MCP server that connects AI assistants to Notion, enabling automated research, GitHub tracking, and content pipelines with human-in-the-loop approval via a Notion task queue.

A Model Context Protocol server for AI agents to manage tasks and track progress across projects, with features like project isolation, search, and reporting.

Analyze GitHub repositories with health scores, issue triage, and action items through MCP tools.

MCP server that enables AI agents to manage Dida365/TickTick tasks, projects, tags, and habits through natural language, with full CRUD, search, and advanced V2 capabilities.

Experimental MCP server for coordinating CLI agents across projects using file-based task boards and assignment tracking.

Enables AI agents to create and manage small project plans—including tasks, assignees, status, progress, dates, and dependencies—and retrieve Gantt-friendly project views over MCP stdio. State is stored in SQLite without external dependencies.

Enables AI agents to manage Dida365 tasks via natural language with a rule engine for automatic project routing, priority assignment, and label management.

Connect an AI agent to your OKRs. FlowyTeam exposes 33 MCP tools covering OKR objectives, key results, KPI indicators and performance cycles, alongside tasks, projects, HR, attendance, tickets and CRM — one hosted connection for the whole workspace. Supports Claude Desktop, Claude web and mobile, ChatGPT (OAuth 2.0 + PKCE), and Claude Code / n8n (Bearer token). Tools respect the caller's existing

AI agent can manage Redmine tickets and projects via MCP tools.

Enables AI agents to coordinate open projects by registering, creating and claiming tasks, submitting and reviewing work, electing coordinators, and chatting in a shared lobby.

Enables software agents to self-register, publish and read structured notes, questions, tasks, and results in public namespaces, and coordinate work via versioned task claims, replies, and incremental change synchronization over MCP.

Enables agentic CLIs to start, manage, and resolve structured mediations between product managers and architects, following a protocol to separate positions from interests and produce auditable recommendations.

Attaches a file-based kanban workflow to any project, allowing agents to create, claim, complete, and block work items using git as the locking mechanism.