"A database that can be operated or managed" matching MCP servers:

A JSON-based database MCP server with JWT authentication that enables user management, project tracking, department analysis, meeting management, and equipment tracking. Integrates with Claude Desktop to provide secure CRUD operations and analytics through natural language commands.

Enables AI assistants to perform QC Database tasks such as uploading records, managing project turnover packages, and signing off on inspections via natural language.

Project management and session memory for AI agents that provides 13 tools for tracking projects, tasks, and context during AI coding sessions.

MCP server for Redmine that enables interaction with issues, wiki pages, and time entries through natural language.

Enables task management through MCP tools, resources, and prompts, backed by a PostgreSQL database.

Connects Claude to Jobber to manage clients, jobs, invoices, quotes, and scheduling through natural language.

Enables AI assistants to manage Bitrix24 CRM entities, tasks, project kanban boards, and Scrum sprints through an incoming webhook, requiring explicit user confirmation for all write operations.

A personal task management MCP server that allows LLM clients to create, read, update, and delete tasks with projects, labels, and comments, using a local SQLite database that can also be accessed via a web UI.

Enables Boneyard to call authenticated, stateless Streamable HTTP tools for searching tickets and adding ticket comments, with caller context, attribution, and bounded results.

A shared, concurrency-safe ledger for LLM code audits. It enables multiple agents to collaboratively report, verify, and resolve bugs with deduplication and hallucination resistance.

A read-only Model Context Protocol server that connects MCP clients such as Claude Desktop, Claude Code, Cursor or VS Code to KanbanFlow, exposing the configured boards and the tasks assigned to a chosen person across all of them. It resolves board, column, swimlane, color, label and people ids to readable names, reports which boards or columns could not be fully loaded, and never modifies any board.

Local-first shared memory that several AI apps can use at once, with every change recording which app, model and machine made it.

An MCP server that lets Claude manage Google Tasks, including listing, creating, updating, completing, moving, and deleting tasks and task lists. It supports both local and remote deployments and can be used with Claude Desktop or as a Cloudflare Worker.

A Python MCP server that gives Claude access to PM workflow data such as sprints, roadmap, blockers, and workload, using synthetic fixture data (no API keys required) and can be forked for real Linear/Jira integration.

Enables trades and field service work to be tracked per job: logging labor hours at worker rates and materials used, keeping running totals in integer cents per currency, and moving each job through a status machine from open to invoiced or archived. It also produces daily or weekly summaries of hours and value, and renders a printable card with a signature line for client sign-off.

Enables AI agents to manage projects, roadmaps, periods, and tasks through MCP tools, backed by a local SQLite database with schema validation.

A read-only MCP server that bridges AI assistants to SAP Cloud ALM, exposing read APIs through four intent-based tools. It runs locally over stdio or remotely over Streamable HTTP, and can be deployed to SAP BTP Cloud Foundry.

Lets AI apps read a student's Google Classroom data, including active classes, to-do and missing assignments, upcoming due dates, grades on returned work, and announcements. It is read-only, so it can never turn in, edit, or delete anything.

Enables AI agents to read and change jobs, job status, customers, quotes with line items, invoices, quote and invoice email, payments, and Scheduler bookings in an account by reusing the user's own signed-in Chrome session, with no official API keys needed. Ships read-only hints and confirmation prompts for tools that reach other people, and can be run over stdio or streamable HTTP.

Exposes read-only Huly task intake, architecture guidance, UX patterns, and static validators through eight MCP tools, letting host agents drive approval-gated Flutter and Frappe delivery workflows. It can also be inspected directly (e.g. via the MCP inspector) so users can exercise the tools without an agent.

Enables MCP clients to read and manage a local Things 3 database on macOS through Things' supported scripting interface, listing, searching, creating, updating, moving, scheduling, and completing tasks, projects, and areas without any hosted service or network telemetry. Reads are paged and filtered, writes are confirmed by read-back verification, and an optional read-only mode blocks all mutations.

Enables an AI assistant to analyse, and when permitted edit, Primavera P6 Professional schedules on a Windows PC, whether they live in a standalone SQLite database or plain XER files. It provides critical path and float analysis, DCMA health checks, progress comparisons, and in-memory what-if scenarios, with write operations off by default and protected by dry runs, backups, and an edit log.

Gives AI assistants structured access to a test automation stack so they can run suites, inspect failure details and captured output, look up test data, and file Jira bugs (or drafts) only for confirmed defects. It works with any framework that emits JUnit XML, letting assistants triage flaky, environment, and test-data issues alongside real product defects.

Enables AI agents to read-only inspect an OmniFocus database, retrieving exact tasks and projects, Inbox roots, complete project hierarchies, tags, dates, notes and workload or review overviews. All access is read-only and bounded, with no mutation, write tools or sync triggers.

Enables AI coding tools to share one Markdown ship's log per project, so each session can read the current state, recent work and next steps across Claude Code, Codex, Gemini CLI and Copilot CLI, plus a dashboard showing every project at once. It also flags sessions that did work but logged nothing, and can be exposed remotely to ChatGPT via a self-hosted beacon.

Enables Claude Code and other MCP clients to read Trello boards, lists and cards—including checklists, comments, members and labels—directly from the editor. Users can tick or untick checklist items, post comments, move cards between lists, and search across boards, so an assistant can work through a card's feedback items and mark them off as they land.

A local workspace whose accessible pages and MCP tools are generated from the same definitions, so AI agents can do everything a person can: create, update and find notes, tasks and projects, build and arrange pages, and read any page back as a screen reader gets it.

An MCP server for Taskwarrior that implements agent claim and lease semantics for task management. It enables agents to list, create, and modify tasks while ensuring mutual exclusion through a system where tasks must be claimed before they are updated.

UseHourly is a free, open-source timesheet for freelancers. Log your day in seconds, then turn the hours into a PDF invoice. Its remote MCP server gives any AI assistant 30 tools to log and edit time, run timers, manage clients and projects, create invoices and read annual reports. It uses Streamable HTTP with bearer tokens that can be read-only or read-write, set to expire, and are revoked on a p

Bridges stdio-only MCP clients — or machines that cannot open a browser, such as CI, servers, and containers — to a remote fenbs board over HTTP using a hand-issued token. It lets an AI assistant act as the token's owner on that board, listing and managing tasks, decisions and standing rules, projects, and pre-approved work within the scopes granted.