"browser" matching MCP servers:

Provides read-only access to Azure DevOps using your browser session, no PAT required. Enables browsing projects, repos, work items, pull requests, and feeds through MCP tools.

Browser-backed MCP wrapper for mcp-atlassian with Playwright SSO auth. Enables AI tools to access Atlassian Server/Data Center instances behind corporate SSO (Okta, SAML, ADFS) where API tokens are not available

MCP server that enables accessing Jira and Confluence using browser cookies captured via a Chrome extension, avoiding the need for API tokens or browser automation. It wraps the mcp-atlassian toolset and works with Atlassian Cloud and Server/Data Center behind SSO.

Task planning and execution MCP server with durable SQLite storage and a browser UI for reviewing plans and following progress.

Enables interaction with ServiceNow ITSM through browser-based SSO authentication, providing 80+ tools for incidents, changes, catalog, CMDB, and more via natural language.

MCP server for managing a task graph with live visualization. Enables Claude Code to create, update, and link nodes (tasks, subtasks, ideas, etc.) while a browser viewer displays the graph in real time.

MCP server that gives LLMs full visibility into your ws-cli workspace tree, enabling queries about workspaces, git status, tasks, and saved browser tabs.

Enables natural-language interaction with self-hosted Jira through the Jira REST API, supporting PAT or browser-cookie/SSO authentication. It allows viewing and managing issues, projects, comments, assignments, and statuses, as well as JQL search and issue creation/deletion.

MCP server for Upwork via browser automation. Enables Claude Code to search jobs, manage proposals, messages, and contracts on Upwork.

Enables AI assistants to manage Fiverr seller accounts directly from the browser session. Supports gig management, order tracking, messaging, analytics, and profile updates without API keys.

Lets an AI assistant read and fill an Innoslate project through your own logged-in browser session, surveying the project, reading your documents and guides, and proposing a plan before writing entities, trace links, artifacts and reports after a dry run. It works on the free tier where API keys are refused, since every call goes through the browser instead.

Lets an AI assistant read and, with explicit confirmation, manage a gliding club's planning data through the Click n' Glide API — signups, daily forum, members, roles, events and general forum. It also drives the web app in a headless browser to list, read and send club messages that the official API does not cover.

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.

Runs locally over stdio and forwards tool calls to a Planeshift instance's Rails API, letting Claude list projects, read timelines, and record notes, meetings, todo actions, and important links. It supports browser-based login or token/URL environment variables, with a separate development-mode credential file for self-hosted or local instances.

Connects AI assistants to a Redmine instance over the Redmine REST API, enabling issue, project, user, time-tracking, wiki, file, search, and saved-query operations. Sign-in uses browser-based OAuth 2.0 with PKCE (or an API key for older servers), and the tool catalogue spans 55 tools across 9 groups.

Enables Claude and other MCP clients to browse and manage Redbooth organizations, projects, task lists, tasks, subtasks, and comments, with one-click browser OAuth sign-in and an optional read-only mode.

This MCP server provides a browser-based board for managing threaded feedback sessions with an agent, enabling users to respond to multiple review findings or questions at their own pace with quick replies and batched submission.

MCP server for reading ONES documents in intranet environments, supporting authentication via account/password or browser session reuse.

Enables AI assistants to read and write TickTick/Dida365 tasks, projects, tags, habits, and calendars through the service's private web API using browser session-cookie authentication. It exposes 34 tools covering task creation, completion, search, batch operations, trash restore, and full-account delta sync.

Enables users and AI agents to collaboratively create and edit live boards of cards, connections, groups, and notes, with changes synced instantly between the browser and agent.