← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionNotion MCP ServerOfficial Notion MCP server for querying, editing, and managing Notion pages and databases via AI agents.Atlassian Rovo MCP ServerSecurely connect Atlassian Cloud to AI tools.Figma Console MCPYour design system as an API. Connect AI to Figma for extraction, creation, and debugging.
FMRS64 / 100 · C66 / 100 · C63 / 100 · C
Reliability8 / 208 / 208 / 20
Security and permissions17 / 2015 / 2013 / 20
Maintenance10 / 2015 / 2015 / 20
Documentation16 / 2015 / 2014 / 20
Setup experience13 / 2013 / 2013 / 20
Best for
  • Teams and individuals who already manage docs/wikis in Notion and want AI clients (Claude Desktop, Cursor, etc.) to operate on that content directly
  • Developers who want to self-host a local MCP server rather than use a remote hosted option
  • Automation/agent workflows that need to query or update Notion database records programmatically
  • Developers, content creators, and project teams using Atlassian Cloud
  • Teams that want Atlassian access inside ChatGPT, Claude, Cursor, or VS Code
  • Users who need natural-language search, write, and cross-product workflows
  • Designers and design system teams looking to integrate AI into their workflow.
  • Developers needing quick prototyping or visual spec generation.
  • Product managers who need to communicate visual requirements during discussions.
  • Teams managing multi-file design systems (via figma_execute_across_files).
  • Developers who need to export tokens from Figma to their codebase (token sync).
Not for
  • Users who want the standard-OAuth, zero-JSON-config install with active official support — Notion recommends its newer remote Notion MCP server for that
  • Users uncomfortable handing a Notion integration token to a locally-run LLM client
  • Use cases needing capabilities the integration deliberately excludes, such as deleting databases
  • Long-term production deployments that need guaranteed maintenance, given this repo may be sunset
  • Users without an Atlassian Cloud site or relevant product permissions
  • Deployments requiring a self-hosted MCP server
  • Users unwilling to grant an AI client access to Atlassian data or actions
  • Jira Service Management or Bitbucket Cloud workflows requiring OAuth authentication
  • Users who need read-only access and want to avoid installing Node.js — consider Remote SSE mode (9 read-only tools).
  • Users who strictly need code generation (e.g., React/HTML) — the official Figma Dev Mode MCP is more suitable.
  • Users who want quick evaluation without write capabilities — Remote SSE is sufficient.
  • Users who want to design in the cloud but avoid installing the Desktop Bridge plugin (Cloud Mode still requires the plugin).
Required permissions
  • A Notion internal integration token (NOTION_TOKEN or the Authorization value in OPENAPI_MCP_HEADERS), scoped by that integration's Capabilities (can be limited to read-only)
  • Access limited to the specific pages/databases explicitly connected to the integration, not the whole workspace
  • A separate bearer auth token when using the Streamable HTTP transport (--auth-token / AUTH_TOKEN)
  • Network access to the Notion API
  • Jira and Confluence provide read, write, and search permission groups
  • Jira Service Management provides read and write access through API tokens only
  • Bitbucket Cloud provides read and write access through scoped API tokens only
  • Compass is available through OAuth 2.1 only
  • The first OAuth installer for a site must have access to the Atlassian apps requested by the MCP scopes
  • Organization administrators can manage domain controls, API-token authentication, app access, and audit logs
  • Figma personal access token (PAT): file content read, file versions read, variables read, comments read/write (local mode).
  • Desktop Bridge plugin permissions: access current file via plugin API, read selection, console logs, document changes, and execute write operations (create frames, variables, etc.).
  • Local filesystem: the server writes/reads plugin files in ~/.figma-console-mcp/ (auto-created).
  • WebSocket ports 9223-9232: the server listens on these ports locally for plugin connections.
  • For Cloud Mode, OAuth is required (remote endpoint) or PAT (Cloud Mode bypasses Enterprise restrictions).
Risks and side effects
  • If the integration is granted broad read/write capabilities and connected to many pages, that content is effectively exposed to the LLM, risking data leakage or unintended edits
  • Running with --unsafe-disable-auth removes bearer authentication on the HTTP transport, potentially making it reachable via DNS rebinding from pages a user visits — the README says to only use it on an isolated network
  • Multi-tenant token passthrough requires careful TLS/gateway configuration; misconfiguration risks leaking or misrouting Notion tokens between tenants
  • The README states this local server may be sunset in favor of the remote Notion MCP, and that issues/PRs here are not actively monitored, so long-term maintenance and security fixes are not guaranteed
  • Storing NOTION_TOKEN or OPENAPI_MCP_HEADERS directly in shared client config files risks leaking the secret
  • AI clients can perform Jira, Confluence, Jira Service Management, Bitbucket, and Compass actions on the user’s behalf
  • Prompt injection, indirect prompt injection, and tool-poisoning attacks may cause data exfiltration or unintended changes
  • Use least privilege, scoped tokens, and minimal project or workspace access
  • Require human confirmation for high-impact or destructive actions and monitor audit logs
  • Write operation risk: tools like figma_execute can run arbitrary plugin code, potentially modifying or deleting designs unintentionally — test on a copy file first.
  • Token leakage: FIGMA_ACCESS_TOKEN is stored in plaintext in client configs; if the config file leaks, the token could be abused.
  • Remote server trust: the remote SSE endpoint is hosted by a third party (southleft); data (design info) passes through their infrastructure; self-hosting options exist.
  • Multi-instance issues: port conflicts may cause connection issues, but multi-instance support is implemented (automatic port fallback).
  • Update banner issue: plugin-server version mismatch may cause persistent re-import prompts — fixed in recent releases, but restart clients after upgrading.
Supported clientsClaude Desktop, Cursor, Zed, GitHub Copilot CLIOpenAI ChatGPT, Claude, Cursor, Visual Studio Code (GitHub Copilot), GitHub Copilot CLI, Google Gemini CLI, Amazon Quick Suite, Local MCP-compatible clients via mcp-remoteClaude Desktop, Claude Code, Cursor, Windsurf
Tools9074