M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

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

DimensionBitbucket MCP ServerA Model Context Protocol (MCP) server for Bitbucket Cloud and Server API integration.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS52 / 100 · D79 / 100 · B
Reliability4 / 2012 / 20
Security and permissions10 / 2018 / 20
Maintenance10 / 2016 / 20
Documentation14 / 2018 / 20
Setup experience14 / 2015 / 20
Best for
  • Developers using Bitbucket Cloud or Server who want AI assistant integration.
  • Teams that need to interact with Bitbucket repos and PRs programmatically or via natural language.
  • Users leveraging MCP standard to operate Bitbucket within tools like Cursor.
  • Engineering teams scaling AI coding agents while controlling spend
  • Platform teams that need auditable, rollback-aware agent execution records
  • Organizations using multiple agents (Claude, Codex, Gemini) under one governed flow
Not for
  • Users who need delete operations on Bitbucket resources (delete tools are disabled by default).
  • Users who need a GUI instead of CLI or AI integration.
  • Users without Bitbucket credentials.
  • Developers who just want a simple code-completion helper without run governance
  • Teams unwilling to accept local JSONL run records with HMAC signing
  • Environments without a supported adapter (Claude/Codex/Gemini CLIs, direct provider, or verifier-only)
Required permissions
  • Requires Bitbucket app password or access token.
  • Needs at least 'Repositories: Read' for most operations.
  • For pipeline operations, 'Pipelines: Read' is required.
  • For write operations (e.g., create/update PRs), 'Pull requests: Write' is required.
  • Read/write access to the configured repo root (writable scope restrictable via --allow-path/--deny-path)
  • Ability to invoke the chosen agent CLI (Claude/Codex/Gemini, etc.) and its underlying model account
  • Local disk writes for run records, receipts, and share outputs (share/run-receipt., etc.)
  • Execution of user-configured verifier commands (e.g. npm test)
Risks and side effects
  • Using app passwords or tokens may lead to unauthorized access if leaked.
  • Overly permissive credentials might allow unintended modifications or deletions (though delete tools are disabled by default).
  • Misconfiguration could expose sensitive information (e.g., incorrect logging levels).
  • Verifier commands are executed; poorly chosen verifier commands carry security risk despite preflight policy checks
  • Cost and token figures may be estimates (labeled with provenance) and should not be treated as settled accounting
  • Receipt integrity must be verified before use as trustworthy evidence; missing rollback evidence is flagged as EVIDENCE_BOUNDARY
  • Policy defaults come from martin.config.yaml and can be overridden by CLI flags; misconfiguration can loosen safety boundaries
Supported clientsCursor, Claude DesktopClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools400