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.

DimensionCircleCI MCP ServerIntegrate CircleCI development workflows with the Model Context Protocol for AI-powered development.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS42 / 100 · D79 / 100 · B
Reliability6 / 2012 / 20
Security and permissions10 / 2018 / 20
Maintenance8 / 2016 / 20
Documentation10 / 2018 / 20
Setup experience8 / 2015 / 20
Best for
  • Developers using MCP-compatible clients like Cursor, VS Code, Claude Desktop.
  • Teams that want to manage CircleCI pipelines seamlessly within their IDE.
  • Developers needing quick diagnostics for build failures and test issues.
  • 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 needing the latest features and security updates, as the package is deprecated and unmaintained.
  • Users seeking a hosted solution; CircleCI's hosted MCP server is recommended.
  • Users needing public remote access unless deploying a self-managed remote server with extra security.
  • 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 a CircleCI Personal API token (CIRCLECI_TOKEN) with read access to projects.
  • In remote mode, requires configuring allowed hosts (MCP_ALLOWED_HOSTS) and authentication.
  • File-related tools may read/write files; set MCP_FILE_OUTPUT_ROOTS to restrict root directories.
  • 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
  • Token exposure: if the personal or shared token leaks, unauthorized operations may occur.
  • Deprecation risk: the server is no longer maintained, potentially with security or compatibility issues.
  • Remote mode risk: if authentication is disabled (REQUIRE_REQUEST_TOKEN=false), anyone reaching the port can act on the server.
  • 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, VS Code, Claude Desktop, Claude Code, Windsurf, Amazon Q DeveloperClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools130