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.

DimensionMemory Journal MCP ServerPersistent memory and context handoff across AI sessions, with deep GitHub workflow integration.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS70 / 100 · B79 / 100 · B
Reliability11 / 2012 / 20
Security and permissions15 / 2018 / 20
Maintenance13 / 2016 / 20
Documentation17 / 2018 / 20
Setup experience14 / 2015 / 20
Best for
  • Developers working on large projects who need persistent AI memory.
  • Teams want to integrate IDE agents and GitHub Copilot with shared context.
  • Engineers managing multiple repositories who need unified project intelligence.
  • 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 only a trivial, stateless tool without any configuration.
  • Projects where persistent memory is explicitly not desired due to privacy concerns.
  • Environments that do not permit local file storage or database files.
  • 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
  • Local filesystem access limited by the `ALLOWED_IO_ROOTS` environment variable, used for import/export and Code Mode.
  • GitHub API access via the `GITHUB_TOKEN` to interact with issues, PRs, actions, etc.
  • Network access for remote HTTP/SSE transport, fetching embedding models, and OAuth token validation.
  • Read/write access to SQLite database files stored on the local machine.
  • 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
  • Misconfiguration of `ALLOWED_IO_ROOTS` could expose unintended file paths to the MCP tools.
  • A compromised GITHUB_TOKEN could allow unauthorized access to your repositories.
  • Code Mode executes sandboxed JavaScript, but there is always a risk if the sandbox is not perfectly isolated.
  • HTTP transport without proper authentication (e.g., OAuth or token) could allow unauthorized access.
  • Third-party embedding models may introduce supply chain risks.
  • 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 clientsClaude Desktop, CursorClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools640