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.

DimensionHeadroomA local context-compression layer for AI agentsMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS60 / 100 · C79 / 100 · B
Reliability9 / 2012 / 20
Security and permissions11 / 2018 / 20
Maintenance12 / 2016 / 20
Documentation15 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • Developers who use AI coding agents regularly
  • Users who want local processing and lower LLM context costs
  • Workflows combining multiple agents or MCP tools
  • 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
  • Sandboxed environments that cannot run local processes
  • Users satisfied with a single provider's native compaction and without a need for cross-agent features
  • 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
  • The MCP host must start a local Headroom process
  • The server must process incoming tool outputs, logs, files, RAG chunks, or conversation context
  • Reversible compression may cache original content locally
  • 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
  • Compression changes the form of content sent to the LLM; the project claims answer preservation, but results depend on the input
  • The local cache may contain sensitive information from tool outputs, files, or logs
  • Some features may download runtime or model assets from cdn.pyke.io or huggingface.co
  • Unsupported Python, platform, or AVX2 conditions can cause installation failures or feature fallbacks
  • 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 Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools30