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.

DimensionReversecore MCPAI-powered reverse engineering and security analysisMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS54 / 100 · D79 / 100 · B
Reliability10 / 2012 / 20
Security and permissions8 / 2018 / 20
Maintenance11 / 2016 / 20
Documentation13 / 2018 / 20
Setup experience12 / 2015 / 20
Best for
  • Security researchers and malware analysts
  • Teams that need natural-language orchestration across analysis engines
  • Developers performing binary, firmware, vulnerability, or forensic analysis
  • 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
  • General development tasks without security-analysis requirements
  • Users who want to handle untrusted samples without an isolated environment
  • Users seeking only basic file operations or general database capabilities
  • 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
  • Access to the configured analysis workspace and sample files
  • A mounted local sample directory for Docker deployments
  • Optional API-key, upload-size, and rate-limit configuration in HTTP mode
  • Optional Redis, SQLite memory storage, and container sandbox access
  • 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
  • Samples may be malicious or exploitative and should be analyzed in an isolated environment.
  • PoC generation, ROP construction, and vulnerability-research tools can create misuse risks.
  • Sandbox execution is disabled by default; dynamic analysis may run on the host unless enabled.
  • Misconfigured HTTP, uploads, or workspace mounts can increase file or network exposure.
  • Results can include inference; the project distinguishes OBSERVED, INFERRED, and POSSIBLE evidence.
  • 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
Tools120