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.

DimensionThumbGate MCP ServerSelf-improving firewall for AI coding agents that gates tool calls before they runGitHub MCP ServerGitHub's official MCP server for managing repos, issues, PRs, and workflows via natural language
FMRS61 / 100 · C76 / 100 · B
Reliability8 / 2013 / 20
Security and permissions13 / 2014 / 20
Maintenance13 / 2018 / 20
Documentation14 / 2017 / 20
Setup experience13 / 2014 / 20
Best for
  • Developers running AI coding agents in production or high-blast-radius workflows who need an external enforcement boundary
  • Engineering/security/platform teams wanting auditable, inspectable gate decisions
  • Teams converting repeated corrections into reusable rules instead of relying on model memory
  • Teams that want an AI assistant to directly operate on GitHub repos and collaboration workflows
  • Users already in the GitHub Copilot ecosystem who want a zero-deployment remote option
Not for
  • Small teams happy with a small static hand-written denylist (native hooks suffice)
  • Those expecting gating to improve model generation quality (it intercepts execution only)
  • Cursor/Cline/OpenCode users handling irreversible actions, since advisory verdicts can be ignored
  • Scenarios where you don't want the assistant to have write access to repos (enable only read-only toolsets)
  • Environments with strict network isolation for private repos that can't reach the official remote endpoint
Required permissions
  • Runs locally over stdio; reads/writes ~/.claude or in-repo .claude config, hooks, and lesson stores
  • Writes local state (.thumbgate/), JSONL logs, and task-outcome receipts
  • Requires modifying the agent's MCP and PreToolUse hook configuration files
  • Task-outcome decisions need THUMBGATE_HUMAN_REVIEWER_ID and an independently revocable human reviewer key
  • A personal access token (PAT) or OAuth App token; effective scope depends on the token's own permissions
  • Enabling toolsets like actions/issues/pull_requests grants write access — request tokens on a least-privilege basis
Risks and side effects
  • Advisory integrations (Cursor, Cline, OpenCode, Amp) can be ignored by the agent — no true blocking of irreversible actions
  • In strict mode, false positives from stale or noisy rules can block legitimate work; recovery relies on break-glass
  • Ships warn-by-default: most high-risk commands are not blocked unless strict enforcement is on
  • Dashboard token/dollar savings are estimates, not measured provider usage
  • Lesson DBs contain sensitive engineering context and must stay gitignored in per-project installs
  • Regulated-industry templates are roadmap directions, not shipped compliance capabilities
  • Write toolsets (creating/merging PRs, triggering workflows) can cause accidental changes if the token is overscoped — try a read-only toolset first
  • In hosted mode, credentials travel via the Authorization header — make sure the client-to-api.githubcopilot.com connection is trusted
Supported clientsClaude Code, Claude Desktop, Cursor, Codex, Gemini CLI, Cline, OpenCode, AmpClaude Desktop, Claude Code, VS Code, Cursor, Windsurf, JetBrains IDEs, Zed, Amp
Tools1315