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.

DimensionLmOffload routine tasks from Claude Code to local or cloud LLMs to save token spend.GitHub MCP ServerGitHub's official MCP server for managing repos, issues, PRs, and workflows via natural language
FMRS52 / 100 · D76 / 100 · B
Reliability6 / 2013 / 20
Security and permissions9 / 2014 / 20
Maintenance9 / 2018 / 20
Documentation15 / 2017 / 20
Setup experience13 / 2014 / 20
Best for
  • Developers using Claude Code for large refactors who want to reduce token bills.
  • Users with a local GPU server who want to leverage local models for repetitive tasks.
  • Those needing to offload bounded, well-defined tasks from Claude to a cheaper model.
  • Developers familiar with MCP and OpenAI-compatible APIs.
  • 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
  • Tasks requiring strong reasoning or tool access should stay on Claude.
  • Latency-sensitive interactive scenarios, as local inference can be 3-30x slower than frontier models.
  • Users who do not need an MCP server but want to call LLM APIs directly.
  • Users not using Claude Code or Claude Desktop as an MCP client.
  • 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
  • Read local files on the system (when using the code_task_files tool).
  • Create and read a local SQLite database file (~/.houtini-lm/model-cache.db).
  • Make network requests to the LLM endpoint (local or cloud).
  • Run Node.js processes.
  • 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
  • Sending code or data to a local or cloud LLM may lead to information leakage, especially with cloud APIs.
  • Running untrusted code on local models may introduce security vulnerabilities.
  • Over-reliance on local models may degrade output quality because local models can be less capable.
  • The MCP server may inadvertently expose local file system paths, so use code_task_files with caution.
  • Token savings may be overestimated, as local inference can take more time or resources.
  • 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 Desktop, Claude CodeClaude Desktop, Claude Code, VS Code, Cursor, Windsurf, JetBrains IDEs, Zed, Amp
Tools815