Skip to main content
Glama
116,475 servers. Updated

Matching MCP tools:

Matching MCP Connectors:

"Information about Claude AI clones or alternatives" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables MCP clients such as Cursor to hand a bounded task to a scoped, non-interactive Claude Code session billed to a Claude subscription rather than Cursor model credits. Runs read-only by default, with optional file edits or Bash, plus budget, timeout, and session-resume controls.
    16 npm
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Two AIs. One answer. ChatGPT and Claude discuss with each other until they agree, through your own signed-in CLIs: no API keys. Both read your project (never change it) and search the web. Plugin for Claude Code, Codex, Claude Desktop and the ChatGPT app.
    2
    8
    448 npm
    5
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Generates AI context files (CLAUDE.md, AGENTS.md, Cursor/Windsurf/Cline/Continue/Kilo Code/Trae rules, GEMINI.md, Copilot, Aider, Junie, Warp) for any repository. Runs as CLI or MCP server, 100% local.
    3
    23 npm
    1
    MIT
  • A
    license
    B
    quality
    D
    maintenance
    MCP server that enables calling Anthropic Claude models from OpenAI Codex Desktop/GUI, supporting API key or OAuth authentication and providing chat, model listing, and diagnostic tools.
    8
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables Claude Code to retain cross-session memory of facts, decisions, and lessons with semantic search, while tracking user corrections as behavioral patterns and evolving self-improving frameworks over time. All processing runs locally through an MCP server and hooks, requiring no cloud service or API key.
    6 npm
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables voice-driven software development by bridging the Claude app's voice mode to Claude Code, allowing users to direct repository work through natural language while requiring approval before any write or shell execution.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables Claude to search past coding transcripts stored locally — by exact words or by meaning — read them page by page, and reopen them in a terminal to resume work in the original directory. Everything stays on the machine, with a year-long archive.
    7 npm
    ISC
  • A
    license
    Not graded
    quality
    A
    maintenance
    Gives Claude Code persistent memory across sessions with semantic search, tracks and classifies user corrections to surface behavioral patterns, and evolves behavioral frameworks over time based on accumulated evidence. Runs entirely locally through 15 MCP tools and hooks, requiring no API key or cloud service.
    6 npm
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Gives Claude Code persistent cross-session memory with semantic search, automatically detecting and classifying user corrections to track behavioral patterns over time. It also extracts signals from each session to evolve, promote, or retire behavioral frameworks, letting the assistant develop judgment that improves across sessions.
    6 npm
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Gives Claude Code persistent cross-session memory with semantic search, automatic detection and classification of user corrections, and evolving behavioral frameworks that develop over time. Runs fully locally through Claude Code's hooks and 15 MCP tools, requiring no API key or cloud service.
    6 npm
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables Claude Code to retain identity, memories, and behavioral frameworks across sessions — saving facts and decisions for later semantic search, detecting and classifying user corrections, and evolving learned frameworks over time. Everything runs locally through a SQLite-backed engine with 15 MCP tools plus hooks, requiring no cloud service or API key.
    6 npm
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Gives Claude Code persistent cross-session memory with semantic search over saved facts, decisions, and journals, alongside automatic detection and classification of user corrections as trackable behavioral patterns. It also extracts behavioral signals from sessions and evolves self-authored frameworks over time, so the assistant develops judgment that carries forward between conversations — all local, with no cloud or API key required.
    6 npm
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables Claude Code to search and retrieve information from its past session transcripts, including tool calls, errors, and project-specific history, via an SQLite FTS5 full-text search index.
    11 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Provides tools for Claude to query local Claude Code token usage and cost data, enabling spend analysis and insights through natural language.
    12 npm
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables Claude Code to request and read hand-drawn sketches or annotations on a persistent canvas displayed on local or networked devices.
    1
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Gives Claude Code a persistent identity and cross-session memory with semantic search over saved facts, decisions, and journals. It also detects and classifies user corrections into behavioral patterns with lifecycle trends, reflecting periodically to promote or retire working frameworks.
    6 npm
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Relays messages between two Claude Code sessions running on separate machines, using the Channels API to push an incoming message directly into the other session so one session can ask another about its own checkout. Each message carries an id and is tracked as sent, delivered-to-process, or answered, with a per-message reply budget.
    63 npm
    21
    MIT