MCP Comparison
Compare features, tools, and capabilities of these MCP servers side by side.
Graphiti MCP Server
Graphiti MCP Server is an experimental implementation that exposes Graphiti's real-time, temporally-aware knowledge graph capabilities through the MCP (Model Context Protocol) interface. It enables AI agents and MCP clients to interact with Graphiti's knowledge graph for structured extraction, reasoning, and memory across conversations, documents, and enterprise data. The server supports multiple backends (FalkorDB by default and Neo4j), a variety of LLM providers (OpenAI, Anthropic, Gemini, Groq, Azure OpenAI), and multiple embedder options, all accessible via an HTTP MCP endpoint at /mcp/ for broad client compatibility. It also includes queue-based asynchronous episode processing, rich entity types for structured data, and flexible configuration through config.yaml, environment variables, or CLI arguments.
Github MCP Server
GitHub's official MCP Server. This repository hosts the MCP server implementation that enables Model Context Protocol (MCP) tooling for GitHub data and workflows. It exposes a wide registry of MCP tools spanning code management, repository operations, issues, pull requests, workflows, gists, and more. The documentation and commit history reveal a broad set of tools (GetMe, GetTeams, ListIssues, CreateOrUpdateFile, GetRepositoryTree, and many others) that are designed to be wired into dynamic toolsets and accessed via a consistent ServerTool pattern. This MCP server is built with extensibility in mind, supporting features like tool dependencies, dynamic toolsets, and feature flags to adapt to varied prompts and use cases. The project emphasizes a registry-driven approach where tools, resources, and prompts are defined and validated, enabling robust integration with client apps and AI models.
| Feature | Graphiti MCP Server | Github MCP Server |
|---|---|---|
| Verified | ||
| Official | ||
| Tools Available | 9 | 103 |
| Has Installation Guide | ||
| Has Examples | ||
| Website | ||
| Source Code |
- add_episode
- search_nodes
- search_facts
- delete_entity_edge
- delete_episode
- get_entity_edge
- get_episodes
- clear_graph
- get_status
- actions_get
- actions_list
- actions_run_trigger
- cancel_workflow_run
- delete_workflow_run_logs
- download_workflow_run_artifact
- get_job_logs
- get_job_logs
- get_workflow_run
- get_workflow_run_logs
- +93 more tools
Can't decide? Check out both MCP servers for more details.