contextforge-mcp
Related Servers
Alternatives to contextforge-mcp
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityDmaintenancePersistent memory server for AI assistants with semantic search and three-layer context (global, project, personality). Works with MCP-compatible AI tools like Claude Code, Cursor, Continue, Cline, and more.1-
- AlicenseNot gradedqualityDmaintenanceMCP Memory Server for Claude Code that provides persistent context across sessions using semantic search (RAG).Apache 2.0
- AlicenseNot gradedqualityAmaintenanceA local markdown memory and cross-agent context engine for AI coding assistants. It provides an MCP server with tools to search, add, retrieve, and distill persistent memory across tools like Claude Code, Cursor, and Zed.63 PyPI5MIT
- AlicenseBqualityCmaintenanceMCP server that provides cross-session persistent memory for AI coding assistants using local vector database and semantic search, enabling automatic recall of project context, issues, and tasks.925 PyPI91Apache 2.0
- FlicenseNot gradedqualityDmaintenanceA persistent, conflict-aware memory MCP server for AI coding assistants (Cursor, Claude Code).-

threadctx-mcpofficial
AlicenseAqualityBmaintenanceShared memory MCP server for AI coding agents, enabling context sharing across sessions with local SQLite or cloud-based semantic search, compatible with Claude Code and Cursor.232 npm1MIT
TDQS
Scored across 69 tools
Tools are grouped by clear domain prefixes (memory_, tasks_, skills_, routines_, session_) and most have distinct purposes. However, tasks_resolve and tasks_resolve_by_name are nearly identical in behavior, and the various memory delete variants (memory_delete, memory_delete_batch, memory_forget) create some boundary ambiguity.
Tool names consistently follow a [domain]_[action] snake_case pattern throughout the entire set, making the naming highly predictable. Even subdomains like memory_git_ and memory_snapshot_ preserve the same convention, so agents can infer behavior from name structure.
69 tools is an extremely large surface for an MCP server, far beyond the 25+ threshold that typically makes a set feel overloaded. While the breadth covers multiple subsystems, several tools are redundant (tasks_resolve vs tasks_resolve_by_name) and the sheer count will make tool selection slower and more error-prone for agents.
The server covers full CRUD/lifecycle for memory, spaces, projects, tasks, skills, routines, snapshots, and git sync, which is impressively comprehensive. Minor gaps exist, such as no way to delete a memory relationship, no comment update/delete, and no routine execution history listing, but these are workarounds.