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.165 PyPI5MIT
- AlicenseBqualityDmaintenanceMCP 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.991Apache 2.0
- FlicenseNot gradedqualityDmaintenanceA persistent, conflict-aware memory MCP server for AI coding assistants (Cursor, Claude Code).-

threadctx-mcpofficial
AlicenseAqualityCmaintenanceShared 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.264 npm1MIT
TDQS
Scored across 11 tools
Most tools have clear, distinct roles: memory ingest/query/freshness tools, task list/next tools, session list, and the catch-all cf_tools. There is mild overlap between tasks_list and tasks_what_next, and cf_tools can serve as an alternate entry point for capabilities, but the descriptions provide strong usage triggers.
The tools mostly follow a clear prefix-plus-verb pattern like memory_ingest, memory_query, tasks_list, and session_list. The main inconsistency is cf_tools, which breaks the naming convention, and memory_help/tasks_what_next are slightly less verb-oriented, but the overall pattern is still readable.
With 11 primary tools, the visible surface is well-scoped and within the ideal range for an MCP server. The cf_tools meta-tool cleverly keeps the count manageable while exposing 59 additional capabilities, so the apparent tool count matches the server's core workflows.
The memory lifecycle is well covered with ingest, query, freshness checking, confirm, correct, and forget, and task/session reading is present. General memory updates/deletes and task editing are not first-class tools but are accessible through cf_tools, which creates a minor discoverability gap rather than a true dead end.