Contextforge
@alfredoizdev
About Contextforge
Persistent memory MCP server for Claude. Store decisions, code snippets, and knowledge that
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"contextforge": {
"command": "npx",
"args": [
"-y",
"contextforge-mcp"
],
"env": {
"CONTEXTFORGE_API_KEY": "<YOUR_API_KEY>"
}
}
}
}Tools
44Add content to the contextual memory. Use this to store code snippets, documentation, decisions, or any knowledge you want to remember.
Search the contextual memory using semantic search. Returns the most relevant stored content based on your query.
Get the full content of a knowledge item by its ID. Use this when memory_query returns truncated previews and you need the complete content.
List all projects. Projects contain multiple spaces for organizing knowledge by project.
Create a new project to organize related spaces
List knowledge spaces (workspaces). By default shows only knowledge spaces. Use space_type "git" for GitHub repos, or "all" to see everything.
Create a new memory space (workspace) for organizing knowledge
Move a space to a different project
Delete a space and all its items permanently. This action cannot be undone.
Delete a project and all its spaces permanently. This will delete all spaces and their items within the project. This action cannot be undone.
Create a relationship between two knowledge items
Delete a knowledge item from memory by ID or title
Get statistics about memory usage
List all items stored in memory. Shows titles, previews, tags, and creation dates.
Show help and usage instructions for ContextForge memory commands
Connect a GitHub repository to automatically sync commits and PRs to memory
List all connected GitHub repositories
Activate or deactivate a connected repository webhook after setup
Disconnect a GitHub repository and stop syncing
Sync existing commits and PRs from a connected GitHub repository into memory
List commits stored in memory from connected repositories
List pull requests stored in memory from connected repositories
Create a snapshot (backup) of the current memory state
List all available snapshots
Restore memory to a previous snapshot state
Delete a snapshot
Export all items from a space to JSON, Markdown, or CSV format
Import items from JSON, Markdown, Notion, or Obsidian format into a space
Add multiple items to memory in a single operation. More efficient than multiple single ingests.
Delete multiple items from memory based on filters. Use dry_run=true first to preview what will be deleted.
Link the current directory to a ContextForge project. When linked, all queries will be automatically filtered to only search within that project's spaces. This creates a .contextforge file in the current directory.
Remove the project link from the current directory. This deletes the .contextforge file and queries will no longer be filtered by project.
Show the currently linked project for this directory, including its spaces. Use this to see which project is linked and what spaces are available.
List tasks assigned to you. Shows pending tasks by default. Use status "all" to see everything, or "resolved" for completed tasks. IMPORTANT: Each task includes a dashboard URL (🔗). You MUST include these clickable links when presenting tasks to the user.
Mark a task as "in_progress". Use this when you start working on a task. The response includes a dashboard URL — always show it to the user.
Mark a task as "resolved". Use this when you finish working on a task. The response includes a dashboard URL — always show it to the user.
Get a recommendation of what task to work on next, based on priority and due dates. Use this when you want to know what task to focus on. The response includes a dashboard URL — always show it to the user.
Create a new task in a project. Optionally assign it to a collaborator by their email. The response includes a dashboard URL — always show it to the user.
Update a task's title, description, status, priority, tags, due date, or assignee. Provide issue_id or short_id to identify the task, plus one or more fields to update. The response includes a dashboard URL — always show it to the user.
Assign a task to a collaborator by their email address. The response includes a dashboard URL — always show it to the user.
Resolve a task by searching for it by title. Use this when you only know the task name. The response includes a dashboard URL — always show it to the user.
Delete a task by ID or short_id. This performs a soft delete (sets deleted_at timestamp).
List collaborators on a shared project. Shows who has access and what tasks are assigned to them.
Share a project with a collaborator by email. Creates an invitation and returns the invite URL. An email notification may also be sent.
Overview
What is Contextforge?
Contextforge is an MCP server that provides persistent memory for AI coding agents, such as Claude Code, Cursor, and GitHub Copilot. It stores code patterns, decisions, project context, and user preferences across sessions, eliminating the need to re‑explain context. It uses pgvector embeddings for semantic search and offers Git/PR sync, project‑based organization, team collaboration, and a free tier.
How to use Contextforge?
Install with npx contextforge-mcp or add via Claude Code using claude mcp add contextforge -e CONTEXTFORGE_API_KEY=<your-key> -- npx contextforge-mcp. Obtain an API key at contextforge.dev.
Key features of Contextforge
- Semantic search with pgvector embeddings tuned for technical content
- Automatic Git/PR sync — every commit becomes searchable context
- Project‑based organization with separate memory per project
- Team collaboration – share knowledge across your team
- Free tier includes 1 project, 3 spaces, 200 documents, 500 queries/month
Use cases of Contextforge
- AI coding assistants remember code patterns and project decisions across sessions
- Automatically index commits and pull requests as searchable context
- Separate context per project and share it among team members
FAQ from Contextforge
Which AI coding agents does Contextforge support?
Contextforge works with Claude Code, Claude Desktop, Cursor, GitHub Copilot (via MCP), ChatGPT (via MCP), Windsurf, and any MCP‑compatible client.
How do I get started with Contextforge?
Run npx contextforge-mcp after obtaining a free API key from contextforge.dev. No credit card is required for the free tier.
Does Contextforge have a free tier?
Yes – it includes 1 project, 3 spaces, 200 documents, and 500 queries per month, with no credit card needed.
Where does my data live?
The README does not specify where data is stored; it references contextforge.dev for an API key and the npm/GitHub repositories.
What are the runtime requirements for Contextforge?
The README does not list specific runtime dependencies beyond Node.js (implied by npx).
More Memory & Knowledge MCP servers
Notion MCP Server
makenotionOfficial Notion MCP Server
MCP server for Obsidian
MarkusPfundsteinMCP server that interacts with Obsidian via the Obsidian rest API community plugin
Notion MCP Server
suekouA Model Context Protocol server for connecting Notion to MCP-compatible clients
Ultimate Google Docs & Drive MCP Server
a-bonusThe Ultimate Google Docs, Sheets, Drive, Gmail, & Google Calendar MCP Server. This MCP (primarily for use in Claude Desktop) gains full access to your google suite and lets claude do its thing.
Memory Bank MCP Server
alioshrA Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank.
Comments