loading…
Search for a command to run...
loading…
Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot. Semantic search, Git sync, project-based, Persistent memory MCP server for Claude Code
Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot. Semantic search, Git sync, project-based, Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot. Semantic search, Git sync, project-based organization, and team collaboration via Model Context Protocol.
npm version License: MIT Node.js Glama MCP
Give Claude Code, Cursor, and GitHub Copilot persistent memory across sessions via the Model Context Protocol (MCP). Stop re-explaining your project every time.
ContextForge MCP is an open-source MCP server that connects your AI coding assistants to long-term, searchable memory. Decisions, architecture notes, debugging context, and project knowledge stay available across every session — across every tool that supports MCP.
npm install -g contextforge-mcp
cf_)Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"contextforge": {
"command": "contextforge-mcp",
"env": {
"CONTEXTFORGE_API_KEY": "your-api-key-here"
}
}
}
}
Restart Claude Desktop.
claude mcp add contextforge \
-e CONTEXTFORGE_API_KEY=your-api-key-here \
-- contextforge-mcp
Restart Claude Code and run /mcp to verify it's connected.
Add to your Cursor MCP settings:
{
"mcpServers": {
"contextforge": {
"command": "npx",
"args": ["contextforge-mcp"],
"env": {
"CONTEXTFORGE_API_KEY": "your-api-key-here"
}
}
}
}
Add to your Copilot MCP config:
{
"servers": {
"contextforge": {
"command": "npx",
"args": ["contextforge-mcp"],
"env": {
"CONTEXTFORGE_API_KEY": "your-api-key-here"
}
}
}
}
After installing the MCP, run this in every project directory where you want Claude to use ContextForge memory:
npx contextforge-mcp init
This writes a CLAUDE.md file that tells Claude Code to use the ContextForge MCP instead of its built-in file-based auto-memory. Without this step, Claude will silently ignore ContextForge for memory queries — even though the MCP is connected — because the built-in auto-memory wins by default.
The command is idempotent: running it again is a no-op if the section is already present. If you already have a CLAUDE.md, the ContextForge section is appended without touching your existing content.
ContextForge provides tools for Knowledge Management, GitHub Integration, Issue Tracking, and Collaboration.
| Tool | Description |
|---|---|
memory_ingest |
Save knowledge to memory |
memory_query |
Search your knowledge semantically |
memory_list_items |
List all stored items |
memory_delete |
Remove specific items |
memory_ingest_batch |
Save multiple items at once |
memory_delete_batch |
Delete items by filter |
| Tool | Description |
|---|---|
memory_list_spaces |
List your spaces |
memory_create_space |
Create a new space |
memory_delete_space |
Delete a space |
memory_move_space |
Move space to project |
memory_list_projects |
List your projects |
memory_create_project |
Create a new project |
memory_delete_project |
Delete a project |
memory_link_project |
Link directory to project |
memory_unlink_project |
Unlink directory |
memory_current_project |
Show linked project |
| Tool | Description |
|---|---|
memory_git_connect |
Connect a GitHub repo |
memory_git_list |
List connected repos |
memory_git_activate |
Activate/deactivate webhook |
memory_git_sync |
Import existing history |
memory_git_commits |
List synced commits |
memory_git_prs |
List synced PRs |
memory_git_disconnect |
Disconnect a repo |
| Tool | Description |
|---|---|
issues_list |
List your issues |
issues_create |
Create a new issue |
issues_start |
Mark as in progress |
issues_resolve |
Mark as resolved |
issues_resolve_by_name |
Resolve by title |
issues_assign |
Assign to collaborator |
issues_what_next |
Get recommendation |
| Tool | Description |
|---|---|
project_share |
Share project by email |
collaborators_list |
List collaborators |
| Tool | Description |
|---|---|
memory_snapshot_create |
Create a backup |
memory_snapshot_list |
List all snapshots |
memory_snapshot_restore |
Restore from backup |
memory_snapshot_delete |
Delete a snapshot |
memory_export |
Export to JSON/MD/CSV |
memory_import |
Import from file |
| Tool | Description |
|---|---|
memory_stats |
View usage statistics |
memory_relate |
Link two items |
memory_help |
Show help |
You don't need to memorize commands — just talk naturally to your AI:
# Knowledge
"Save this: we use PostgreSQL for the main database"
"What database do we use?"
"List my spaces"
# GitHub
"Connect my repo github.com/myuser/myproject"
"What commits did I make today?"
"Show PRs merged this week"
# Issues
"Create an issue: Update the login page design"
"What's pending?"
"What should I work on next?"
"Mark the login issue as done"
| Variable | Required | Description |
|---|---|---|
CONTEXTFORGE_API_KEY |
Yes | Your API key from the dashboard |
CONTEXTFORGE_API_URL |
No | API endpoint (defaults to production) |
CONTEXTFORGE_DEFAULT_SPACE |
No | Default space for operations |
ContextForge MCP is a thin client that translates Model Context Protocol tool calls into authenticated HTTP requests against the ContextForge API. Your knowledge is stored, indexed (semantic embeddings), and retrieved on the server side — the MCP client itself is stateless.
This means:
Manage your memory visually at contextforge.dev:
# Clone and install
git clone https://github.com/alfredoizdev/contextforge-mcp.git
cd contextforge-mcp
npm install
# Build
npm run build
# Run tests
npm test
# Watch mode
npm run dev
Issues and pull requests are welcome at github.com/alfredoizdev/contextforge-mcp.
MIT © Alfredo Izquierdo
Выполни в терминале:
claude mcp add contextforge-mcp -- npx Не уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории development