Contextforge Mcp

Name: Contextforge Mcp
Author: alfredoizdev

by alfredoizdevcommunityv0.2.0

ContextForge MCP is an MCP server that gives AI coding assistants persistent, searchable project memory across sessions by sending tool calls to the ContextForge API. It also supports GitHub repo syncing, issue tracking, collaboration, snapshots, and export/import of memory data.

From the registry: Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot.

GitHub Repository

Install & configure

Prerequisites

required
Install Node.js 20+
Node.js version 20 or newer is required to run the MCP server.
https://nodejs.org/
required
Install ContextForge MCP
Install the MCP server globally using npm. The README also shows npx-based invocation in some client examples, but the primary quick-start install path is a global npm install.
```
$ npm install -g contextforge-mcp
```
required
Create a ContextForge API key
Sign up at ContextForge and generate an API key from Settings → API Keys. This key is required for the server to authenticate.
https://contextforge.dev
required
Initialize each project directory
Run the init command in every project directory where you want ContextForge memory to be used. This writes or updates CLAUDE.md so Claude uses ContextForge memory instead of built-in file-based auto-memory. Without this step, the MCP may be connected but ignored for memory queries in Claude workflows.
```
$ npx contextforge-mcp init
```

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `contextforge-mcp` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install Node.js 20+** — Node.js version 20 or newer is required to run the MCP server. (https://nodejs.org/)
- **Install ContextForge MCP** — Install the MCP server globally using npm. The README also shows npx-based invocation in some client examples, but the primary quick-start install path is a global npm install. Run: `npm install -g contextforge-mcp`
- **Create a ContextForge API key** — Sign up at ContextForge and generate an API key from Settings → API Keys. This key is required for the server to authenticate. (https://contextforge.dev)
- **Initialize each project directory** — Run the init command in every project directory where you want ContextForge memory to be used. This writes or updates CLAUDE.md so Claude uses ContextForge memory instead of built-in file-based auto-memory. Without this step, the MCP may be connected but ignored for memory queries in Claude workflows. Run: `npx contextforge-mcp init`

Canonical MCP server config (stdio transport):
- command: `contextforge-mcp`
- args: []
- required environment variables:
  - `CONTEXTFORGE_API_KEY`: Your ContextForge API key from the dashboard. (example: `<your-api-key>`)
- optional environment variables:
  - `CONTEXTFORGE_API_URL`: Override the ContextForge API endpoint; defaults to the production API. (example: `<your-api-url>`)
  - `CONTEXTFORGE_DEFAULT_SPACE`: Default space to use for operations. (example: `<your-default-space>`)

Note: The README shows both a globally installed binary (`contextforge-mcp`) and npx-based examples. Per the quick-start and portability guidance in the README, the canonical stdio shape can use the installed command directly after `npm install -g contextforge-mcp`. The server is a stdio MCP client wrapper around authenticated HTTP requests to the ContextForge API.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: The README shows both a globally installed binary (`contextforge-mcp`) and npx-based examples. Per the quick-start and portability guidance in the README, the canonical stdio shape can use the installed command directly after `npm install -g contextforge-mcp`. The server is a stdio MCP client wrapper around authenticated HTTP requests to the ContextForge API.

Tools (41)

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

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

Environment variables

CONTEXTFORGE_API_KEYrequiredYour API key from the dashboard

Packages

contextforge-mcp

npmv0.2.0transport: stdio

Details

Language: JavaScript
License: MIT
Released: Jun 2, 2026
Last commit: Jul 7, 2026
Registry name: io.github.alfredoizdev/contextforge-mcp

Related Servers

Claude Flow

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

64.3k

Codebase Memory Mcp

Persistent codebase knowledge graph. Survives session restarts and context compaction.

31.2k

Serena

A powerful toolkit for coding, providing semantic retrieval and editing capabilities.

26.4k