Contextforge

Created By
Alfredo Izquierdo3 months ago
Persistent memory MCP server for Claude. Store decisions, code snippets, and knowledge that survives across sessions. Features semantic search, Git integration (auto-sync commits/PRs), task tracking, memory snapshots, and team collaboration.
Overview

ContextForge MCP Server

Persistent memory for AI coding agents — Claude Code, Cursor, GitHub Copilot, and more.

What it does

ContextForge gives your AI coding assistants long-term memory. They remember code patterns, decisions, project context, and your preferences across sessions. No more re-explaining the same context every conversation.

Key features

  • Semantic search — pgvector embeddings tuned for technical content
  • Git/PR sync — every commit becomes searchable context automatically
  • Project-based organization — separate memory per project, with shared spaces
  • Team collaboration — share knowledge across your team
  • Free tier — 1 project, 3 spaces, 200 documents, 500 queries/month, no credit card

Works with

  • Claude Code
  • Claude Desktop
  • Cursor
  • GitHub Copilot (via MCP)
  • ChatGPT (via MCP)
  • Windsurf
  • Any MCP-compatible client

Install

Quick install:

npx contextforge-mcp

Or via Claude Code:

claude mcp add contextforge -e CONTEXTFORGE_API_KEY=<your-key> -- npx contextforge-mcp

Get your API key at contextforge.dev.

Server Config

{
  "mcpServers": {
    "contextforge": {
      "command": "npx",
      "args": [
        "-y",
        "contextforge-mcp"
      ],
      "env": {
        "CONTEXTFORGE_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}
Project Info
Created At
3 months ago
Updated At
15 days ago
Author Name
Alfredo Izquierdo
Star
-
Language
-
License
-
Category

Recommend Servers

View All
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

8 hours ago