labforgedev avatar

Copilot Memory MCP

labforgedev/copilot-memory-mcp

Gives Copilot persistent memory across VS Code sessions using ChromaDB and local vector embeddings. Runs entirely in Docker with no cloud dependencies. You get five MCP tools: create_memory, search_memories, update_memory, delete_memory, and list_memories. Memories are embedded with all-MiniLM-L6-v2 for semantic search and can be scoped by project or tagged. Ships with ready-to-use agent instructions for Copilot, Cursor, and Claude, plus custom prompt examples for recall and save workflows. Useful when you want your AI pair programmer to remember architectural decisions, coding conventions, or project context without re-explaining them every session.

GitHub stars
1
tools
5
transport
SSE
last updated
Mar 15, 2026

Tools

5 tools

Public tool metadata for what this MCP can expose to an agent.

create_memoryStore a new memory with title, content, optional project scope and tags

Store a new memory with title, content, optional project scope and tags

No parameter schema in public metadata yet.

search_memoriesSemantic vector search; filter by project and/or tags

Semantic vector search; filter by project and/or tags

No parameter schema in public metadata yet.

update_memoryUpdate an existing memory by ID; re-embeds on change

Update an existing memory by ID; re-embeds on change

No parameter schema in public metadata yet.

delete_memoryPermanently delete a memory by ID

Permanently delete a memory by ID

No parameter schema in public metadata yet.

list_memoriesBrowse memories with pagination (lightweight, no content)

Browse memories with pagination (lightweight, no content)

No parameter schema in public metadata yet.

Sponsors

Readme

copilot-memory-mcp

License: MIT

Persistent semantic memory for GitHub Copilot in VS Code.

A local MCP server that gives Copilot durable, project-scoped memory across sessions. Memories are stored in an embedded ChromaDB vector database with all-MiniLM-L6-v2 embeddings, enabling semantic retrieval (RAG). Everything runs in a single Docker container — no cloud services required.


Why this exists

Copilot starts every session with a blank slate. This MCP server gives it a persistent, searchable knowledge base so decisions, conventions, and context carry over between sessions — all running locally in Docker.


Quick start

docker compose up -d

The server starts on http://localhost:8000/sse.

The .vscode/mcp.json already points Copilot at the server — no further VS Code configuration needed.

A sample config is provided in examples/vscode/mcp.json. Copy it to your project's .vscode/mcp.json.


MCP tools


View the full README on GitHub

Details

Repository
github.com/labforgedev/copilot-memory-mcp
Categories
AI & LLM Tools, Search & Web Crawling
Package
ghcr.io/labforgedev/copilot-memory-mcp:1.0.0
Transport
SSE
Registry
MCP registry, active

Related AI & LLM Tools MCP servers

View all
1mikerawsonnz avatarAuthenticated Multi Llm Agentmikerawsonnz/gosce-agentsGoogle-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f0stars
2csoai-org avatarVector Knowledge Graph Mcpcsoai-org/vector-knowledge-graph-mcpAI-powered vector knowledge graph MCP server for agents. Supports add node, add edge, semantic node0stars
3xultrax-web avatarAgent Memory Mcpxultrax-web/agent-memory-mcpMarkdown memory for AI agents. Files you can read, edit, grep, and commit. Not a database.0stars
4xchucx avatarAgent Memoryxchucx/agent-memoryGit-native project memory for AI coding agents: Markdown source of truth, reviewable, secret-safe.15stars
5fradser avatarSequential Thinkingfradser/mcp-server-mas-sequential-thinkingAn advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.300stars
6aicastle-school avatarAicastle School Openai Api Agent Projectaicastle-school/openai-api-agent-projectFetch current stock prices and key data for symbols across global markets. Look up companies like…11stars