productivity MCP Server
Persistent shared memory and coordination MCP server for multi-agent AI workflows. The memory component of the Junto system. MongoDB + ChromaDB. Production-tested with 6+ agents over 500+ sessions.
Discovered via github-topic:mcp-server and last synced 3mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
E[(External DBs)] ``` The server runs as a single Docker Compose stack. AI agents connect over MCP (streamable HTTP transport on port 8080). All knowledge, messages, and coordination state are persisted across restarts in MongoDB and ChromaDB volumes. --- ## Install — Hand It to Your AI This server is designed for AI coding agents, so the install procedure is too. Clone the repo, then ask your agent to install it for you: ```bash git clone https://github.com/tlemmons/mcp-shared-memory.git cd mcp-shared-memory # Now hand the prompt below to your AI agent in a fresh session. ``` Copy this prompt to a fresh Claude Code (or Cursor, or any MCP-capable agent) session in the cloned directory: > Install the MCP Shared Memory Server in this repository for me. Read `AGENT_INSTALL.md` and follow it step by step. Use the root-level `docker-compose.yml`. Stop and confirm with me before any destructive operation, before any change that needs a real value (passwords, API keys, port choices), and before enabling auth. When the install is done, run the smoke test described in the doc and report all six done-when results back to me. The agent walks through prerequisites, env-file configuration, container start, health check, and MCP-client config — pausing at the right places to ask you for decisions (passwords, ports, auth on/off). **Why this way?** The install has accumulated enough operational gotchas — Chroma volume mount path, Mongo init credentials, the auth env-var with soft-fallback, the difference between localhost and remote-host trust models — that a 6-line quickstart misleads more often than it helps. `AGENT_INSTALL.md` is dense, branchy, and tested against the actual current code; an agent reads and executes it in a few minutes. If you don't trust an AI agent to run the install, this server is probably not for you — its whole purpose is to coordinate fleets of AI agents working on real codebases. **Manual install:** `AGENT_INSTALL.md` is human-readable too. It's denser than typical README prose, but follow it the same way and the install works. After install, MongoDB listens on `localhost:27019`, ChromaDB on `localhost:8001`, and the MCP server on `localhost:8080`. ### Your First Session Once connected, your agent's first interaction looks like this: ``` Agent: memory_start_session(project="my-app", claude_instance="main") → Returns: session ID, any prior learnings, active work, handoff notes Agent: memory_record_learning( session_id="...", topic="postgres connection pooling", content="PgBouncer silently drops connections after 5 min idle. Must set keepalive_idle=60 in connection string or requests fail with 'server closed the connection unexpectedly'." ) → Stored. Next session, memory_start_session returns this automatically. Agent: memory_register_function( session_id="...", name="retry_with_backoff", file_path="src/utils/resilience.py:42", purpose="Retry async calls with exponential backoff and jitter", gotchas="Max 5 retries. Raises RetryExhausted, not the original exception." ) → Registered. Any future agent asking "how do we handle retries?" finds this via memory_find_function. ``` Three calls. Your agent now has persistent memory, and every future session starts with context instead of a blank slate. --- ## Connecting Your AI ### Claude Code Add to `~/.claude.json` (or your project's `.mcp.json`): ```json { "mcpServers": { "shared-memory": { "type": "http", "url": "http://localhost:8080/mcp" } } } ``` > **Note on transport naming:** the underlying MCP protocol is "streamable HTTP", but the value in the JSON config file is `"http"` for Claude Code 2.x. Using `"streamable-http"` in the config triggers a schema validation error. ### Cursor Add to `.cursor/mcp.json` in your project root: ```json { "mcpServers": { "shared-memory": { "type": "http", "url": "http://localhost:8080/mcp" } } } ``` ### Any MCP-Compatible Client Point your client to the MCP endpoint: ``` URL: http://localhost:8080/mcp Transport: Streamable HTTP (stateless) ``` **Stdio transport** is also supported for clients that prefer it. Pass `--transport stdio` when starting the server: ```bash # From the project root: python server.py --transport stdio # Or as a module (from the src/ directory): python -m shared_memory --transport stdio ``` Example MCP client config for stdio mode: ```json { "mcpServers": { "shared-memory": { "type": "stdio", "command": "python", "args": ["-m", "shared_memory", "--transport", "stdio"], "cwd": "/path/to/mcp-shared-memory/src" } } } ``` No API keys or authentication tokens are required for local use (see [Security](#security) for remote deployments). --- ## Tool Reference 48 tools organized into 14 categories. (For the canonical, current list with grouping and end-to-end flows, see the architecture spec inside the server: `memory_get_spec(name="architecture:shared-memory-v1", project="shared_memory")`.) ### Session Management (2)
Add a task, feature request, or tech debt item to the backlog.
Track message lifecycle: pending, delivered, received, completed, failed.
View functions awaiting librarian enrichment.
`mcp_orchestrator`
Enforce read-only queries.
Store a new document (architecture, API spec, code snippet, interface contract, etc.).
View current file locks with stale detection (inactive > 30 min).
Get pending messages for your agent. Scoped by project.
Search for functions by purpose or name. Check before implementing to avoid duplication.
`changeme`
`false`
Standard agent access, scoped to assigned projects
Typical MCP Memory Server
Description
Mark a backlog item as done or won't-do, with optional resolution notes.
Discover registered agents across projects with roles and last activity.
Create or update a versioned spec with owner-only enforcement. Supports semver and history.
Read-only queries against registered external databases. Actions: `list`, `schema`, `query`. SQL injection protection built in.
Bulk archive all documents matching a tag (e.g., end-of-version cleanup).
`localhost`
Access
Record a summary, files modified, and handoff notes. Releases all locks. Call this when done.
List all projects with document counts. No session required.
Yes — Read-only SQL queries (MSSQL, MySQL) against your project databases
Register a session and receive context: recent learnings, active agents, file locks, pending signals. Call this first.
Search across all projects and shared collections at once.
List backlog items with filters: project, status, priority, assignee, milestone.
No
Quick shortcut to record a learning, gotcha, or technique for other agents.
Mark a message as received (shortcut for status update).
Add deep analysis to a function ref: signature, parameters, side effects, complexity. For librarian use.
Manage projects and agents. Actions: `create`, `get`, `list`, `delete`, `add_agent`, `remove_agent`, `update_agent`.
Manage API keys and view audit logs. Actions: `create_key`, `revoke_key`, `list_keys`, `audit_log`, `auth_status`. Requires owner role when auth is enabled.
Yes — MongoDB + ChromaDB vector search
Search the knowledge base by natural language. Returns relevant docs with relevance scores.
Atomically lock files for exclusive editing. Supports directory locks. Auto-releases on session end.
Retrieve a spec by name, optionally at a specific historical version.
Bulk restore previously archived documents by tag.
`8001`
Full access — manage API keys, guidelines, all projects
Retrieve a specific document by its exact ID.
Release specific file locks or all locks held by your session.
Send a message to another agent. Supports categories (task, question, blocker, etc.) and threading.
Register a function reference with name, file, purpose, and optional gotchas. Triggers librarian enrichment.
List all specs with optional version history and type filtering.
Manage behavioral rules that all agents receive at session start. Actions: `list`, `set`, `delete`, `get`. Update once, every agent on every machine picks it up.
Default
Manage backlog, specs, functions, messaging across all projects
Update a backlog item's status, priority, assignee, or description.
Get heartbeat status of agents. Flags agents stale after 5 minutes.
Change a document's status: active, deprecated, superseded, archived. Preserves history.
Send a heartbeat with your current status (idle, busy, error). Enables stale detection.
Get a prompt and unenriched functions to run local enrichment on your machine.
Shared checklists for launch readiness, deploy steps, etc. Actions: `create`, `get`, `add`, `check`, `delete`, `list`.
Update your current work status and files touched. Enables overlap detection and dependency signaling.
`localhost`
Query timeout in seconds.
`mcp_orch`
External database port.
Query and search only, no writes
`27019`
Maximum rows returned per query.
Persistent memory system for Claude Code. Two-layer architecture (hot cache + knowledge wiki), safety hooks, /close-day end-of-day synthesis. Zero external dependencies.
Detect and exploit NoSQL injection vulnerabilities in MongoDB, CouchDB, and other NoSQL databases to demonstrate authentication bypass, data extraction, and unauthorized access risks.
Done-for-you .faf generator. One-click AI context for any project - new, legacy, or famous. Auto-detects stack, scores readiness, works everywhere.
Especialista profundo em Claude Code - CLI da Anthropic. Maximiza produtividade com atalhos, hooks, MCPs, configuracoes avancadas, workflows, CLAUDE.md, memoria, sub-agentes, permissoes e integracao com ecossistemas.
When Philosophy meets AI
ClickUp CLI for AI agents
Ota is the open repo-readiness layer for every stack, every team, and every AI agent.
🌌 PARA Workspace is an open-source workspace framework that defines how humans and AI agents organize knowledge and collaborate on projects. It ships as a repo containing a kernel (constitution), CLI tools, and templates — which generates workspaces where you actually work.
Learn how to use the strategy-builder Claude skill. Complete guide with installation instructions and examples.
Learn how to use the Send Email Claude skill. Complete guide with installation instructions and examples.
Learn how to use the sales-alfred Claude skill. Complete guide with installation instructions and examples.