agentpluginsdirectory
teamshared-ai avatar

teamshared

v0.13.0

by teamshared-ai · author: Loreum Labs Ltd

Shared team memory for Cursor: remote MCP with email/OTP Connect, the recall-first memory rule, and hooks that capture Agent Chat plus failed-tool/preCompact events.

What teamshared does, in the publisher's words

Registers the teamshared MCP server. The Cursor plugin also ships the recall-first memory rule and two Cursor hooks (postToolUse for failed test/lint/shell, preCompact for a short session summary). The Cursor plugin still has no skills, slash commands, extra hooks, or extra agents.

This repo also ships a Claude Code marketplace plugin under claude/ (remote MCP + TEAMSHARED_TOKEN auth). Claude Code does not inherit Cursor Connect.

The native Codex package under plugins/teamshared/ uses the server's MCP OAuth discovery flow and includes a recall-first teamshared-memory skill. A manual Codex TOML setup remains available under install/codex/.

From the project README, punctuation lightly normalized · Open the README on GitHub

Skills
0
MCP servers
1
Stars
0
License
MIT
Repo created
2026-08-15
Last pushed
2026-10-13
Publisher type
Organization
Version
0.13.0

Links

MCP servers · 1

teamsharedhttp
https://teamshared.com/mcp

Read from the plugin's own mcp.json. We list environment variable names, never values.

Category

Agent Tooling. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.

Keywords

teamshared · mcp · memory · agent-memory · shared-brain

Related by publisher and keywords

  • hindsightvectorize-io

    Long-term memory for AI agents. Recalls relevant past context before you answer and retains durable facts as you work, backed by Hindsight's retain/recall/reflect memory engine.

  • compartmentMaxFreedomPollard

    High-security, fully offline, encrypted vector memory for AI agents. AEAD-encrypted vault, locked by default after restart, no API key and no network at runtime.

  • openvikingvolcengine

    Semantic long-term memory and context engine for coding agents. Recall prior knowledge with the find/search/read MCP tools and persist durable facts with remember/write, backed by an OpenViking server.

  • longmemoryCaviraOSS

    Project-scoped durable memory, recall, Skills, and governed context for AI agents.

  • aws-agentsaws

    Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore (Strands, LangGraph), connecting tools via Gateway and MCP, multi-agent and A2A orchestration, memory, Cedar policies, evaluation, observability, debugging traces and logs, and production hardening.

  • powercontextoceanbase

    Reusable PowerContext skills and MCP configuration for agent integrations.

Add the verified badge to your README[![Verified by AgentPluginsDirectory.com against Schema 1.0.0](https://agentpluginsdirectory.com/badge.svg)](https://agentpluginsdirectory.com/plugins/teamshared)

✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.