Provides shared team memory for AI agents by capturing decisions from PRDs, Slack, and Jira to brief every session on team standards and skills.
Also known as lockstep-team-agent/lockstep, lockstep, lockstep-cli
- Stars
- 12
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.4.0
- Last commit
- Nov 12, 2026
- License
- Apache-2.0
What is Lockstep AI MCP?
Lockstep AI provides shared team memory for AI agents by capturing decisions from PRDs, Slack, and Jira to brief every session on team standards and skills.
Summary generated from the project's README
About Lockstep AI MCP server
Lockstep AI functions as a shared memory layer designed to provide AI agents with consistent team context. It works by capturing critical decisions from various sources including Jira, Slack, pull requests, and PRDs. Once these decisions are captured, the system requires approval from the relevant owner to ensure accuracy before rolling out specific team standards and skills to your agents.
Developers can integrate this service into any MCP client to brief every session on established protocols. The system includes an opt-in check that flags any new changes which might conflict with previously binding decisions. You can set up the environment using the lockstep-cli via npm, which includes commands for authentication, onboarding, and checking configuration health. For those preferring local infrastructure, the project supports self-hosting through a single docker compose command under the Apache-2.0 license.
What you can do with it
- 1Briefing AI sessions with standardsProvide an AI agent with your team's specific coding standards and skills at the start of a session.
- 2Preventing decision conflictsUse an automated check to identify if new information contradicts existing team decisions.
- 3Centralizing team knowledgeGather and store important project decisions from Slack, Jira, and pull requests for agent access.
Written from the project's README. Every use case is checked against a quote from it.
How to install Lockstep AI MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Lockstep AI MCP in Claude Code
$ claude mcp add lockstep -- npx -y lockstep-cliInstall Lockstep AI MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"lockstep": {
"command": "npx",
"args": [
"-y",
"lockstep-cli"
]
}
}
}Install Lockstep AI MCP in VS Code
.vscode/mcp.json
{
"servers": {
"lockstep": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"lockstep-cli"
]
}
}
}Install Lockstep AI MCP in VS Code CLI
$ code --add-mcp '{"name":"lockstep","type":"stdio","command":"npx","args":["-y","lockstep-cli"]}'Install Lockstep AI MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"lockstep": {
"command": "npx",
"args": [
"-y",
"lockstep-cli"
]
}
}
}Install Lockstep AI MCP in Codex
$ codex mcp add lockstep -- npx -y lockstep-cliInstall Lockstep AI MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.lockstep] command = "npx" args = ["-y", "lockstep-cli"]
Install Lockstep AI MCP in Gemini CLI
$ gemini mcp add -s user lockstep npx -- -y lockstep-cliInstall Lockstep AI MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"lockstep": {
"command": "npx",
"args": [
"-y",
"lockstep-cli"
]
}
}
}Configuration
LOCKSTEP_VENDORAgent vendor label used for session registration (e.g. claude-code, cursor). Optional; defaults to unknown.
| Name | Description | |
|---|---|---|
| LOCKSTEP_VENDOR | Agent vendor label used for session registration (e.g. claude-code, cursor). Optional; defaults to unknown. |
Automated checks
Ran Nov 13, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablelockstep-team-agent/lockstep is public and reachablegithub.com/lockstep-team-agent/lockstep ↗Pass
- Package names this repository as its sourcelockstep-cli names lockstep-team-agent/lockstep as sourcenpmjs.com/package/lockstep-cli ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-12github.com/lockstep-team-agent/lockstep ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from lockstep-cliPass
- No critical advisory in the package or its dependencies133 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHublockstep-cli
The CLI for Lockstep AI: shared team memory for Claude Code.
Lockstep captures decisions from PRDs, Slack, Jira, and pull requests, gets each one approved by its owner, rolls out your team's standards and skills, and briefs every Claude Code session at start. Any MCP client can call the same tools. An opt-in check flags changes that may conflict with a binding decision.
Install
npm install -g lockstep-cli
Quick start
lockstep login # authenticate
lockstep onboard # one step: wire up hooks + MCP for your agent, link this repo
lockstep status # check auth + config health
Full setup, MCP configuration, and self-hosting (Apache-2.0, one docker compose up):
- Website: https://www.getlockstep.dev
- How it works: https://www.getlockstep.dev/how-it-works
- Source: https://github.com/lockstep-team-agent/lockstep
Star the repo
If Lockstep helps your team, star it on GitHub so other teams can find it.
License
Apache-2.0
Lockstep AI MCP questions
How do I add Lockstep AI MCP to Claude Code?
Run claude mcp add lockstep -- npx -y lockstep-cli in your terminal. Add --scope user to make it available in every project.
How do I add Lockstep AI MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What does Lockstep AI do?
It captures decisions from PRDs, Slack, Jira, and pull requests to brief Claude Code sessions on team standards and skills.
Can I use Lockstep with other MCP clients?
Yes, any MCP client can call the same tools provided by Lockstep.
How do I install the Lockstep CLI?
You can install it globally using npm with the command npm install -g lockstep-cli.