crewkit
MarketplaceFeaturesPricingDocsGitHub
Sign InGet Started
crewkitInstallationQuickstartConfigurationTroubleshootingFAQ

Usage

TUICLIDashboardAnalytics

Collaborate

ArtifactsSession sharingBlueprintsAgent identitiesMCP server

Configure

AgentsSkillsRulesCommandsInheritancePlaybooksExperimentsHooksTeamWorkspaces

API Reference

API OverviewAuthenticationSessions APIResources APIOrganizations APIProjects APIPlaybooks APIExperiments API

MCP server

Expose your project's institutional memory to any MCP-capable agent with crewkit mcp serve.

crewkit works with Claude Code today — and any MCP-capable agent can pull project context through the crewkit MCP server. Project memory, conventions, prior work, active work, and blueprint state become tools the agent can call mid-session.


Automatic registration

Sessions launched with crewkit code register the crewkit MCP server automatically — there is nothing to configure. The tools below are available in every session.


Manual registration

crewkit mcp serve runs a stdio MCP server. Register it in any MCP-capable client:

{
  "mcpServers": {
    "crewkit": {
      "command": "crewkit",
      "args": ["mcp", "serve"]
    }
  }
}

The server resolves your organization and project from the git remote of the working directory. Override when that's not possible:

crewkit mcp serve --org <org-id> --project <project-id>

Or via the CREWKIT_ORG_ID and CREWKIT_PROJECT_ID environment variables.

Authentication uses your CLI login (crewkit auth login). If you're signed out, tool calls return an actionable error instead of failing silently.

The server implements MCP 2026-07-28 (stateless lifecycle, server/discover) and remains compatible with clients speaking 2025-11-25 and earlier — including current Claude Code — via the standard initialize handshake. Both paths serve the same tools identically.


Available tools

ToolWhat it does
search_project_contextHybrid lexical + semantic search over project memory: uploaded docs, meeting transcripts, captured Slack messages, Drive imports, and indexed past sessions
find_prior_workFind past conversations where someone already worked on something similar — avoid re-solving solved problems
get_active_workWho's working on what right now: open conversations and claimed blueprint tasks, grouped by user
get_conventionsThe playbook conventions that apply to this project's stack — coding standards, legacy patterns, severity-tiered rules
get_blueprint_stateThe active blueprint: progress, epics, task statuses, and the caller's assigned tasks
save_stateSave a session handoff as your rolling personal save state (the agent is instructed to show it to you for approval first)
load_stateLoad a save state: your personal handoff, or the most recent team digest
share_updateBroadcast a short, milestone-level update so teammates' sessions can avoid overlapping work

What this means in practice

Mid-session, an agent can ask "has anyone touched this before?", check which conventions govern a decision, see whether a teammate already claimed the task, and pick up exactly where the last session left off. crewkit's memory works wherever your agents do.


Next steps

  • Artifacts and project memory
  • Blueprints
  • Playbooks

Agent identities

Give a project an agent teammate with its own Slack handle.

Agents

Configure specialized AI assistants for your team.

On this page

Automatic registrationManual registrationAvailable toolsWhat this means in practiceNext steps
crewkit

crewkit is the institutional memory and governance layer for AI-assisted engineering: agents work as teammates, prior work is one search away, and every session is attributed to the exact agent version that ran it.

Product

  • Marketplace
  • Features
  • Pricing
  • Documentation

Resources

  • GitHub
  • Changelog
  • Report Issue
  • System Status

Company

  • About
  • Privacy
  • Terms

© 2026 Karibew Inc. All rights reserved.

Command Palette

Search conversations, projects, playbooks, and more