obot
Complete AI Governance Platform from Obot AI
Obot is an open-source AI governance platform that manages, secures, and audits organizational AI ecosystems through centralized infrastructure. It provides an MCP Gateway for controlled access to MCP servers, an LLM Gateway for model provider connections, sandboxed execution environments for hosted agents and MCP servers, and curated registries for distributing approved tools and skills. The platform enables organizations to govern AI activity across desktop clients like Claude Code, Cursor, and VS Code without forcing standardization on a single model or tool ecosystem. Obot correlates audit logs from user devices, hosted workloads, and gateway traffic to provide comprehensive visibility and policy enforcement.
Key Features
Use Cases
- 01Centrally manage which MCP servers and tools engineering teams can access across different AI clients
- 02Audit and track AI usage, token consumption, and model costs across an organization's workforce
- 03Enforce network egress policies and credential isolation for hosted MCP servers running in production
- 04Distribute approved skills and MCP servers to developers without sharing sensitive API keys
- 05Monitor local AI tool usage on employee devices through Sentry integration with desktop AI clients
- 06Create composite MCP servers that expose selected tools from multiple upstream servers with unified access control
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
obot — FAQ
What is Obot and how does it work with MCP servers?+
Obot is an AI governance platform that acts as an MCP Gateway, proxying access to multiple MCP servers while enforcing policies, managing credentials, and auditing activity. It allows organizations to control which users can access specific MCP tools without requiring each AI client to connect directly to individual servers.
How do I install Obot for development?+
Run Obot locally with Docker by mounting the Docker socket and setting a bootstrap token of at least six characters. After starting the container on port 8080, sign in with the token and configure an authentication provider. For production use, deploy to Kubernetes following the installation guide.
Which AI clients work with Obot?+
Obot supports Claude Code, Codex, Cursor, VS Code, and other AI-enabled IDEs and CLIs through its MCP Gateway. Obot Sentry can monitor and audit local activity in these clients when installed on managed devices.
Does Obot require API keys or authentication providers?+
You need a bootstrap token for initial setup and must configure an authentication provider for user access. Model provider credentials are required only if using the LLM Gateway feature. Obot centralizes these credentials so individual users don't need their own API keys.
Is Obot free and open source?+
Yes, Obot is licensed under the MIT License and available as open-source software. You can self-host it on Docker or Kubernetes at no cost.
Can Obot host MCP servers itself or only proxy external ones?+
Obot can both proxy external MCP servers and host npx, uvx, and containerized MCP servers in sandboxed Docker or Kubernetes environments. Hosted servers run isolated from the main Obot process with configurable network policies.
How do I install obot?+
Open the source repository on GitHub and follow its README. obot is a mcp server — MCP Agents Market links you directly to the official repo.
Is obot free?+
obot is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.