Unblocked is the context layer for agentic software development. It reasons across your code, conversations, issues, docs, product, and production systems so agents can complete work correctly with less human intervention.
Coding agents know the code. They do not know why it was written that way, which of two conflicting docs is current, what a ticket decided, or what production is doing right now. Unblocked gives them that organizational understanding by connecting the context scattered across your code, messaging platforms, issue trackers, documentation, and product and production data, reconciling conflicts between sources, and enforcing the permissions you already set in each tool.
One MCP server replaces a dozen. Context is ranked, compressed, and assembled server-side before it reaches the agent, so the agent reasons over higher-quality input. The result: reliable code that reflects how your team actually builds software, generated with fewer tokens and less back-and-forth.
Works with Claude Code, Cursor, Windsurf, GitHub Copilot, and Codex over MCP, or through the Unblocked CLI and API. Connects to GitHub, GitLab, Slack, Microsoft Teams, Jira, Linear, Confluence, Notion, Google Drive, Sentry, Datadog, and more.
How to use
- 1Add it in ChatGPT
Open Unblocked in ChatGPT's Plugin directory (button above), select + to add it and sign in if asked.
- 2Use it in a chat
Type @ in the composer and pick Unblocked, or start your message with its name. ChatGPT may also suggest it when it fits what you ask.
Skills 2
- unblocked-context-get-urls-mcp
Loads full content for known pull request, issue, document, message, and public web URLs with the context_get_urls MCP tool. Use when the user supplies URLs or a prior search returns URLs that need full-text review. Use context_research when the URL is not known. Do not use for local files or private network URLs.
- unblocked-context-research-mcp
Searches connected code, pull requests, documentation, messages, and issue trackers with the context_research MCP tool. Use for decision history, prior work, team conventions, planning, incident investigation, cross-system questions, or code that is not available in the local workspace. Use local file search when the current implementation alone can answer the question.