# Unblocked

Supplies coding assistants with background details from code, pull requests, tickets, and team chats. It helps agents find answers backed by citations.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 16
- Author: unblocked
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/unblocked/skills
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/mcp/unblocked

## What it does

The hosted server links your coding tool to `https://getunblocked.com/api/mcpsse`. It exposes two operations: `context_research` and `context_get_urls`. The research tool investigates codebases, task trackers, and documentation to prepare answers with source citations. The URL utility extracts text directly from specified web links.

The client must handle OAuth. A configured Unblocked workspace is mandatory before connecting. Filtered search commands for pull requests and tickets rely on the standalone Unblocked CLI instead of this remote MCP endpoint.

## Requirements
- Remote server: `https://getunblocked.com/api/mcpsse`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http unblocked-mcp https://getunblocked.com/api/mcpsse
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add unblocked --url https://getunblocked.com/api/mcpsse
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "unblocked": {
            "url": "https://getunblocked.com/api/mcpsse"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "unblocked": {
            "type": "http",
            "url": "https://getunblocked.com/api/mcpsse"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http unblocked https://getunblocked.com/api/mcpsse
```

## When to use it
- investigate past architecture decisions through merged pull requests
- fetch project context with direct source citations
- extract text from external links using `context_get_urls`
- trace bug history across tickets and team conversations

## Example prompts
- Use context_research to investigate why we altered the authentication flow.
- Search team discussions about database connection drops on the staging cluster.
- Fetch content from the incident URL and summarize the findings.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md