Dosu MCP Server

The Dosu MCP Server provides coding agents with direct access to your team's knowledge via the Model Context Protocol. Instead of guessing from training data, an agent can search your Documents, ask across your Sources, and pull in answers that your team has already written. This page covers what the server exposes, which clients work with it, how to connect, and the workflow that gets the best results.

What it is#

MCP (Model Context Protocol) is an open standard that lets AI agents call external tools. The Dosu MCP Server is a hosted MCP endpoint that exposes your organization's knowledge as a set of tools an agent can use mid-task. It is managed from the MCP servers page in the Dosu app, where each server is scoped to the Sources you select.

The same server also carries built-in knowledge from hundreds of public open source libraries (projects like Airflow, vLLM, Prisma, and Zod). That gives an agent grounded context about your dependencies, not just your own code.

Why it matters#

Coding agents are only as good as the context they are given. Run them at scale, and the cost adds up. Agents re-read the same files, miss decisions buried in past issues and chat, and produce inconsistent work because each one starts cold. The Dosu MCP Server provides every agent with a shared source of truth, so answers stay consistent across people, repos, and tools, and knowledge lost to turnover remains accessible.

Tools the server exposes#

The server provides a focused set of tools. The most used ones:

init_knowledge searches your curated knowledge (approved answers and Topics) for context on a task. Call this first.
list_available_data_sources lists the Sources an agent can query, returning their IDs and descriptions (GitHub repos, Slack channels, documentation, and more).
ask runs a multi-step agent across selected Sources and returns a synthesized answer with citations. It is the most thorough tool and the slowest, so reach for it when you need a cross-source answer.
search_documentation searches raw documentation Sources and returns summaries with source IDs.
fetch_source retrieves the full content of a source by its ID, with optional line ranges for large files.

For knowledge that lives in public open source projects, find_public_library lists and filters the public Libraries Dosu indexes, and ask_public_library answers questions about a specific one by its slug.

Agents can also write back. generate_documentation creates a new Document from your Sources, and update_documentation applies targeted edits to an existing one. Both run in the background, and the drafts they produce land in Review so your team can approve, edit, or decline them before anything is published.

Supported clients#

The Dosu MCP Server works with any MCP-compatible client, including:

Claude Code
Cursor
VS Code Copilot

Each server in the MCP servers page shows copy-paste connection instructions for these clients.

How to connect#

The fastest path is the Dosu CLI, which configures your client for you.

Open the MCP servers page. A default server is created with your organization and linked to your Sources. To scope a server to specific Sources, create a new one and select them.
Run the setup command in your terminal:
```
npx @dosu/cli setup
```
If you prefer Homebrew, install the CLI with brew install dosu-ai/dosu/dosu, then run dosu setup. To target a specific server, append --deployment <your-deployment-id>.
Follow the prompts to pick your client and authenticate. Restart the client if it does not pick up the new server right away.

Manual configuration#

If you would rather configure a client by hand, the server uses HTTP transport. Use the path-based endpoint shown on the MCP servers page:

https://api.dosu.dev/v1/mcp/deployments/<your-deployment-id>

For authentication, OAuth is recommended where the client supports it, since it handles credential rotation for you. Clients without OAuth can authenticate with an API key passed in the X-Dosu-API-Key header. Create one in Settings, Account, API keys.

Recommended workflow#

For grounded answers, have your agent move from broad to specific:

init_knowledge to load curated context for the task.
list_available_data_sources to see what is connected.
ask against the relevant Sources when you need a synthesized, cited answer.

Use search_documentation and fetch_source in between when you want to pull exact passages rather than a synthesized answer.

Notes#

A server only reaches the Sources selected for it, so scope servers to match what each agent should see.
The CLI also installs hooks that automatically inject Dosu knowledge into Claude Code. See the Dosu CLI guide.