DeepWiki: repo Q&A

DeepWiki (by Cognition) exposes an MCP server that reads and answers questions about the documentation of any public GitHub repository. It is free, needs no authentication, and is the best first MCP integration to write — the only key you need is the one for your LLM.


Server	`https://mcp.deepwiki.com/mcp`
Auth	none
Tools	`read_wiki_structure`, `read_wiki_contents`, `ask_question`
Model used here	`claude-sonnet-5`

Prerequisites

Python 3.10+
One LLM provider key. This tutorial uses Anthropic; any LiteLLM model with tool-calling support works.

Build it

Install swarms

pip install -U swarms

Set your LLM key

export ANTHROPIC_API_KEY="sk-ant-..."

Only your model provider needs a key. DeepWiki itself is open.

Write a system prompt that forces grounding

An agent with a research tool will still answer from memory unless you tell it not to. This prompt is the difference between a citation and a guess:

DEEPWIKI_SYSTEM_PROMPT = (
    "You are a repository research specialist who uses the DeepWiki MCP "
    "server to answer questions about public GitHub repositories. Inspect the "
    "repository's wiki structure and relevant documentation before responding, "
    "then provide a clear, technically accurate explanation grounded only in "
    "the retrieved material. Cite relevant files, modules, or documentation "
    "sections when available, distinguish verified details from reasonable "
    "inferences, and state clearly when DeepWiki does not provide enough "
    "information to answer a question."
)

Point the agent at the server

from swarms import Agent

agent = Agent(
    agent_name="DeepWiki-Agent",
    agent_description="Answers questions about GitHub repos via DeepWiki MCP.",
    system_prompt=DEEPWIKI_SYSTEM_PROMPT,
    model_name="claude-sonnet-5",
    mcp_url="https://mcp.deepwiki.com/mcp",
    max_loops=1,
)

mcp_url is the entire integration. On startup the agent connects, fetches the server’s tool list, and converts each tool into a function-calling schema the model can use.

Run a task

result = agent.run(
    "Use your DeepWiki tools to explain what the kyegomez/swarms "
    "repository is for and list its main multi-agent structures."
)
print(result)

The complete script

from swarms import Agent

DEEPWIKI_SYSTEM_PROMPT = (
    "You are a repository research specialist who uses the DeepWiki MCP "
    "server to answer questions about public GitHub repositories. Inspect the "
    "repository's wiki structure and relevant documentation before responding, "
    "then provide a clear, technically accurate explanation grounded only in "
    "the retrieved material. Cite relevant files, modules, or documentation "
    "sections when available, distinguish verified details from reasonable "
    "inferences, and state clearly when DeepWiki does not provide enough "
    "information to answer a question."
)

agent = Agent(
    agent_name="DeepWiki-Agent",
    agent_description="Answers questions about GitHub repos via DeepWiki MCP.",
    system_prompt=DEEPWIKI_SYSTEM_PROMPT,
    model_name="claude-sonnet-5",
    mcp_url="https://mcp.deepwiki.com/mcp",
    max_loops=1,
)

result = agent.run(
    "Use your DeepWiki tools to explain what the kyegomez/swarms "
    "repository is for and list its main multi-agent structures."
)
print(result)

What happens when you call `run()`

The agent connects over streamable HTTP, the default transport. You never configure it for this server.
Tools are discovered. The agent asks the server what it exposes and converts each tool to an OpenAI-format function schema.
The model chooses. It typically calls read_wiki_structure to see what exists, then read_wiki_contents or ask_question for the parts that matter.
Results come back into the conversation, and the model writes its answer from them.

The smallest possible version

Strip the system prompt and you still have a working integration — useful for a first smoke test:

from swarms import Agent

agent = Agent(
    agent_name="MCP-Agent",
    model_name="claude-sonnet-5",
    mcp_url="https://mcp.deepwiki.com/mcp",
    max_loops=1,
    max_tokens=16_000,
)

print(agent.run("Use your tools to explain what the kyegomez/swarms repository does."))

Troubleshooting

The agent answers without calling a tool

Two fixes, in order: say “use your tools” in the task, and put the instruction to retrieve before answering in the system prompt. Weaker models need both.

Timeouts on large repositories

read_wiki_contents can take a while on a big repository. One tool call may run for tool_timeout seconds, 120 by default; raise it with mcp_config=MCPConnection(url="https://mcp.deepwiki.com/mcp", tool_timeout=300). mcp_timeout only bounds connecting and sending requests.

cannot import name 'streamablehttp_client'

Your swarms predates mcp 2.x support, which renamed that function. Upgrade with pip install -U swarms; 15.0.1 and later work with both mcp 1.x and 2.x.

Source: examples/mcp/agents/01_deepwiki_repo_qa.py and deepwiki_minimal.py

GitMCP — scope a server to one repository.
Several servers at once — combine DeepWiki with Microsoft Learn.

Index

Basic Examples

Model Providers

Single Agent

Tree of Thoughts

Multi-Agent Examples

Auto Agent Builder

Scheduled Agents

Applications

Research

Technical Analysis

Use Cases

Finance

Voice Agents

Integrations

MCP Tool Integrations

Deployment

CLI

DeepWiki: repo Q&A

Prerequisites

Build it

The complete script

What happens when you call `run()`

The smallest possible version

Troubleshooting

Next

​Prerequisites

​Build it

​The complete script

​What happens when you call run()

​The smallest possible version

​Troubleshooting

​Next

Prerequisites

Build it

The complete script

What happens when you call `run()`

The smallest possible version

Troubleshooting

Next