sourcebot-dev/Sourcebot

Sourcebot MCP - Fetch code context from GitHub, GitLab, Bitbucket, and more

The Sourcebot MCP server gives your LLM agents the ability to fetch code context across thousands of repos hosted on GitHub, GitLab, BitBucket and more. Ask your LLM a question, and the Sourcebot MCP server will fetch relevant context from its index and inject it into your chat session. Some use cases this unlocks include:

• Enriching responses to user requests:

  • "What repositories are using internal library X?"
  • "Provide usage examples of the CodeMirror component"
  • "Where is the useCodeMirrorTheme hook defined?"
  • "Find all usages of deprecatedApi across all repos"

• Improving reasoning ability for existing horizontal agents like AI code review, docs generation, etc.

  • "Find the definitions for all functions in this diff"
  • "Document what systems depend on this class"

• Building custom LLM horizontal agents like like compliance auditing agents, migration agents, etc.

  • "Find all instances of hardcoded credentials"
  • "Identify repositories that depend on this deprecated api"

Getting Started

1. Install Node.JS >= v18.0.0.

2. (optional) Spin up a Sourcebot instance by following this guide. The host url of your instance (e.g., http://localhost:3000) is passed to the MCP server via the SOURCEBOT_HOST url. This allows you to control which repos Sourcebot MCP fetches context from (including private repos).

   If a host is not provided, then the server will fallback to using the demo instance hosted at https://demo.sourcebot.dev. You can see the list of repositories indexed here. Add additional repositories by opening a PR.

3. Install @sourcebot/mcp into your MCP client:

   Cursor

   Cursor MCP docs

   Go to: Settings -> Cursor Settings -> MCP -> Add new global MCP server

   Paste the following into your ~/.cursor/mcp.json file. This will install Sourcebot globally within Cursor:

   {
       "mcpServers": {
           "sourcebot": {
               "command": "npx",
               "args": ["-y", "@sourcebot/mcp@latest" ],
               // Optional - if not specified, https://demo.sourcebot.dev is used
               "env": {
                   "SOURCEBOT_HOST": "http://localhost:3000"
               }
           }
       }
   }
   

   Windsurf

   Windsurf MCP docs

   Go to: Windsurf Settings -> Cascade -> Add Server -> Add Custom Server

   Paste the following into your mcp_config.json file:

   {
       "mcpServers": {
           "sourcebot": {
               "command": "npx",
               "args": ["-y", "@sourcebot/mcp@latest" ],
               // Optional - if not specified, https://demo.sourcebot.dev is used
               "env": {
                   "SOURCEBOT_HOST": "http://localhost:3000"
               }
           }
       }
   }
   

   VS Code

   VS Code MCP docs

   Add the following to your .vscode/mcp.json file:

   {
       "servers": {
           "sourcebot": {
               "type": "stdio",
               "command": "npx",
               "args": ["-y", "@sourcebot/mcp@latest"],
               // Optional - if not specified, https://demo.sourcebot.dev is used
               "env": {
                   "SOURCEBOT_HOST": "http://localhost:3000"
               }
           }
       }
   }
   

   Claude Code

   Claude Code MCP docs

   Run the following command:

   # SOURCEBOT_HOST env var is optional - if not specified,
   # https://demo.sourcebot.dev is used.
   claude mcp add sourcebot -e SOURCEBOT_HOST=http://localhost:3000 -- npx -y @sourcebot/mcp@latest
   

   Claude Desktop

   Claude Desktop MCP docs

   Add the following to your claude_desktop_config.json:

   {
       "mcpServers": {
           "sourcebot": {
               "command": "npx",
               "args": ["-y", "@sourcebot/mcp@latest"],
               // Optional - if not specified, https://demo.sourcebot.dev is used
               "env": {
                   "SOURCEBOT_HOST": "http://localhost:3000"
               }
           }
       }
   }
   

   
   

   Alternatively, you can install using via Smithery. For example:

   npx -y @smithery/cli install @sourcebot-dev/sourcebot --client claude
   

4. Tell your LLM to use sourcebot when prompting.

For a more detailed guide, checkout the docs.

Available Tools

search_code

Searches for code that matches the provided search query as a substring by default, or as a regular expression if useRegex is true.

Parameters

Name	Required	Description
query	yes	The search pattern to match against code contents. Do not escape quotes in your query.
useRegex	no	Whether to use regular expression matching. When false, substring matching is used (default: false).
filterByRepos	no	Scope the search to specific repositories.
filterByLanguages	no	Scope the search to specific languages.
filterByFilepaths	no	Scope the search to specific filepaths.
caseSensitive	no	Whether the search should be case sensitive (default: false).
includeCodeSnippets	no	Whether to include code snippets in the response (default: false).
ref	no	Commit SHA, branch or tag name to search on. If not provided, defaults to the default branch.
maxTokens	no	The maximum number of tokens to return (default: 10000). Higher values provide more context but consume more tokens.

list_repos

Lists repositories indexed by Sourcebot with optional filtering and pagination.

Parameters

Name	Required	Description
query	no	Filter repositories by name (case-insensitive).
page	no	Page number for pagination (min 1, default: 1).
perPage	no	Results per page for pagination (min 1, max 100, default: 30).
sort	no	Sort repositories by 'name' or 'pushed' (most recent commit). Default: 'name'.
direction	no	Sort direction: 'asc' or 'desc' (default: 'asc').

read_file

Reads the source code for a given file.

Parameters

Name	Required	Description
repo	yes	The repository name.
path	yes	The path to the file.
ref	no	Commit SHA, branch or tag name to fetch the source code for. If not provided, uses the default branch.

list_tree

Lists files and directories from a repository path. Can be used as a directory listing tool (depth: 1) or a repo-tree tool (depth > 1).

Parameters

Name	Required	Description
repo	yes	The name of the repository to list files from.
path	no	Directory path (relative to repo root). If omitted, the repo root is used.
ref	no	Commit SHA, branch or tag name to list files from. If not provided, uses the default branch.
depth	no	Number of directory levels to traverse below path (min 1, max 10, default: 1).
includeFiles	no	Whether to include file entries in the output (default: true).
includeDirectories	no	Whether to include directory entries in the output (default: true).
maxEntries	no	Maximum number of entries to return before truncating (min 1, max 10000, default: 1000).

list_commits

Get a list of commits for a given repository.

Parameters

Name	Required	Description
repo	yes	The name of the repository to list commits for.
query	no	Search query to filter commits by message content (case-insensitive).
since	no	Show commits more recent than this date. Supports ISO 8601 (e.g., '2024-01-01') or relative formats (e.g., '30 days ago').
until	no	Show commits older than this date. Supports ISO 8601 (e.g., '2024-12-31') or relative formats (e.g., 'yesterday').
author	no	Filter commits by author name or email (case-insensitive).
ref	no	Commit SHA, branch or tag name to list commits of. If not provided, uses the default branch.
page	no	Page number for pagination (min 1, default: 1).
perPage	no	Results per page for pagination (min 1, max 100, default: 50).

list_language_models

Lists the available language models configured on the Sourcebot instance. Use this to discover which models can be specified when calling ask_codebase.

Parameters

This tool takes no parameters.

ask_codebase

Ask a natural language question about the codebase. This tool uses an AI agent to autonomously search code, read files, and find symbol references/definitions to answer your question. Returns a detailed answer in markdown format with code references, plus a link to view the full research session in the Sourcebot web UI.

Parameters

Name	Required	Description
query	yes	The query to ask about the codebase.
repos	no	The repositories that are accessible to the agent during the chat. If not provided, all repositories are accessible.
languageModel	no	The language model to use for answering the question. Object with provider and model. If not provided, defaults to the first model in the config. Use list_language_models to see available options.
visibility	no	The visibility of the chat session ('PRIVATE' or 'PUBLIC'). Defaults to PRIVATE for authenticated users and PUBLIC for anonymous users. Set to PUBLIC to make the chat viewable by anyone with the link (useful in shared environments like Slack).

Supported Code Hosts

Sourcebot supports the following code hosts:

• GitHub
• GitLab
• Bitbucket Cloud
• Bitbucket Data Center
• Gitea
• Gerrit

| Don't see your code host? Open a feature request.

Future Work

Semantic Search

Currently, Sourcebot only supports regex-based code search (powered by zoekt under the hood). It is great for scenarios when the agent is searching for is something that is super precise and well-represented in the source code (e.g., a specific function name, a error string, etc.). It is not-so-great for fuzzy searches where the objective is to find some loosely defined category or concept in the code (e.g., find code that verifies JWT tokens). The LLM can approximate this by crafting regex searches that attempt to capture a concept (e.g., it might try a query like "jwt|token|(verify|validate).*(jwt|token)"), but often yields sub-optimal search results that aren't related. Tools like Cursor solve this with embedding models to capture the semantic meaning of code, allowing for LLMs to search using natural language. We would like to extend Sourcebot to support semantic search and expose this capability over MCP as a tool (e.g., semantic_search_code tool). GitHub Discussion