The Sourcebot MCP server gives your LLM agents the ability to fetch code context across thousands of repos hosted on [GitHub](https://docs.sourcebot.dev/docs/connections/github), [GitLab](https://docs.sourcebot.dev/docs/connections/gitlab), [BitBucket](https://docs.sourcebot.dev/docs/connections/bitbucket-cloud) and [more](#supported-code-hosts). 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:
2. (optional) Spin up a Sourcebot instance by following [this guide](https://docs.sourcebot.dev/self-hosting/overview). 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](https://demo.sourcebot.dev/~/repos). Add additional repositories by [opening a PR](https://github.com/sourcebot-dev/sourcebot/blob/main/demo-site-config.json).
**Temporal Filtering**: Use `since` and `until` to filter by repository index time (when Sourcebot last indexed the repo). This is different from commit time. See `search_commits` for commit-time filtering.
**Temporal Filtering**: Use `activeAfter` and `activeBefore` to filter by repository index time (when Sourcebot last indexed the repo). This is the same filtering behavior as `search_code`'s `since`/`until` parameters.
Searches for commits in a specific repository based on actual commit time (NOT index time).
**Requirements**: Repository must be cloned on the Sourcebot server disk. Sourcebot automatically clones repositories during indexing, but the cloning process may not be finished when this query is executed. Use `list_repos` first to get the repository ID.
**Date Formats**: Supports ISO 8601 dates (e.g., "2024-01-01") and relative formats (e.g., "30 days ago", "last week", "yesterday").
| `repoId` | yes | Repository identifier: either numeric database ID (e.g., 123) or full repository name (e.g., "github.com/owner/repo") as returned by `list_repos`. |
| `query` | no | Search query to filter commits by message (case-insensitive). |
| `since` | no | Show commits after this date (by commit time). Supports ISO 8601 or relative formats. |
| `until` | no | Show commits before this date (by commit time). Supports ISO 8601 or relative formats. |
| `author` | no | Filter by author name or email (supports partial matches). |
| `maxCount` | no | Maximum number of commits to return (default: 50). |
Currently, Sourcebot only supports regex-based code search (powered by [zoekt](https://github.com/sourcegraph/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](https://docs.cursor.com/context/codebase-indexing) 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](https://github.com/sourcebot-dev/sourcebot/discussions/297)
