MCP server for Bitbucket Server / Data Center with code review, cross-repo PRs, and CI insights
Bitbucket MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. MCP server for Bitbucket Server / Data Center with code review, cross-repo PRs, and CI insights.
Once Bitbucket is connected, these are the calls the assistant has available:
Repositories — The Repositories tool exposed by this serverForks — The Forks tool exposed by this serverUsers — The Users tool exposed by this serverLabels — The Labels tool exposed by this serverWebhooks — The Webhooks tool exposed by this serverKeys — The Keys tool exposed by this serverPrompts — The Prompts tool exposed by this serverResources — The Resources tool exposed by this serverCaching — The server caches frequently accessed data in memory (project lists, repository metadata, default reviewers) to reduce API calls. The cache uses LRUThe server ships on npm as @pavel-kalmykov/bitbucket-server-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
You will need 2 environment variables: BITBUCKET_URL, BITBUCKET_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
npx) - Bun (via bunx) - DockerPlenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Bitbucket's toolset — Repositories, Forks, Users and 6 more — is a fair guide to whether it matches your workflow. It is maintained by GitHub Actions; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| Repositories | The Repositories tool exposed by this server. |
| Forks | The Forks tool exposed by this server. |
| Users | The Users tool exposed by this server. |
| Labels | The Labels tool exposed by this server. |
| Webhooks | The Webhooks tool exposed by this server. |
| Keys | The Keys tool exposed by this server. |
| Prompts | The Prompts tool exposed by this server. |
| Resources | The Resources tool exposed by this server. |
| Caching | The server caches frequently accessed data in memory (project lists, repository metadata, default reviewers) to reduce API calls. The cache uses LRU eviction (max 500 entries) so memory stays bounded, and write operation |
{
"mcpServers": {
"bitbucket-server-1": {
"command": "npx",
"args": ["-y", "@pavel-kalmykov/bitbucket-server-mcp"],
"env": {
"BITBUCKET_URL": "your-value",
"BITBUCKET_TOKEN": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| BITBUCKET_URL | Endpoint or connection string the server talks to. | Yes |
| BITBUCKET_TOKEN | Credential the server authenticates with. | Yes |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.