@jestay/bitbucket-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BITBUCKET_EMAIL | Yes | Atlassian account email | |
| BITBUCKET_API_TOKEN | Yes | Atlassian API token with required scopes | |
| BITBUCKET_WORKSPACE | No | Default workspace so tools don't need it per call |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_pull_requestsA | List pull requests of a repository, filtered by state (default OPEN). Returns a summary per PR: id, title, author, branches, state, comment count and last update. Paginated; |
| get_pull_requestA | Get full metadata of a pull request: title, description, author, branches with commit hashes, state, and reviewers with their approval status. |
| get_pull_request_diffA | Get the unified diff of a pull request as plain text. This is the primary input for a code review. |
| get_file_contentA | Get the raw content of a file at a given ref (branch name, tag or commit hash). Useful to see full context beyond the diff hunks during a review. |
| list_pull_request_commentsA | List the comments of a pull request (general and inline). Use it before posting review comments to avoid repeating observations already made. Paginated; |
| create_pull_request_commentA | Posts publicly visible content to Bitbucket — do NOT call this tool unless the user has explicitly approved the exact comment text. Post a comment on a pull request. Three modes: general (only |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: listing PRs, getting PR metadata, getting the diff, reading file content, listing comments, and posting comments. There is no overlap or ambiguity between them.
All tool names follow a consistent verb_noun pattern using snake_case, such as list_pull_requests, get_pull_request_diff, and create_pull_request_comment. The naming is uniform and predictable.
With exactly 6 tools, the server is well-scoped for a pull request review workflow. Each tool serves a necessary function without redundancy or bloat.
The tool set covers the full review loop: discover PRs, inspect details and diffs, view file contents for context, check existing comments, and post new feedback. No critical gaps are apparent for the intended purpose.