Bitbucket MCP

io.github.FabianSchurigPublished by GitHub account FabianSchurigv0.20.2Updated Oct 24, 2026

Bitbucket Cloud MCP in Go: complete API auto-generated from spec, customizable prompts.

VerifiedSTDIODesktop onlyCloud & InfrastructureDeveloper Tools

Overview

AI-generated overview

A local MCP server that exposes Bitbucket Cloud operations as tool calls, generated from the live Bitbucket OpenAPI spec.

What you can do
Call Bitbucket Cloud API operations as MCP tools, covering the endpoint groups generated from the live OpenAPI spec, including some internal/undocumented endpoints carried in hand-authored schemas. Work with repositories, projects, tags and other Bitbucket resources through the same generated operation set the project's CLI and Terraform provider use. Authenticate with a Bitbucket API token or OAuth2 access token, optionally with a username for Basic auth.
When to use it
Use it when an AI agent should read or act on Bitbucket Cloud data — repositories, projects, tags and related endpoints — without leaving the assistant. It suits teams already using the project's CLI or Terraform provider who want the same API coverage in agent workflows.
Requirements
Runs as a local process on the user's machine (stdio), distributed as a container image and via Homebrew, APT, RPM, Scoop, Winget and an install script. Needs a Bitbucket Cloud account and the BITBUCKET_TOKEN environment variable; BITBUCKET_USERNAME is required for Basic auth and omitted for workspace/repo access tokens. Network access to Bitbucket Cloud.
Before you install
Requires a Bitbucket API token or OAuth2 access token in BITBUCKET_TOKEN, which grants whatever the token allows on the account or workspace. The tool surface is generated broadly from the API spec, so it likely includes write operations that can change or delete repositories, projects and other Bitbucket data; review before granting a broad token. Requests go to Bitbucket Cloud and, for internal endpoints, to undocumented Bitbucket API paths.

Installation

In SourceWeft

  1. Open Bitbucket MCP in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

bitbucket-cli

[CI] [GitHub Release] [Terraform Registry] [Sonar Quality Gate] [Sonar Maintainability Rating] [Sonar Vulnerabilities] [Sonar Technical Debt] [Sonar Security Rating]

Low-maintenance Bitbucket Cloud tooling built from the live OpenAPI spec: a CLI for software engineers, an MCP server for AI agents, and a Terraform provider for DevSecOps teams.

[!IMPORTANT] https://github.com/FabianSchurig/bitbucket-cli is the canonical repository. If you found this project through the terraform-provider-bitbucket mirror, watch, star, file issues, and contribute in bitbucket-cli.

Start here

AudienceBest fitStart here
DevSecOps engineersTerraform providerTerraform Registry, generated provider docs, example: bitbucket_tags
Software engineers / computer scientistsbb-cliCLI usage guide
AI agents / agent platform usersbb-mcpMCP usage guide

Quick links

Install

Homebrew (macOS & Linux)

To install the CLI tool via our custom tap, tap the repository and explicitly trust the formula to reduce supply chain risks:

bash
brew tap FabianSchurig/tapbrew trust --formula FabianSchurig/tap/bitbucket-clibrew install bitbucket-cli

Or to install the MCP server:

bash
brew tap FabianSchurig/tapbrew trust --formula FabianSchurig/tap/bitbucket-mcpbrew install bitbucket-mcp

(Note: If you previously tapped the old cask, you can safely untap via brew untap fabianschurig/tap before running the command).

APT (Debian / Ubuntu)

Download the .deb package from the latest release and install it. Supported architectures: amd64, arm64.

bash
TAG_URL=$(curl -fsSIL -o /dev/null -w '%{url_effective}' https://github.com/FabianSchurig/bitbucket-cli/releases/latest)VERSION=${TAG_URL##*/}VERSION=${VERSION%%\?*}VERSION=${VERSION%%\#*}VERSION=${VERSION#v}ARCH=$(dpkg --print-architecture)curl -LO "https://github.com/FabianSchurig/bitbucket-cli/releases/download/v${VERSION}/bb-cli_${VERSION}_${ARCH}.deb"sudo dpkg -i "bb-cli_${VERSION}_${ARCH}.deb"

Replace bb-cli with bb-mcp to install the MCP server instead.

RPM (Fedora / RHEL / CentOS)

Download the .rpm package from the latest release and install it. Supported architectures: amd64, arm64.

bash
TAG_URL=$(curl -fsSIL -o /dev/null -w '%{url_effective}' https://github.com/FabianSchurig/bitbucket-cli/releases/latest)VERSION=${TAG_URL##*/}VERSION=${VERSION%%\?*}VERSION=${VERSION%%\#*}VERSION=${VERSION#v}ARCH=$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/')curl -LO "https://github.com/FabianSchurig/bitbucket-cli/releases/download/v${VERSION}/bb-cli_${VERSION}_${ARCH}.rpm"sudo rpm -i "bb-cli_${VERSION}_${ARCH}.rpm"

Replace bb-cli with bb-mcp to install the MCP server instead.

Scoop (Windows)

powershell
scoop bucket add bitbucket https://github.com/FabianSchurig/scoop-bucketscoop install bb-cliscoop install bb-mcp

Winget (Windows)

powershell
winget install FabianSchurig.bb-cliwinget install FabianSchurig.bb-mcp

Install script

bash
curl -fsSL https://raw.githubusercontent.com/FabianSchurig/bitbucket-cli/main/install.sh | sh

See install.sh options for version selection, binary choice (bb-cli, bb-mcp, or all), and custom install directories.

Other methods

MethodCommand
Go installgo install github.com/FabianSchurig/bitbucket-cli/cmd/bb-cli@latest
Dockerdocker pull ghcr.io/fabianschurig/bitbucket-cli:latest
Download binariesGitHub Releases

For full installation details see the CLI usage guide and the MCP usage guide.

What this project is

This repository keeps Bitbucket Cloud tooling maintainable by generating most of the surface area from the live Bitbucket OpenAPI spec.

  • One API description, three user-facing tools: CLI, MCP, and Terraform all come from the same schema pipeline.
  • Thin hand-written runtime: auth, dispatch, output, and Terraform runtime stay generic instead of growing per-endpoint glue.
  • Fast spec adoption: new Bitbucket endpoints flow in through generation instead of large manual rewrites.
  • Maintenance-first design: the main development effort goes into the shared generators and runtime, not duplicated endpoint code.
  • Internal/undocumented endpoints supported the same way: schemas under schema/ can be hand-authored for endpoints that are not in Bitbucket's public OpenAPI spec (for example the project-level branch-restrictions endpoint exposed only via https://bitbucket.org/!api/internal/...). The generators and runtime treat them identically — schema paths may use absolute URLs and the dispatcher passes them through unchanged.

Architecture

mermaid
flowchart LR    A[Live Bitbucket OpenAPI spec] --> B[enrich_spec.py]    B --> C[partition_spec.py]    C --> D[schema/*-schema.yaml]    D --> E[oapi-codegen models]    D --> F[CLI generator]    D --> G[MCP generator]    D --> H[Terraform generator]    E --> I[Shared generated types]    F --> J[bb-cli]    G --> K[bb-mcp]    H --> L[terraform-provider-bitbucket]    I --> J    I --> K    I --> L    M[Hand-written runtime\nauth, dispatch, output, MCP handler, TF runtime] --> J    M --> K    M --> L

In practice:

  • CLI exposes Bitbucket operations as terminal commands.
  • MCP exposes the same operations as tool calls for AI agents.
  • Terraform maps operation groups into generic resources and data sources.
  • Hand-written code stays small on purpose; generated code handles endpoint coverage.

CI pipelines

mermaid
flowchart TD    A[push / pull_request] --> B[ci.yml]    A --> C[terraform-tests.yml]    D[schedule / manual] --> E[schema-sync.yml]    E --> F[Fetch live spec]    F --> G[Regenerate code and docs]    G --> H[Build and test]    H --> I[Tag new version]    I --> J[release.yml]    J --> K[docker.yml]    I --> L[terraform-release.yml]    K --> M[Publish to MCP Registry]
  • ci.yml: builds, lints, vets, runs Go tests, and sends analysis to SonarQube Cloud.
  • terraform-tests.yml: runs mock-based Terraform acceptance and terraform test suites, plus real API tests when credentials exist. See docs/e2e-coverage.md for the current list of endpoints exercised by the real-API tests.
  • schema-sync.yml: daily/manual sync that fetches the live Bitbucket spec, regenerates generated artifacts, rebuilds docs, tests everything, and tags a release when the schema changed.
  • release.yml: publishes tagged binary releases via GoReleaser.
  • docker.yml: builds multi-arch container images for bb-cli and bb-mcp, pushes them to GHCR, publishes their SBOM and CVE reports (see Supply chain: SBOM and CVE reports), and publishes the bb-mcp server to the MCP Registry.
  • terraform-release.yml: mirrors the tagged source into terraform-provider-bitbucket and publishes the Terraform provider release.

Schema sync safety

The live OpenAPI document is treated as an input, not as an authority to delete a working API group because of a transient omission. Three mechanisms keep the daily sync from breaking published surface or itself:

  • Group preservation: when a group extracts with no paths, partition_spec.py preserves its existing populated schema; a genuinely empty or new group is still written normally.
  • Stable operationIds: ids are recorded in the committed lockfile schema/operation-ids.json, keyed by "<method> <path>". An operation keeps its id forever, and ids of removed operations stay reserved — so a sibling endpoint can never inherit an id and silently rename a shipped CLI command, MCP tool, or CRUDConfig reference.
  • Operation retention: Atlassian regularly removes deprecated but still functional endpoints from the published spec. Rather than dropping commands in an automatic patch release, partition_spec.py carries such operations forward verbatim from the committed schema, annotated x-bb-cli-retained: true so the schema diff shows exactly what upstream stopped publishing. Retiring one for good is a deliberate act: delete it from schema/*-schema.yaml, and the invariant tests then flag any hand-maintained mapping (for example in CRUDConfig) that still references it.

Acceptance tests in internal/tfprovider/acceptance_test.go are hand-written and are never deleted by schema generation. Generated Terraform fixtures are regenerated from the surviving resource groups, while the schema-sync build and test gate, including the mock Terraform acceptance suites, must pass before any change is committed or released. The generated real-API coverage report makes missing group coverage visible without requiring manual bookkeeping.

Supply chain: SBOM and CVE reports

Every released container image ships with a Software Bill of Materials and a vulnerability report in standard formats. Both are produced from the exact image digest that was pushed to GHCR.

ArtifactFormatWhere to get it
Image SBOMSPDX 2.3 JSONsbom-bitbucket-cli.spdx.json / sbom-bitbucket-mcp.spdx.json on the matching GitHub Release, or as a signed attestation on the image itself
Image CVE reportGrype JSON + plain-text tablecves-bitbucket-cli.{json,txt} / cves-bitbucket-mcp.{json,txt} on the matching GitHub Release
Source SBOMSPDX JSONAttached to the GitHub Release by release.yml (covers the git tag, not the image)

The SBOM is also attached to the image as a signed, digest-bound GitHub attestation, so consumers can verify and fetch it without any access to this repository:

bash
gh attestation verify oci://ghcr.io/fabianschurig/bitbucket-mcp:latest --owner FabianSchuriggh attestation download oci://ghcr.io/fabianschurig/bitbucket-mcp:latest --owner FabianSchurig

Runtime images are built FROM scratch and contain only the static binary plus CA certificates, so the SBOM is deliberately small and there is no OS package surface to patch.

Vulnerability scan results are additionally uploaded to GitHub code scanning (categories docker-bitbucket-cli and docker-bitbucket-mcp) for maintainers, and the Go module tree is checked by govulncheck in security.yml.

How this differs from DrFaust92/terraform-provider-bitbucket

AspectDrFaust92/terraform-provider-bitbucketFabianSchurig/bitbucket
Maintenance modelHand-written provider resourcesMostly generated from the live Bitbucket OpenAPI spec
ScopeTerraform provider onlyTerraform provider + CLI + MCP server in one canonical repo
API coverage modelCurated, typed resourcesBroad endpoint coverage through grouped generic resources/data sources
Update flowManual feature work per resourceSchema sync pipeline regenerates code and docs
Resource shapeResource-specific typed fieldsGeneric params, response fields, and raw API response
Best fitOpinionated Terraform workflowsTeams that want fast Bitbucket API coverage and shared tooling across Terraform, shells, and AI agents

This project optimizes for breadth, maintenance, and shared infrastructure across interfaces. If you want a heavily hand-modeled Terraform UX, the DrFaust92 provider may feel more familiar. If you want one maintained pipeline that keeps Terraform, CLI, and MCP aligned with Bitbucket Cloud, this repository is designed for that.

Documentation map

Use the short guides on this first page to get started, then switch to the detailed docs for the interface you need.

The Terraform documentation under docs/ is generated. The root README stays focused on orientation, links, architecture, maintenance, and contribution entry points.

Maintenance and contributions

  • Read CONTRIBUTING.md before changing generators or runtime code.
  • Do not hand-edit generated files; fix the generator or schema source instead.
  • Prefer changes that improve the shared pipeline or hand-written runtime across all endpoints.
  • Open issues and pull requests in the canonical bitbucket-cli repository.

Source: README.md at commit fc0acf5

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.20.2LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts