bitbucket-mcp

Provides a Model Context Protocol (MCP) server that lets AI assistants access Bitbucket (Cloud and Server) data and perform operations on repositories and pull requests (read and some write-style actions).

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ DevTools mcp bitbucket ai-agents developer-tools pull-requests scm-integration
⚙ Agent Friendliness
54
/ 100
Can an agent use this?
🔒 Security
64
/ 100
Is it safe for agents?
⚡ Reliability
30
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
75
Documentation
72
Error Messages
0
Auth Simplicity
45
Rate Limits
20

🔒 Security

TLS Enforcement
90
Auth Strength
65
Scope Granularity
55
Dep. Hygiene
55
Secret Handling
55

Uses Bitbucket app passwords or access tokens via environment variables. README suggests creating least-privilege app password permissions (repos read, PR read/write, pipelines read). It also mentions a `BITBUCKET_ENABLE_DANGEROUS` flag to gate dangerous tools, which is a helpful safety control. However, the provided documentation does not describe how errors are surfaced (risk of leaking info), does not state TLS/auth-header behavior explicitly, and provides limited guidance on operational safety/idempotency and rate limits. Dependency hygiene and CVE status are not verifiable from the provided manifest alone.

⚡ Reliability

Uptime/SLA
0
Version Stability
55
Breaking Changes
40
Error Recovery
25
AF Security Reliability

Best When

You want an MCP integration so an AI agent can read Bitbucket repo/PR context and optionally carry out controlled PR management actions.

Avoid When

You need strong production-grade operational guarantees (SLA, documented retry/idempotency semantics) or you cannot accept credential-based authentication over Basic/Auth header mechanisms.

Use Cases

  • List and browse Bitbucket repositories and pull requests for a given workspace
  • Retrieve pull request details and activity for code review context
  • Create and manage pull requests (including draft/publish and merge flows)
  • Comment on pull requests and resolve/update comment threads
  • Approve/unapprove/decline/request-changes on pull requests

Not For

  • Automating destructive repository operations without explicit enabling
  • Acting as a general-purpose Bitbucket API proxy outside MCP use cases
  • Environments where storing long-lived Bitbucket credentials in environment variables is unacceptable

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: BITBUCKET_USERNAME + BITBUCKET_PASSWORD (app password) BITBUCKET_TOKEN (access token)
OAuth: No Scopes: No

Authentication is configured via environment variables. The README indicates app passwords with specific permissions (e.g., repositories read, PR read/write). No OAuth flow is documented.

Pricing

Free tier: No
Requires CC: No

Pricing for the MCP server itself is not described; it is available as an npm package. Bitbucket API usage depends on Bitbucket account limits.

Agent Metadata

Pagination
supports pagelen/page plus an `all` convenience that follows next links with a safety cap (up to 1,000 entries)
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Mutating operations are potentially enabled only when `BITBUCKET_ENABLE_DANGEROUS` is set for dangerous tools; ensure the agent is configured to avoid destructive actions by default.
  • Authentication requires Bitbucket app password or token; incorrect permissions/format typically cause 401s (README provides troubleshooting).
  • The README excerpt contains duplicated pagination guidance for some tools and some tool sections appear truncated in the provided content; verify full tool schemas in the actual repo before relying on them.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for bitbucket-mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered