bitbucket-mcp-server

pipeline-steps

List, inspect, or fetch logs for Bitbucket pipeline steps to review execution details and troubleshoot pipeline runs.

Instructions

Pipeline step operations. Use action: "list" to list all steps, "get" to fetch a single step's metadata, "log" to fetch a single step's log output. step_uuid is required when action is get or log.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "repo_slug": "<repo_slug>",
      "pipeline_uuid": "<pipeline_uuid>",
      "action": "<action>"
    },
    "name": "pipeline-steps"
  }
}

Input Schema

Name	Required	Description
`page`	No	(action=list only) Page number or opaque next page URL
`action`	Yes	Which operation to perform
`pagelen`	No	(action=list only) Items per page (10-100, default 10)
`repo_slug`	Yes	Repository slug/name
`step_uuid`	No	Step UUID. Required when action is `get` or `log`.
`workspace`	No	Bitbucket workspace name. Falls back to BITBUCKET_WORKSPACE env var if not provided.
`pipeline_uuid`	Yes	Pipeline UUID

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.2.0Nov 10, 2026

TDQS

B3.3/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It never states that all three operations are read-only, says nothing about log size/truncation or pagination limits beyond the schema, and gives no auth or permission context for repo-scoped access.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with purpose and then the operation modes, with no filler. The opening fragment 'Pipeline step operations' is slightly redundant with the name but functions as a useful framing sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only 7-parameter tool with fully documented schema and no output schema, the description covers the operation modes and conditional parameter adequately. The missing pieces are behavioral (read-only nature, log truncation, pagination behavior) rather than structural.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the description only restates what the schema already declares — the action enum meanings and that step_uuid is required for get/log. It adds no format, constraint, or interaction detail (e.g., how step_uuid is obtained, whether page applies only to list).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific resource (pipeline steps) and enumerates the three operations, so an agent knows exactly what this tool returns. It does not differentiate from the sibling 'pipelines' tool, leaving the step-vs-pipeline boundary implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The action enum values are explained, which implies when each mode applies, but there is no statement of when to reach for this tool versus 'pipelines' or any prerequisite (e.g., needing a pipeline_uuid from a list call). Guidance is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server