mcpField
D
drone-ci-mcp

drone-ci-mcp

Local
github.com/madappa-sharathDeveloper Tools6Updated 72w ago

About drone-ci-mcp

drone-ci-mcp is a read-only MCP server for developers and DevOps teams that need Drone CI build details and step logs. It returns build information as YAML and logs as Markdown.

Key features

  1. 01Look up Drone CI build information
  2. 02Retrieve logs for a build step
  3. 03Return build details as YAML
  4. 04Return step logs as Markdown

Use cases

  1. 01Inspect a Drone CI build result
  2. 02Review logs for a failed pipeline step

MCP support

Exposes read-only Drone CI build information and step logs as MCP tools. It connects using a server URL and access token.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

drone-ci-mcp

An opinionated mcp server that exposes drone.io ci build information and logs as MCP. Will only support readonly features.

Warning

Still Under Active Development, use at your own risk

Usage

Launch the transport
npx -y drone-ci-mcp --access-token=<access-token-from-drone> --server-url=<url>
Claude Settings
{
  "mcpServers": {
    "drone-ci-mcp": {
      "command": "npx",
      "args": [
        "-y"
        "drone-ci-mcp",
        "--access-token=<token>",
        "--server-url=<url>"
      ]
    }
  }
}
MCP Inspector
npx @modelcontextprotocol/inspector npx -y drone-ci-mcp --access-token=<token> --server-url=<url>

Tools

drone_build_info

Readonly tool that looks up a build information and returns the output as YAML.

Inputs:

  1. repoSlug - The slug of the repository in drone. Combination of owner/org and repository name seperated by '/', i.e. owner/repo
  2. buildNumber - The drone CI build number

Outputs:

Response from https://docs.drone.io/api/builds/build_info/ as Mardown + YAML

# Build **1** in **<repo slug>**

```yaml
id: 1
repo_id: 5
trigger:<trigger>
number: 1
status: success
event: custom
action: ''
link: >-
  https://github.com/<commit-link>
timestamp: 0
message: <commit message>
before: dbde12a8600cb6591f4c84085acb95d08b5505e6
after: dbde12a8600cb6591f4c84085acb95d08b5505e6
ref: refs/heads/main
source_repo: ''
source: main
target: main
author_login: <username>
author_name: <name>
author_email: <email>
author_avatar: <avatar>
sender: madappa-sharath
started: 1745806907
finished: 1745806908
created: 1745806904
updated: 1745806907
version: 3
stages:
  - id: 1
    repo_id: 5
    build_id: 1
    number: 1
    name: hello-world
    kind: pipeline
    type: docker
    status: success
    errignore: false
    exit_code: 0
    machine: drone-runner-65d8dd8798-rf8xr
    os: linux
    arch: arm64
    started: 1745806907
    stopped: 1745806908
    created: 1745806904
    updated: 1745806908
    version: 4
    on_success: true
    on_failure: false
    steps:
      - id: 1
        step_id: 1
        number: 1
        name: clone
        status: success
        exit_code: 0
        started: 1745806907
        stopped: 1745806908
        version: 4
        image: drone/git:latest
        .....
```
drone_build_info

Readonly tool that looks up a logs for a step.

Inputs:

  1. repoSlug - The slug of the repository in drone. Combination of owner/org and repository name seperated by '/', i.e. owner/repo
  2. buildNumber - The drone CI build number
  3. stageNumber - The build stage number. Indicated by the field 'number' on a stage
  4. stepId - The build step id. Indicated by the field 'step_id' on a step

Outputs:

Response from https://docs.drone.io/api/builds/build_logs/ as Mardown

# Logs for step 2 in stage **1** of **1** build in **<repo slug>** repository

```shell
+ echo 'hello-world'
,hello-world
```

Demo

screen shot of tool use in claude - page 1 screen shot of tool use in claude - page 2

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.