AI Clients
This guide explains how to connect your AI clients to the MCP servers provided by Develocity. To enable the MCP servers on your Develocity installation, see the Installation Manual.
Permissions
Both MCP servers require an access key whose user has the Access build data via the API and MCP permission.
This permission is included in the default Developer role.
The Develocity Analytics MCP Server additionally requires access to build data across all projects, because Develocity Analytics data isn’t subject to project-level access control.
This cross-project access is granted by either the Read all build data with or without an associated project or the Access all data with or without an associated project permission.
|
Both MCP servers validate the access key and its permissions at the start of every request, including when listing the available tools.
A request made without a valid access key, or with one that lacks the |
You can check your permissions by visiting the /settings/access page when logged in to Develocity.
For detailed instructions on generating access keys, see the Develocity API user manual.
MCP Client Configuration
Configure your AI client with a single MCP server pointed at your Develocity instance with the path /mcp, for example, https://develocity.example.com/mcp.
If you are using Develocity Reporting via Athena Data Export, the Develocity Analytics MCP tools are available directly from the Develocity MCP Server at /mcp, subject to the user’s permissions. No additional client configuration is required.
If you are using the Develocity Reporting Kit, you must configure a separate MCP server hosted by the Reporting Kit at /drv-mcp on the Reporting Kit instance URL.
Each tab below shows the Develocity snippet, with an optional Reporting Kit snippet.
In the snippets below, replace <develocity-url> with your Develocity instance URL (for example, https://develocity.example.com) and <reporting-kit-url> with your Reporting Kit instance URL (for example, https://reporting-kit.example.com).
|
If you use Develocity Reporting via Athena Data Export, configure a single server entry at |
-
Claude Code CLI
-
GitHub Copilot (IntelliJ IDEs)
-
GitHub Copilot (Visual Studio Code)
-
Gemini CLI
-
Gemini in Android Studio
-
Claude Desktop (via npx mcp-remote)
Use the Claude Code CLI to add the MCP server (guide):
claude mcp add --transport http develocity --scope user <develocity-url>/mcp --header "Authorization: Bearer <Develocity Access Key>"
For the Develocity Reporting Kit, add the Analytics MCP Server separately:
claude mcp add --transport http develocity-analytics --scope user <reporting-kit-url>/drv-mcp --header "Authorization: Bearer <Develocity Access Key>"
Use the GitHub Copilot plugin for IntelliJ IDEs to connect to the MCP server (guide).
For the Develocity Reporting Kit, add a separate develocity-analytics entry alongside the develocity entry.
{
"servers": {
"develocity": {
"type": "http",
"url": "<develocity-url>/mcp",
"requestInit": {
"headers": {
"Authorization": "Bearer <Develocity Access Key>"
}
}
},
"develocity-analytics": {
"type": "http",
"url": "<reporting-kit-url>/drv-mcp",
"requestInit": {
"headers": {
"Authorization": "Bearer <Develocity Access Key>"
}
}
}
}
}
Use GitHub Copilot for Visual Studio Code to connect to the MCP server (guide).
Using inputs is recommended to avoid hardcoding the Develocity access key within the JSON configuration.
You will be prompted for your access key the first time you start the server.
For the Develocity Reporting Kit, add a separate develocity-analytics entry alongside the develocity entry.
{
"inputs": [
{
"type": "promptString",
"id": "develocity-access-key",
"description": "Develocity Access Key",
"password": true
}
],
"servers": {
"develocity": {
"type": "http",
"url": "<develocity-url>/mcp",
"headers": {
"Authorization": "Bearer ${input:develocity-access-key}"
}
},
"develocity-analytics": {
"type": "http",
"url": "<reporting-kit-url>/drv-mcp",
"headers": {
"Authorization": "Bearer ${input:develocity-access-key}"
}
}
}
}
Add the following JSON configuration to your Gemini settings file, typically located at ~/.gemini/settings.json.
More details can be found in the documentation.
For the Develocity Reporting Kit, add a separate develocity-analytics entry alongside the develocity entry.
{
"mcpServers": {
"develocity": {
"httpUrl": "<develocity-url>/mcp",
"headers": {
"Authorization": "Bearer <Develocity Access Key>"
}
},
"develocity-analytics": {
"httpUrl": "<reporting-kit-url>/drv-mcp",
"headers": {
"Authorization": "Bearer <Develocity Access Key>"
}
}
}
}
Use Gemini in Android Studio to connect to the MCP server (guide).
For the Develocity Reporting Kit, add a separate develocity-analytics entry alongside the develocity entry.
{
"mcpServers": {
"develocity": {
"httpUrl": "<develocity-url>/mcp",
"headers": {
"Authorization": "Bearer <Develocity Access Key>"
}
},
"develocity-analytics": {
"httpUrl": "<reporting-kit-url>/drv-mcp",
"headers": {
"Authorization": "Bearer <Develocity Access Key>"
}
}
}
}
Claude Desktop doesn’t support connecting to MCP servers using an access key for authentication, which is required by the Develocity MCP servers. To use the MCP servers with Claude Desktop, configure a local MCP proxy that converts the streamable HTTP API into the STDIO protocol.
A popular proxy server for this purpose is mcp-remote.
|
Gradle isn’t affiliated with or involved in the development of Please ensure that any third-party software you install complies with your organization’s security policies. |
Modify the Claude Desktop configuration file ( in settings) with the following, replacing <develocity-url> and <Develocity Access Key>.
For the Develocity Reporting Kit, add a separate develocity-analytics entry alongside the develocity entry.
{
"mcpServers": {
"develocity": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"<develocity-url>/mcp",
"--header",
"Authorization: Bearer ${API_ACCESS_TOKEN}",
"--transport",
"http-only"
],
"env": {
"API_ACCESS_TOKEN": "<Develocity Access Key>"
}
},
"develocity-analytics": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"<reporting-kit-url>/drv-mcp",
"--header",
"Authorization: Bearer ${API_ACCESS_TOKEN}",
"--transport",
"http-only"
],
"env": {
"API_ACCESS_TOKEN": "<Develocity Access Key>"
}
}
}
}
Usage Tips
Recommended Models
After testing the MCP servers against a variety of models, use the latest or frontier version of your selected model where possible.
Testing has shown the "light" versions of these models are capable of basic analysis. However, they’re more prone to making mistakes and generally provide worse results than the frontier versions of the models.
Avoiding Common Issues With LLMs
When using the Develocity Analytics MCP Server, briefly inspect the SQL queries submitted by the LLM to the MCP server to catch obvious errors.
Long conversations with many different lines of questioning or analysis may lead to the model’s responses becoming gradually worse. Consider starting a new session or clearing the model’s context to fix this when it happens.
Authentication Troubleshooting
Authentication or access key errors may be interpreted by client applications as a trigger to initiate the OAuth access flow. If you begin to see messages or errors related to authentication or OAuth, verify that your access key configuration is correct, the key is valid, and the associated Develocity user has the required permissions.
Some clients may need a restart for MCP configuration to be correctly updated.
Example Usage
Develocity MCP Server
Here are some example prompts you can use with Develocity MCP Server:
-
What are the most flaky tests from this week?
-
What different kinds of failures happened on CI on my branch?
-
What was the cause of the most recent failed build?
-
How can I make builds for this project faster?
Develocity Analytics MCP Server
Here are some example prompts you can use with Develocity Analytics MCP Server:
-
Are any projects using a version of log4j earlier than 2.17.1?
-
Which projects are using a non-LTS JDK version?
-
What tasks should I prioritize fixing to stabilize my CI builds?
-
Can you identify whether some users are impacted more by locally failing builds than others?
-
What’s the typical configuration time for local builds?
-
Which are the longest-running tasks in my CI builds?
-
What are the top 5 slowest builds in the last week?