You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@@ -14,84 +14,225 @@ MCP (Model Context Protocol) is a lightweight middleware protocol (and server) t
14
14
15
15
ReportPortal MCP Server allows to receive summaries of launches and perform various operations without manually opening the UI. The actions that can be performed through the MCP Server are called Tools.
16
16
17
-
Available tools:
18
-
19
-
1. Run Unique Error Analysis
20
-
2. Run Quality Gate
21
-
3. Run Auto-Analysis
22
-
4. Get Test Items by Filter
23
-
5. Get Launches
24
-
6. Launch Force Finish
25
-
7. Launch Delete
26
-
8. Get Test Item Logs by Filter
27
-
9. Get Test Item by ID
28
-
10. Get Test Item Attachments
29
-
11. Get Last Launch by Name
30
-
12. Get Project Defect Types
31
-
13. Update defect types by item IDs
17
+
## Prerequisites
18
+
19
+
### Server Mode (MCP_MODE)
20
+
21
+
First, you need to decide on a strategy for using MCP Server: whether to use it locally or as a remote endpoint. In the second case, first deploy the MCP Server and then configure a connection to it.
22
+
23
+
`MCP_MODE` is a system environment variable that controls the transport mode of the MCP server:
24
+
25
+
| Value | Description |
26
+
|-------|-------------|
27
+
|`stdio`|**(default)** Standard input/output – used for local AI tool integrations (Claude Desktop, Cursor, VS Code Copilot, etc.) |
28
+
|`http`| HTTP/SSE streaming – exposes an HTTP endpoint for remote or multi-client access |
29
+
30
+
This variable is only needed when you want to run the server in HTTP mode. For local AI tool integrations the default `stdio` mode is used and no extra configuration is required.
31
+
32
+
:::important
33
+
`http` mode is intended for server deployments. The MCP server must be **deployed and running** with `MCP_MODE=http` before any AI tool can connect to it remotely.
34
+
:::
35
+
36
+
Before setting up the MCP server, you need the following information from your ReportPortal instance:
37
+
38
+
### ReportPortal Host URL (RP_HOST)
39
+
40
+
The URL of your ReportPortal instance:
41
+
- Example: https://reportportal.example.com
42
+
- For local: http://localhost:8080
43
+
44
+
### Project Name (RP_PROJECT)
45
+
46
+
To find your project name:
47
+
1. Log into ReportPortal
48
+
2. Check the URL: https://your-rp-instance.com/ui/#PROJECT_NAME/...
49
+
3. Or find it in the top-left dropdown menu
50
+
51
+
### API Token (RP_API_TOKEN)
52
+
53
+
You can get an API token from your ReportPortal Profile or generate a new one.
54
+
55
+
:::note
56
+
Never commit tokens to version control or share them publicly.
57
+
:::
58
+
59
+
## Available Tools
60
+
61
+
The MCP Server provides the following tools for interacting with ReportPortal:
62
+
63
+
- Get Launches by filter
64
+
- Get Last Launch by Name
65
+
- Get Launch by ID
66
+
- Run Quality Gate
67
+
- Run Auto Analysis
68
+
- Run Unique Error Analysis
69
+
- Force Finish Launch
70
+
- Delete Launch
71
+
- Get Suites by filter
72
+
- Get Test Items by filter
73
+
- Get Logs by filter
74
+
- Get Attachment by ID
75
+
- Get Test Item by ID
76
+
- Get Project Defect Types
77
+
- Update defect types by item IDs
78
+
79
+
## Installation
80
+
81
+
There are two ways to connect to the ReportPortal MCP Server:
82
+
1.**Locally** - via *Docker* (recommended) or using *pre-built binaries*.
83
+
2.**Connecting to a remote MCP server** (when the server is already deployed)
84
+
85
+
### Local Installation
86
+
87
+
The configurations below use the default `stdio` mode (`MCP_MODE=stdio`), which is the correct choice for all local AI tool integrations.
Refer to the detailed user guide for the [full setup instructions](https://github.com/reportportal/reportportal-mcp-server) of the MCP Server.
300
+
## Verifying Your Setup
301
+
302
+
### 1. Verify Remote MCP Server (if using remote deployment)
303
+
304
+
If connecting to a remote MCP server, verify it's accessible before configuring your AI tool:
305
+
306
+
**Via Browser:**
307
+
```
308
+
http://your-mcp-server-host:port/
309
+
```
310
+
Should return server information and available endpoints.
311
+
312
+
**Via ping (network connectivity only):**
313
+
```bash
314
+
ping your-mcp-server-host
315
+
```
316
+
317
+
**Via curl (MCP protocol test):**
318
+
```bash
319
+
# Test MCP endpoint with JSON-RPC request
320
+
curl -X POST http://your-mcp-server-host:port/mcp \
321
+
-H "Content-Type: application/json" \
322
+
-H "Authorization: Bearer your-api-token" \
323
+
-H "X-Project: YourProject" \
324
+
-d '{
325
+
"jsonrpc": "2.0",
326
+
"method": "tools/list",
327
+
"id": 1
328
+
}'
329
+
```
330
+
331
+
**Expected Results:**
332
+
- Server responds to health checks
333
+
-`/info` returns server configuration
334
+
- MCP endpoint returns list of available tools
335
+
- No connection refused or timeout errors
336
+
337
+
### 2. Verify MCP Server Integration
338
+
339
+
After configuration, verify the AI assistant can communicate with the MCP server:
340
+
341
+
1.**Check Available Tools**: Ask your AI assistant "What ReportPortal tools are available?"
342
+
- Expected: A list of 15 tools including launches, test items, analysis tools, etc.
343
+
344
+
2.**Test Basic Query**: Try "List the 5 most recent test launches"
345
+
- Expected: A formatted list of recent launches with names, statuses, and timestamps.
346
+
347
+
For detailed verification steps, troubleshooting, and developer information, refer to the [full documentation](https://github.com/reportportal/reportportal-mcp-server).
348
+
349
+
## Example Queries
350
+
351
+
Here are some real-world examples of what you might ask your AI after setup:
352
+
353
+
-**"List the 5 most recent test launches."** – returns a paginated list of recent test runs with names and statuses.
354
+
-**"What tests failed in the latest run?"** – shows failed test items for the most recent launch.
355
+
-**"Show me details of launch with ID 119000."** – retrieves a specific launch directly by its ID.
356
+
-**"Run quality gate on launch 12345."** – executes quality gate analysis to verify if launch meets defined quality criteria.
357
+
-**"Run an analysis on launch ABC."** – triggers the ReportPortal's auto-analysis to summarize results and failures.
358
+
-**"Show me the top five 500-level errors in the last hour"** - lists the top 5 such errors from the recent test results.
359
+
360
+
## More Information
361
+
362
+
For comprehensive documentation including:
363
+
- Detailed installation and configuration options
364
+
- ReportPortal compatibility information
365
+
- Complete tools reference with all parameters
366
+
- Developer guide and API documentation
367
+
- Troubleshooting and common issues
368
+
- Building from source
369
+
370
+
Please refer to the [complete README](https://github.com/reportportal/reportportal-mcp-server).
161
371
162
372
Whether you're aiming to optimize test analysis or simplify routine QA tasks, MCP empowers your AI tools to act with clarity and precision.
0 commit comments