What can you do with this server?

Lucius is an Allure TestOps MCP server that lets AI agents manage QA/test-management workflows through focused tools. * Create, read, update, archive/delete test cases, including steps, tags, issues, attachments, descriptions, and custom fields. * Search/list test cases and discover project metadata such as custom fields and integrations. * Manage shared steps, test layers, hierarchy suites, and test case-to-suite assignments. * Manage custom field values and clean up unused custom fields. * Create/manage launches and test results, upload results, add attachments, rerun tests, and handle manual test sessions. * Create/update/delete/list test plans, manage their content, and run plans as launches. * Manage defects and defect matchers, link/unlink issues to test cases, and list defect-linked test cases. * Generate framework-specific test code from existing test cases.

Which integrations are available for this server?

Enables interaction with GitHub issue tracking via Allure TestOps integration, allowing linking of defects and test cases to GitHub issues.

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Lucius search for test cases related to payment" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Lucius

by ivanostanin

Overview Schema Source Related Servers Discussions Admin

Python

Remote

Allure TestOps MCP Server

Lucius is a specialized Model Context Protocol (MCP) server for Allure TestOps, built with FastMCP and Starlette.

🎯 Motivation

Allure TestOps is a powerful tool with a huge API. When you're using an AI agent to manage your tests, it can easily get lost in the details or fail because of a small technical mistake.

Lucius makes this easier by giving your AI tools that are simple to use and hard to break:

Clear Tools: Every tool is designed for a specific task, like "finding a test case" or "updating a launch".
Helpful Errors: If an AI makes a mistake, Lucius doesn't just return a code—it provides an "Agent Hint" that explains exactly what went wrong and how to fix it.
Solid Foundation: We follow a clean "Thin Tool" structure, meaning the logic is consistent and easy for both humans and AI to follow.

Related MCP server: Allure TestOps MCP

🛠️ Supported Tools

See the full reference in Tool Reference.

Tool Category	Description	All Tools
Test Case Mgmt	Full lifecycle for test documentation.	`create_test_case`, `update_test_case`, `delete_test_case`, `delete_archived_test_cases`, `get_test_case_details`, `get_test_case_custom_fields`
Automation Generation	Generate framework-specific code from existing test cases.	`generate_test_code`
Search & Discovery	Advanced search and project metadata discovery.	`list_test_cases`, `search_test_cases`, `get_custom_fields`, `list_integrations`, `get_project`
Shared Steps	Create and manage reusable step sequences.	`create_shared_step`, `list_shared_steps`, `update_shared_step`, `delete_shared_step`, `delete_archived_shared_steps`, `link_shared_step`, `unlink_shared_step`
Test Layers	Manage test taxonomy and auto-mapping schemas.	`list_test_layers`, `create_test_layer`, `update_test_layer`, `delete_test_layer`, `list_test_layer_schemas`, `create_test_layer_schema`, `update_test_layer_schema`, `delete_test_layer_schema`
Test Hierarchy	Organize suites and assign tests in tree paths.	`create_test_suite`, `list_test_suites`, `assign_test_cases_to_suite`, `delete_test_suite`
Custom Fields	Project-level management of custom field values.	`list_custom_field_values`, `create_custom_field_value`, `update_custom_field_value`, `delete_custom_field_value`, `delete_unused_custom_fields`
Launch Management	Manage launches, result uploads, manual execution, reruns, and attachments.	`create_launch`, `list_launches`, `get_launch`, `list_launch_test_results`, `upload_test_results`, `attach_file_to_launch`, `rerun_test_results_manually`, `start_manual_test_session`, `submit_manual_test_results`, `add_test_result_attachment`
Test Result Management	Inspect one exact TestOps result and prepare verified evidence downloads.	`get_test_result`, `prepare_attachment_download`
Test Plans	Manage test plans and their content.	`create_test_plan`, `update_test_plan`, `delete_test_plan`, `list_test_plans`, `manage_test_plan_content`, `run_test_plan`
Defect Mgmt	Track defects, linkage, and automation rules.	`create_defect`, `get_defect`, `update_defect`, `delete_defect`, `list_defects`, `link_defect_to_test_case`, `unlink_issue_from_test_case`, `list_defect_test_cases`, `create_defect_matcher`, `list_defect_matchers`, `update_defect_matcher`, `delete_defect_matcher`

🚀 Quick Start

Install uv: curl -LsSf https://astral.sh/uv/install.sh | sh
Setup Credentials: Create a .env file with the variables below, or save CLI auth with lucius auth.
Run Server: uv run start

Basic `.env` for Quick Start

Variable	Description	Example
`ALLURE_ENDPOINT`	Allure TestOps base URL	`https://example.testops.cloud`
`ALLURE_PROJECT_ID`	Default Allure project ID (optional for `get_project`; required by project-scoped tools)	`123`
`ALLURE_API_TOKEN`	Allure API token	`<your_api_token>`
`MCP_MODE`	MCP transport mode for Lucius runtime	`stdio`

🔌 Claude Desktop Integration

The easiest way to use Lucius in Claude Desktop is via the .mcpb bundle:

Download the latest lucius-mcp.mcpb from Releases.
Open with Claude Desktop.
Configure your Allure credentials in the UI.

💻 Claude Code Integration

To add Lucius to Claude Code, use the following command from within your project directory:

claude mcp add --transport stdio --scope project \
  --env ALLURE_ENDPOINT=https://example.testops.cloud \
  --env ALLURE_PROJECT_ID=123 \
  --env ALLURE_API_TOKEN=<your_api_token> \
  --env MCP_MODE=stdio \
  testops-mcp -- uvx --from lucius-mcp --refresh start

Project-scoped text config example (.mcp.json):

{
  "mcpServers": {
    "testops-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "--from",
        "lucius-mcp",
        "--refresh",
        "start"
      ],
      "env": {
        "ALLURE_ENDPOINT": "https://example.testops.cloud",
        "ALLURE_PROJECT_ID": "123",
        "ALLURE_API_TOKEN": "<your_api_token>",
        "MCP_MODE": "stdio"
      }
    }
  }
}

🧠 Codex Integration

To add Lucius to Codex (CLI or IDE extension), use:

codex mcp add testops-mcp \
  --env ALLURE_ENDPOINT=https://example.testops.cloud \
  --env ALLURE_PROJECT_ID=123 \
  --env ALLURE_API_TOKEN=<your_api_token> \
  --env MCP_MODE=stdio \
  -- uvx --from lucius-mcp --refresh start

Text config example (~/.codex/config.toml or project .codex/config.toml):

[mcp_servers.testops-mcp]
command = "uvx"
args = ["--from", "lucius-mcp", "--refresh", "start"]

[mcp_servers.testops-mcp.env]
ALLURE_ENDPOINT = "https://example.testops.cloud"
ALLURE_PROJECT_ID = "123"
ALLURE_API_TOKEN = "<your_api_token>"
MCP_MODE = "stdio"

For detailed setup, including Claude Desktop (MCPB) integration, see Setup Guide.

🐍 Supported Python versions

Lucius supports Python 3.11 through 3.14 for runtime use. The generated MCPB manifests and the representative Nuitka CLI compiler matrix validate the same range. Python 3.15 support is experimental: installation may require source builds, and platform compatibility is still being verified. See the development guide for current limitations. Python 3.10 remains unsupported because the locked filelock security update requires Python 3.11 or newer.

💻 Command-Line Interface (CLI)

Lucius also provides a universal CLI entry point for direct tool execution from the command line:

# List available actions for an entity
uv run lucius test_case

# Execute an action
uv run lucius test_case get --args '{"test_case_id": 1234}'

# Show help for a specific entity/action
uv run lucius test_case get --help

# Save reusable CLI auth
uv run lucius auth --url https://example.testops.cloud --token <your_api_token> --project 123
uv run lucius auth status
uv run lucius auth clear

CLI Features:

🎯 Type-safe entity/action invocation with validation
🔐 Optional persistent CLI auth with native per-user config storage
📊 Multiple output formats (JSON, table, csv, plain)
🔍 Per-action help with parameters and examples
🛡️ Clean error messages with guidance
📦 Standalone binaries for Linux, macOS, and Windows

CLI auth precedence is:

Explicit tool args such as api_token or project_id
Environment variables
Saved CLI auth config from uv run lucius auth
Defaults

Saved CLI auth uses native config locations:

Linux/Unix: $XDG_CONFIG_HOME/lucius/auth.json or ~/.config/lucius/auth.json
macOS: ~/Library/Application Support/lucius/auth.json unless XDG overrides are explicitly set
Windows: %LOCALAPPDATA%\lucius\auth.json

For full CLI documentation and installation instructions, see CLI Guide.

📡 Telemetry

Lucius collects privacy-preserving usage telemetry to improve tool quality. Telemetry is enabled by default and sends metadata to https://stats.ostanin.me, an endpoint operated by the project owner (no third party has access to this endpoint).

If this is acceptable in your environment, staying opted in helps improve Lucius over time. If you want to opt out, set TELEMETRY_ENABLED=false in your environment.

No API tokens, test content, or tool arguments are sent.

See Telemetry & Privacy for the full data dictionary and telemetry behavior details.

📂 Documentation

Full documentation is available in the docs/ folder:

🤝 Contributing

Contributions are welcome! Please see the Contribution Guidelines and the Development Guide for more details.

Available Tools

70 tools

add_test_result_attachmentAdd Test Result AttachmentA

Upload evidence to a manual test result.

The returned attachment_ids can be used as attachment_id values in submit_manual_test_results. Result-level evidence can also be uploaded after a manual result has been resolved.

Inputs: attachment (required), test_result_id (required), project_id, output_format. Returns: target_id, file_names, status_code, target_kind, +1 more

assign_test_cases_to_suiteAssign Test Cases To SuiteA

DestructiveIdempotent

Assign test cases to a suite path in hierarchy.

⚠️ CAUTION: Destructive. Reassigning test cases changes their hierarchy location.

Inputs: suite_id (required), test_case_ids (required), tree_id, project_id, +1 more. Returns: tree_id, suite_id, test_case_ids, assigned_count

attach_file_to_launchAttach File To LaunchA

Attach one file to an existing launch through a secure push or pull transfer.

Push is available only from a persistent HTTP MCP server with an externally reachable HTTPS URL. It returns a short-lived one-use raw upload URL; POST bytes with exactly the returned content type and no TestOps bearer token. Pull reads a regular file below the deployment's configured import root.

Inputs: name (required), launch_id (required), project_id, source_path, +3 more. Returns: Explicit mutually exclusive output states for launch attachment transfer.

close_launchClose LaunchA

DestructiveIdempotent

Close a launch and return updated launch details.

Inputs: launch_id (required), api_token, project_id, output_format. Returns: Stable compact launch fields emitted by create and lifecycle tools.

create_custom_field_valueCreate Custom Field ValueC

Create a new custom field value option.

Inputs: name (required), project_id, output_format, custom_field_id, +1 more. Returns: id, name, custom_field_id, custom_field_name

create_defectCreate DefectA

Create a new defect in the current project.

Use this tool to register a known defect that can later be linked to failing test results through defect matchers (automation rules).

Inputs: name (required), description, output_format. Returns: id, url, name, description

create_defect_matcherCreate Defect MatcherA

Create a defect matcher (automation rule) for a defect.

Matchers automatically link future failing test results to a defect when the test failure's error message or stack trace matches the provided regex patterns.

At least one of message_regex or trace_regex must be supplied.

Inputs: name (required), defect_id (required), trace_regex, message_regex, +1 more. Returns: id, name, defect_id, trace_regex, +1 more

create_launchCreate LaunchB

Create a new launch in Allure TestOps.

Inputs: name (required), tags, links, issues, +4 more. Returns: Stable compact launch fields emitted by create and lifecycle tools.

create_shared_stepCreate Shared StepC

Create a new reusable Shared Step.

Inputs: name (required), steps, project_id, output_format. Returns: id, url, name, project_id

create_test_caseCreate Test CaseB

Create a new test case in Allure TestOps.

Inputs: name (required), tags, steps, issues, +9 more. Returns: id, url, name, issues

create_test_layerCreate Test LayerB

Create a new test layer in Allure TestOps.

Test layers define taxonomy for categorizing test cases. Common examples include 'Unit', 'Integration', 'E2E', 'UI', 'API', etc.

Inputs: name (required), project_id, output_format. Returns: id, name

create_test_layer_schemaCreate Test Layer SchemaA

Create a new test layer schema to map a custom field key to a test layer.

Test layer schemas define the mapping between custom field keys and test layers. This allows test cases with specific custom field values to be automatically assigned to the correct test layer.

Inputs: key (required), project_id (required), test_layer_id (required), output_format. Returns: id, key, test_layer_id, test_layer_name

create_test_planCreate Test PlanA

Create a new Test Plan in Allure TestOps.

This tool allows creating a Test Plan, which is a collection of Test Cases to be executed. You can define the content of the plan either by:

Explicitly listing Test Case IDs (test_case_ids).
Providing an AQL (Allure Query Language) filter (aql_filter).
Both (explicit selection + dynamic filter).

Inputs: name (required), aql_filter, output_format, test_case_ids. Returns: id, url, name, aql_filter, +2 more

create_test_suiteCreate Test SuiteB

Create a new test suite node in the hierarchy tree.

Inputs: name (required), tree_id, project_id, output_format, +1 more. Returns: id, name, tree_id, parent_suite_id

delete_archived_shared_stepsDelete Archived Shared StepsA

DestructiveIdempotent

Permanently delete all archived shared steps in the current project.

Inputs: confirm, project_id, output_format. Returns: action, deleted_count, requires_confirmation

delete_archived_test_casesDelete Archived Test CasesA

DestructiveIdempotent

Permanently delete all archived/deleted test cases in the current project.

Inputs: confirm, project_id, output_format. Returns: action, deleted_count, requires_confirmation

delete_custom_field_valueDelete Custom Field ValueB

DestructiveIdempotent

Delete a custom field value. ⚠️ CAUTION: Destructive.

Inputs: cfv_id (required), confirm, project_id, output_format, +2 more. Returns: id, action, cfv_id, status, +1 more

delete_defectDelete DefectA

DestructiveIdempotent

Permanently delete a defect and all its associated matchers.

This is a destructive operation. The confirm parameter must be set to true to actually perform the deletion.

Inputs: defect_id (required), confirm, output_format. Returns: id, status, defect_id

delete_defect_matcherDelete Defect MatcherA

DestructiveIdempotent

Permanently delete a defect matcher (automation rule).

This is a destructive operation. The confirm parameter must be set to true to actually perform the deletion.

Inputs: matcher_id (required), confirm, output_format. Returns: id, status, matcher_id

delete_launchDelete LaunchC

DestructiveIdempotent

Delete a launch by ID. ⚠️ CAUTION: Destructive.

Inputs: launch_id (required), project_id, output_format. Returns: status, message, launch_id

delete_shared_stepDelete Shared StepA

DestructiveIdempotent

Delete a shared step from the library. ⚠️ CAUTION: Destructive.

⚠️ CAUTION: If this shared step is used by test cases, deleting it will break those references.

Inputs: step_id (required), confirm, project_id, output_format. Returns: id, url, action, status, +2 more

delete_test_caseDelete Test CaseA

DestructiveIdempotent

Archive an obsolete test case. ⚠️ CAUTION: Destructive.

This performs a SOFT DELETE (archive). The test case can typically be recovered from the Allure UI if needed.

⚠️ CAUTION: This action removes the test case from active views. Historical data and launch associations may be affected.

Inputs: test_case_id (required), confirm, project_id, output_format. Returns: url, name, error, action, +3 more

delete_test_layerDelete Test LayerB

DestructiveIdempotent

Delete a test layer from Allure TestOps. ⚠️ CAUTION: Destructive.

Inputs: layer_id (required), confirm, project_id, output_format. Returns: id, action, status, layer_id, +1 more

delete_test_layer_schemaDelete Test Layer SchemaB

DestructiveIdempotent

Delete a test layer schema from the project. ⚠️ CAUTION: Destructive.

Inputs: schema_id (required), confirm, project_id, output_format. Returns: id, action, status, schema_id, +1 more

delete_test_planDelete Test PlanA

DestructiveIdempotent

Delete a Test Plan. ⚠️ CAUTION: Destructive.

Permanently removes the Test Plan from Allure TestOps. The operation is idempotent: if the plan does not exist, it returns success.

Inputs: plan_id (required), confirm, output_format. Returns: action, status, plan_id, requires_confirmation

delete_test_suiteDelete Test SuiteA

DestructiveIdempotent

Delete a test suite node from hierarchy. ⚠️ CAUTION: Destructive.

This operation removes a hierarchy suite/group node. Allure TestOps handles nested entities according to its API behavior for tree groups.

Inputs: suite_id (required), confirm, tree_id, project_id, +1 more. Returns: action, status, suite_id, requires_confirmation

delete_unused_custom_fieldsDelete Unused Custom FieldsA

DestructiveIdempotent

Delete custom fields that are unused by any test case in the current project.

Inputs: confirm, project_id, output_format. Returns: action, deleted_count, requires_confirmation

generate_test_codeGenerate Test CodeA

Read-onlyIdempotent

Generate a current, framework-specific test snippet from a TestOps test case.

Both target selections are required. The tool validates verified TestOps language/framework compatibility locally and synchronizes only requested test-case metadata before generation.

Inputs: language (required), framework (required), test_case_id (required), metadata, +1 more. Returns: code, language, metadata, framework, +1 more

get_custom_fieldsGet Custom FieldsA

Read-onlyIdempotent

Get available custom fields and their allowed values for the project.

Use this tool to discover what custom fields are available (e.g., 'Layer', 'Priority') and what values are valid for them (e.g., 'UI', 'High'). This is essential before creating or updating test cases to ensure you use valid field names and values.

Inputs: name, project_id, output_format. Returns: items, total, filter_name

get_defectGet DefectA

Read-onlyIdempotent

Retrieve detailed information about a specific defect.

Inputs: defect_id (required), output_format. Returns: id, url, name, closed, +2 more

get_launchGet LaunchB

Read-onlyIdempotent

Retrieve a specific launch and summarize its details.

Inputs: launch_id (required), tree_id, project_id, output_format, +1 more. Returns: Rich exact-ID launch fields, with explicit stable nested projections.

get_projectGet ProjectA

Read-onlyIdempotent

Retrieve one project by name or list accessible projects.

Name matching is case-insensitive. An exact match is preferred; an unambiguous partial match is accepted. Omit name to discover the available project IDs and names before making project-scoped calls.

Inputs: name, output_format. Returns: id, abbr, name, items, +3 more

get_test_case_custom_fieldsGet Test Case Custom FieldsB

Read-onlyIdempotent

Retrieve custom field values for a specific test case.

Inputs: test_case_id (required), project_id, output_format. Returns: test_case_id, custom_fields

get_test_case_detailsGet Test Case DetailsA

Read-onlyIdempotent

Get complete details of a specific test case.

Retrieves all information about a test case including its steps, tags, custom fields, and attachments. For each attachment, call prepare_attachment_download with its attachment_id, attachment_kind, and test_case_id, then HTTP GET the returned Lucius URL. Use this before updating a test case to understand its current state.

Inputs: test_case_id (required), project_id, output_format. Returns: Structured details for one test case.

get_test_resultGet Test ResultA

Read-onlyIdempotent

Retrieve one complete TestOps result without recursively reading related results.

Attachment references identify their verified owner. Call prepare_attachment_download with an attachment's attachment_id, attachment_kind, and owner context, then HTTP GET the returned Lucius URL before it expires.

Inputs: test_result_id (required), project_id, output_format. Returns: Stable object-root output for one exact enriched TestOps result.

get_test_suite_contentsGet Test Suite ContentsA

Read-onlyIdempotent

Get test cases directly assigned to one test suite.

This is a targeted hierarchy read. It does not enumerate unrelated suites or recursively traverse the project tree.

Inputs: suite_id (required), tree_id, project_id, output_format, +1 more. Returns: tree_id, suite_id, test_case_ids, assigned_count

link_defect_to_test_caseLink Defect To Test CaseA

Idempotent

Link a defect to a test case through a shared issue mapping.

This operation ensures defect governance and test coverage are connected: the issue is linked to the defect and to the specified test case.

Inputs: defect_id (required), test_case_id (required), issue_key, output_format, +2 more. Returns: defect_id, issue_key, defect_url, test_case_id, +3 more

link_shared_stepLink Shared StepB

Link a shared step to a test case. ⚠️ CAUTION: Destructive.

Adds a reference to the shared step in the test case's step list. The shared step's actions will expand at execution time.

Inputs: test_case_id (required), shared_step_id (required), confirm, position, +2 more. Returns: error, steps, action, status, +5 more

list_custom_field_valuesList Custom Field ValuesA

Read-onlyIdempotent

List available values for a custom field.

Inputs: page, size, sort, query, +6 more. Returns: page, size, items, total, +1 more

list_defect_matchersList Defect MatchersA

Read-onlyIdempotent

List all matchers (automation rules) for a given defect.

Inputs: defect_id (required), output_format. Returns: Matcher list for a defect.

list_defectsList DefectsB

Read-onlyIdempotent

List all defects in the current project.

Inputs: output_format. Returns: page, size, items, total, +1 more

list_defect_test_casesList Defect Test CasesA

Read-onlyIdempotent

List test cases currently linked to a defect.

Inputs: defect_id (required), page, size, output_format. Returns: page, size, items, total, +3 more

list_integrationsList IntegrationsA

Read-onlyIdempotent

List available integrations (issue trackers) in Allure TestOps.

Use this tool to discover which integrations (Jira, GitHub, etc.) are configured and available for linking issues to test cases.

Inputs: project_id, output_format. Returns: items, total

list_launchesList LaunchesC

Read-onlyIdempotent

List launches in a project.

Inputs: page, size, sort, search, +3 more. Returns: Paginated compact launches.

list_launch_test_resultsList Launch Test ResultsB

Read-onlyIdempotent

List test results inside a launch, including manual execution metadata.

Inputs: launch_id (required), page, size, sort, +6 more. Returns: page, size, items, total, +4 more

list_shared_stepsList Shared StepsA

Read-onlyIdempotent

List shared steps in a project to find existing ones.

Inputs: page, size, search, archived, +2 more. Returns: page, size, items, total, +1 more

list_test_casesList Test CasesA

Read-onlyIdempotent

List all test cases in a project.

Returns a paginated list of test cases with their IDs, names, and tags. Use this to review existing test documentation in a project.

Inputs: page, size, tags, status, +3 more. Returns: page, size, items, total, +1 more

list_test_layersList Test LayersA

Read-onlyIdempotent

List test layers to discover available test layer taxonomy.

Test layers define the taxonomy for categorizing test cases (e.g., Unit, Integration, E2E). Use this to find layer IDs and names before creating or updating test cases.

Inputs: page, size, output_format. Returns: page, size, items, total, +1 more

list_test_layer_schemasList Test Layer SchemasA

Read-onlyIdempotent

List test layer schemas for a project.

Test layer schemas map custom field keys to test layers within a project. They determine which test layer is assigned when a specific custom field value is used.

Inputs: page, size, project_id, output_format. Returns: page, size, items, total, +1 more

list_test_plansList Test PlansA

Read-onlyIdempotent

List Test Plans for the current project.

Retrieves a paginated list of Test Plans, showing their IDs, names, and the number of test cases they contain.

Inputs: page, size, output_format. Returns: page, size, items, total, +1 more

list_test_suitesList Test SuitesB

Read-onlyIdempotent

List hierarchy suites for a project tree.

Inputs: tree_id, project_id, include_empty, output_format. Returns: Hierarchy tree and its recursive suite nodes.

manage_test_plan_contentManage Test Plan ContentA

DestructiveIdempotent

Modify the content (Test Cases) of an existing Test Plan.

Allows adding or removing specific Test Cases by ID, or updating the underlying AQL filter query.

Inputs: plan_id (required), output_format, add_test_case_ids, update_aql_filter, +1 more. Returns: url, plan_id, aql_filter, add_test_case_ids, +3 more

prepare_attachment_downloadPrepare Attachment DownloadA

Read-onlyIdempotent

Prepare one verified attachment download, then HTTP GET its returned Lucius URL.

Call this after get_test_result or get_test_case_details provides an attachment ID, kind, and owner context. The returned download URL is one-time and short-lived: HTTP GET it before expires_at without an Allure bearer token. Prepare again if the URL expires or was already retrieved.

Inputs: attachment_id (required), attachment_kind (required), project_id, test_case_id, +2 more. Returns: Opaque one-time attachment delivery metadata returned by the public preparation…

reopen_launchReopen LaunchA

DestructiveIdempotent

Reopen a launch and return updated launch details.

Inputs: launch_id (required), api_token, project_id, output_format. Returns: Stable compact launch fields emitted by create and lifecycle tools.

rerun_test_results_manuallyRerun Test Results ManuallyB

Schedule manual reruns for selected launch results.

Inputs: launch_id (required), result_ids (required), assignees, project_id, +2 more. Returns: assignees, launch_id, result_ids, force_manual, +1 more

run_test_planRun Test PlanA

Start a launch from an existing Test Plan.

Runs the selected test plan by its ID and returns the created launch as a compact mutation summary enriched with the source plan context. Starting a launch is reversible: use delete_launch to remove it when unwanted.

Inputs: plan_id (required), launch_name (required), tags, links, +2 more. Returns: Curated launch-started-from-plan summary with source plan context.

search_test_casesSearch Test CasesA

Read-onlyIdempotent

Search for test cases by name, tag, or AQL query.

Find test cases matching your search criteria. Supports simple name/tag search or advanced AQL (Allure Query Language) for complex filtering.

Simple Query Syntax (use 'query' parameter):

Plain text: Searches in test case names (case-insensitive)
tag:value: Filters by exact tag match
Combined: "login tag:smoke" finds test cases with "login" in name AND "smoke" tag

Important: see https://docs.qameta.io/allure-testops/advanced/aql/ for the full AQL syntax reference. AQL Syntax (use 'aql' parameter):

Operators: and, or, not
Precedence: and binds tighter than or; use parentheses to group
Strings are double-quoted; numbers are unquoted; booleans are true/false
Comparison operators: =, !=, ~= (contains), in, not in
Field examples: status, tag, name, createdBy, automated, layer

Inputs: aql, page, size, query, +2 more. Returns: Paginated output for ``search_test_cases``.

start_manual_test_sessionStart Manual Test SessionB

Start a manual execution session for a launch.

Inputs: launch_id (required), project_id, environment, output_format. Returns: job_id, launch_id, job_run_id, project_id, +2 more

submit_manual_test_resultsSubmit Manual Test ResultsB

Submit manual execution results for a manual session.

Inputs: results (required), test_session_id (required), project_id, output_format. Returns: result_ids, submitted_count, test_session_id

unlink_issue_from_test_caseUnlink Issue From Test CaseA

DestructiveIdempotent

Unlink an issue from a test case.

This operation is idempotent: if the issue is already unlinked, it still returns a successful confirmation. Supply the issue key (for example, PROJ-123) or the internal issue-link ID returned by Allure TestOps.

Inputs: issue_id (required), test_case_id (required), output_format. Returns: Confirmation for unlinking an issue by numeric ID or issue key.

unlink_shared_stepUnlink Shared StepA

DestructiveIdempotent

Remove a shared step reference from a test case. ⚠️ CAUTION: Destructive.

Removes the link to the shared step. The test case will no longer include those steps at execution time.

Inputs: test_case_id (required), shared_step_id (required), confirm, project_id, +1 more. Returns: error, steps, action, status, +5 more

update_custom_field_valueUpdate Custom Field ValueB

DestructiveIdempotent

Update an existing custom field value. ⚠️ CAUTION: Destructive.

Inputs: name (required), cfv_id (required), confirm, project_id, +3 more. Returns: id, name, action, cfv_id, +3 more

update_defectUpdate DefectA

DestructiveIdempotent

Update an existing defect's name, description, or status.

At least one field must be provided. Fields set to null/None are left unchanged.

Inputs: defect_id (required), name, closed, description, +1 more. Returns: id, url, name, closed, +2 more

update_defect_matcherUpdate Defect MatcherA

DestructiveIdempotent

Update a defect matcher's name or regex patterns.

At least one field must be provided.

Inputs: matcher_id (required), name, trace_regex, message_regex, +1 more. Returns: id, name, trace_regex, message_regex

update_shared_stepUpdate Shared StepA

DestructiveIdempotent

Update an existing shared step. ⚠️ CAUTION: Destructive.

⚠️ IMPORTANT: Changes propagate to ALL test cases using this shared step.

Only provided fields will be updated. Omitted fields remain unchanged. Repeated calls with the same data are idempotent.

Inputs: step_id (required), name, confirm, project_id, +2 more. Returns: id, url, name, action, +4 more

update_test_caseUpdate Test CaseA

DestructiveIdempotent

Update an existing test case in Allure TestOps. ⚠️ CAUTION: Destructive.

Performs a partial update: only supplied fields are sent to the API. When provided, steps replace all existing steps, and attachments replace all existing global attachments. Omit a field to preserve its current value.

Inputs: test_case_id (required), name, tags, links, +19 more. Returns: id, url, name, action, +4 more

update_test_layerUpdate Test LayerB

DestructiveIdempotent

Update an existing test layer's name. ⚠️ CAUTION: Destructive.

Inputs: name (required), layer_id (required), confirm, project_id, +1 more. Returns: id, name, action, changed, +2 more

update_test_layer_schemaUpdate Test Layer SchemaB

DestructiveIdempotent

Update an existing test layer schema. ⚠️ CAUTION: Destructive.

Inputs: schema_id (required), key, confirm, project_id, +2 more. Returns: id, key, action, changed, +3 more

update_test_planUpdate Test PlanB

DestructiveIdempotent

Update the metadata of an existing Test Plan.

Currently, supports updating the name of the plan.

Inputs: plan_id (required), name, output_format. Returns: id, url, name

upload_test_resultsUpload Test ResultsA

Upload external test results to an existing launch.

Inputs: results (required), launch_id (required), project_id, output_format. Returns: failures, launch_id, result_ids, uploaded_count, +1 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

TDQS

B3.4/5.0

Scored 2026-09-23 19:55 across 70 tools

Disambiguation4/5

Most tools follow a clear resource-plus-action pattern, so boundaries between test cases, launches, shared steps, layers, plans, and defects are generally distinct. A few pairs like get_test_case_details vs get_test_result or list_test_layers vs list_test_layer_schemas could require careful reading, but the descriptions provide enough context to avoid serious ambiguity.

Naming Consistency5/5

Tool names are overwhelmingly consistent snake_case verb_noun constructions, such as create_test_case, update_test_plan, list_defects, and delete_shared_step. Even less common actions like rerun_test_results_manually or manage_test_plan_content still follow the same predictable pattern.

Tool Count1/5

With 70 tools, this server is far beyond the range of a well-scoped MCP surface and crosses the extreme-count threshold. Even though Allure TestOps is a broad platform, exposing this many tools in one server creates significant selection overhead and would be better split into focused sub-servers.

Completeness4/5

The tool set is remarkably comprehensive, covering CRUD and lifecycle workflows for test cases, launches, shared steps, layers, schemas, suites, test plans, defects, and defect matchers, along with search, attachments, and manual execution. Minor gaps exist, such as no dedicated test-case attachment upload, no shared-step detail read, and integration management being list-only, but agents can work around these.

Maintenance

ActivityNo data

ResponsivenessOutdated data

Resources

Related MCP Connectors

anotherai
dev.anotherai
MCP server for building and testing AI agents with multi-model experimentation and insights.
Agent Orchestration Autonomous Agents Testing & QA Tools
2
https://api.anotherai.dev/mcp
Qase Test Management
io.qase
Official MCP server for Qase — manage test cases, runs, suites, defects via AI tools.
Testing & QA Tools Developer Tools
237
https://mcp.qase.io/mcp
SmartBear MCP
com.smartbear
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
Monitoring Testing & QA Tools API Testing
144
https://zephyr.mcp.smartbear.com/mcp
Flowra
io.github.flowradev
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Agent Orchestration Autonomous Agents
11
https://mcp.flowra.dev/mcp

Related MCP Servers

allure-testops-mcp
Developer Tools Testing & QA Tools
mshegolev
A
license
A
quality
C
maintenance
MCP server for Allure TestOps — lets an LLM agent (Claude Code, Cursor, Windsurf, etc.) inspect test quality without leaving the chat.
Updated 17 days ago (2026-10-29 21:07 UTC)
11
136 PyPI
3
MIT
Allure TestOps MCP
Testing & QA Tools Project Management
iampopovich
A
license
C
quality
C
maintenance
Production-ready MCP server for Allure TestOps, enabling test case, launch, test result, and test plan management via natural language.
Updated 9 days ago (2026-11-06 16:07 UTC)
100
730 npm
2
MIT
TestOps MCP Server
Testing & QA Tools Project Management
kirchik95
A
license
A
quality
D
maintenance
An MCP server that connects AI agents to TestOps, enabling test case management, launches, defects, and analytics through natural language.
Updated 4 months ago (2026-07-26 21:07 UTC)
48
25 npm
MIT
testing-mcp
Testing & QA Tools Developer Tools
charlieNearform
F
license
Not graded
quality
C
maintenance
MCP server that enables AI agents to programmatically run tests, query results, and receive intelligent recommendations about test execution strategy.
Updated 2 months ago (2026-09-14 11:24 UTC)
-

Allure TestOps MCP Server

🎯 Motivation

🛠️ Supported Tools

🚀 Quick Start

Basic .env for Quick Start

🔌 Claude Desktop Integration

💻 Claude Code Integration

🧠 Codex Integration

🐍 Supported Python versions

💻 Command-Line Interface (CLI)

📡 Telemetry

📂 Documentation

🤝 Contributing

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

allure-testops-mcp

Allure TestOps MCP

TestOps MCP Server

testing-mcp

Basic `.env` for Quick Start