Skip to main content
Glama
genxevo-selenium

genxevo-selenium

by genxevo

GenXEvo AI Automation Agent — Python Selenium

An MCP server that gives an AI coding agent reliable eyes and hands for Python + Selenium UI automation engineering — deterministic capabilities, structured evidence, enforced safety boundaries and verifiable results.

Build License: MIT Python 3.11 | 3.12 | 3.13 Status: alpha


The problem

Ask any language model to fix a failing Selenium test and it will produce a confident, plausible, wrong XPath.

It has to. It cannot see the page, it cannot see the test output, and it usually cannot even see the project's real shape — which interpreter the suite runs on, which runner collects it, where the page objects actually live. It fills the gap with fluency.

GenXEvo exists to remove the gap, so the model has something true to reason about.

Related MCP server: AI Web Tester

The principle

Evidence before modification. Evidence before success.

The agent never invents a locator; it observes one. It never declares a fix; it proves one with a run correlated by identifier to the failure it claims to have repaired. Every capability returns evidence with an explicit trust level, every conclusion carries the signals that produced it, and every result says in a machine-readable field whether it succeeded — because an agent that cannot tell success from failure will confidently report a repair it never verified, and that outcome is worse than not helping at all.

What this is, and what it is not

Is

An MCP capability layer around the UI automation engineering workflow you already run

Is not

A test framework, a Selenium wrapper, a replacement for pytest, or an AI of its own

There is no model inside this server. The AI model reasons. GenXEvo is deterministic: it reads what is actually on disk, and later drives a real browser and executes real tests, and returns structured facts. When it does not know something, it says so, with a confidence level attached.


Status — honestly

This is phase 1A: the foundation and exactly two genuinely working capabilities.

Built and tested

Result contract, error vocabulary, evidence model, untrusted-content framing, configuration, path containment, secret redaction, test-selection validation, run model, capability catalogue, capability invoker, MCP adapter

Working MCP tools

genxevo_agent_status, genxevo_discover_project

Designed, catalogued, NOT callable

15 further capabilities, each published with its delivery phase

Not built

Browser control, test execution, repair, verification

There are no stubs in this repository. A planned capability is visible in genxevo_agent_status so an agent can plan around it, and is not registered as a tool, so an agent can never call one. A fake implementation is worse than an honest absence, because it teaches the agent something false.

See docs/roadmap.md for what each phase delivers and its exit criteria.


Quick start

Requirements

  • Python 3.11, 3.12 or 3.13

  • A Python automation project you want the agent to work on

The 3.11 floor is an engineering decision, not a fashion one: tomllib entered the standard library in 3.11, and it is what lets project discovery parse pyproject.toml without a third-party parser in the core. On 3.10 that would require tomli. See ADR-001.

Install

python -m venv .venv
# Windows
.venv\Scripts\activate
# macOS / Linux
source .venv/bin/activate

pip install -e .

Verify it starts — note that the banner goes to stderr, because stdout belongs to the MCP transport:

genxevo-selenium-agent --version

Connect it to an MCP client

Copy .mcp.json.example and point --workspace at your automation project:

{
  "mcpServers": {
    "genxevo-selenium": {
      "command": "C:\\path\\to\\your\\.venv\\Scripts\\python.exe",
      "args": [
        "-m", "genxevo_selenium_agent",
        "--workspace", "C:\\path\\to\\your\\automation-project"
      ]
    }
  }
}

Naming the interpreter explicitly is the reliable form on every platform: a console script lives inside one virtual environment, and an MCP client does not inherit your activated shell.

Full instructions for Claude Code, VS Code and PyCharm: docs/installation.md.

Configure it (optional)

A missing configuration file is not an error — the defaults are the safe configuration. When you want to change something, drop genxevo.config.toml in the workspace root:

version = 1

[execution]
enabled = false          # test execution is off until you turn it on
require_selection = true # never run the whole suite by accident

[security]
redact_secrets = true

Every setting, its default and its rationale: docs/configuration.md.


Architecture

                     AI MODEL   (all reasoning lives here)
                         │  MCP · JSON-RPC over stdio
                         ▼
   ┌──────────────────────────────────────────────────────────┐
   │ genxevo_selenium_agent.mcp_server      THIN ADAPTER        │
   │ tool names · descriptions · annotations · stderr logging   │
   │ every tool function holds no logic                         │
   └──────────────────────────────────────────────────────────┘
                         │
   ┌──────────────────────────────────────────────────────────┐
   │ genxevo_selenium_agent.core            THE PRODUCT         │
   │ standard library + one typing-only shim, and nothing else  │
   │                                                            │
   │  capabilities   runtime · invoker · catalog · 2 built      │
   │  discovery      manifests · runners · venvs · page objects │
   │  security       paths · redaction · selection · globs      │
   │  contracts      ToolResult · AgentError · Evidence         │
   │  runs           RunId · RunOutcome · FileRunRegistry       │
   └──────────────────────────────────────────────────────────┘
              │                  │                  │
              ▼                  ▼                  ▼
        real project      real browser (1C)   real test runs (1D)

Layer rule: behaviour never lives in the adapter. A tool function cannot be unit tested through an MCP client, so nothing that could be wrong is allowed in one.


The result contract

Every capability returns the same envelope, and an agent branches on status, never on prose:

{
  "contractVersion": "1.0",
  "status": "partialSuccess",     // one of nine values — see below
  "operation": "project.discover",
  "summary": "…one sentence for a human…",
  "data": { },                    // shape documented per capability
  "warnings": [ { "code": "…", "message": "…", "detail": "…" } ],
  "error": null,                  // present whenever status is not succeeding
  "evidence": [ { "id": "…", "kind": "…", "trust": "trusted|untrusted", … } ],
  "nextActions": [ { "tool": "…", "reason": "…" } ],
  "durationMs": 41,
  "startedAt": "2026-08-22T09:15:00Z",
  "safeToRetry": true
}

The nine statuses: success · partialSuccess · failure · validationError · configurationError · blocked · timeout · cancelled · skipped

Each is a distinct decision an agent has to make. Nothing else is in the list.

Because the tools are annotated with a TypedDict, this whole contract — including the status enum — is published in tools/list as each tool's outputSchema. An agent learns how to read a result before it calls anything.

Invariants are enforced in code, not by convention: a succeeding status never carries an error, a failing one always does, status is derived from the error's category so the two cannot disagree, and a partialSuccess cannot be constructed without a warning explaining it.


Security posture

GenXEvo reads untrusted content, hands it to a language model, and will later give that model file-write and code-execution capabilities. The design assumption is that the model will eventually be persuaded to ask for something it should not have, and that the server, not the model, refuses.

Control

What it does

Explicit workspace roots

Never inferred. Unconfigured means refuse, with the remedy

Path containment

Reject structurally → canonicalise → then contain → deny list → intent. Capabilities take a ResolvedPath, not a str, so unvalidated I/O does not type-check

Symlink resolution

Path.resolve() follows symlinks before containment is tested, so a link out of the workspace is refused

Deny list

Python-aware: .pypirc, pip.conf, local_settings.py, secrets.py alongside .env, *.pem, ~/.ssh

Secret redaction

Key-name and value-shape detection, including Python source assignments like PASSWORD = "…"

No project code is ever executed

setup.py is recorded and never run; conftest.py is read as text and never imported; installed packages are read from dist-info directory names

Untrusted framing

Escape-proof — a payload cannot forge either delimiter

Selection validation

A selection starting with - is refused outright: pytest -p some.module is arbitrary code execution

Safe defaults

Execution off, redaction on, selection required

Bounded everything

Timeouts, cooperative cancellation, scan limits, repair-cycle ceiling

Run correlation

Stale artefacts cannot be read as proof of a fix

Error hygiene

No traceback ever reaches the agent; refusals never echo the absolute workspace path

Residual risks are documented, not hidden — see SECURITY.md and docs/security.md. Framing does not prevent influence, test execution is arbitrary code by design, stdio MCP has no authentication, and redaction is heuristic.


The GenXEvo family

This is the second product in a family of independent agents. Each is separately cloneable and installable; what they share is a contract, not a build.

Selenium

Playwright

C#

shipped

planned

Python

this repository

planned

Java · JavaScript · TypeScript

planned

planned

What ports across languages is the JSON shape, the nine-status vocabulary, the error codes, the run identifier format, the evidence model and the safety classes. An agent that has learned one GenXEvo server should recognise the next one on first contact.

What is not shared is implementation. This product is Python-native by design: TypedDict output schemas, tomllib configuration, dataclasses instead of a serialisation framework, cooperative cancellation across asyncio.to_thread, and a discovery model built around pyproject.toml, pyvenv.cfg and pytest's own collection rules.


Documentation

Document

Contents

docs/architecture.md

Packages, layers, domain model, contract, evidence, runs, concurrency

docs/installation.md

Claude Code, VS Code, PyCharm; the interpreter trap

docs/configuration.md

Every setting, default and rationale; precedence; validation

docs/mcp-tools.md

Full contract — 2 implemented in detail, 15 planned with their guarantees

docs/agent-workflows.md

The engineering loop, rules for agents, a worked example, anti-patterns

docs/security.md

Threat model, controls with rationale, residual risks

docs/decisions.md

Architecture decision records, each tied to the defect that motivated it

docs/roadmap.md

Phases 1A–3 with exit criteria and what is out of scope

docs/troubleshooting.md

Concrete failure modes and their fixes

prompts/

How to talk to the agent, with complete worked prompts

examples/

Working configuration files


Development

pip install -e ".[dev]"

ruff check .          # lint
ruff format --check . # format
mypy                  # strict type checking
pytest                # the full suite

These checks also run in CI (Build) on every push and pull request — ruff · ruff format · mypy · pytest across Python 3.11–3.13 on Linux & Windows, plus stdout-purity and package-build checks.

The standard, written into CONTRIBUTING.md: every security control ships with tests that assert the attack, not only the happy path, and genxevo_selenium_agent.core imports the standard library and exactly one typing-only shim — enforced by a test that parses every module with ast, not by convention. The one exception is typing_extensions, and ADR-002 explains why the alternative is a server that will not start on Python 3.11.


Author

Rajeshkumar Muthu — Senior QA Automation Agentic AI Engineer.

Licensed under the MIT License.

Available Tools

2 tools
genxevo_agent_statusGenXEvo agent statusA
Read-onlyIdempotent

Report what the GenXEvo agent currently is: whether it is configured, which workspace roots it may read, what its security policy is, which Python interpreter is hosting the server, whether test execution is permitted, and exactly which capabilities this build provides versus which are planned for a later phase. Call this FIRST in any session, and again whenever a capability behaves unexpectedly. Note that the interpreter reported here runs GenXEvo itself and is usually NOT the interpreter the automation project's tests run on -- use genxevo_discover_project for that. Returns the GenXEvo ToolResult envelope: branch on the 'status' field, never on the prose in 'summary'. Read-only and always safe to repeat.

Inputs: no named parameters. Returns: data, error, runId, status, +9 more

genxevo_discover_projectDiscover the Python automation projectA
Read-onlyIdempotent

Scan the configured workspace and report the Python automation project that is actually there: pyproject.toml, requirements files, setup.cfg and lock files with their declared dependencies; the test runner the project itself states it uses (pytest or unittest, or 'unknown' -- never assumed); the test roots, established from files matching the project's own collection patterns rather than from any folder being called 'tests'; virtual environments with the interpreter version read from pyvenv.cfg; the browser automation library in use (Selenium, Playwright, Appium); candidate page-object directories, identified because their modules drive a browser and are not collected as tests; and CI configuration. Every conclusion carries the signals that produced it and an explicit confidence level, so you can tell a fact from a guess. GenXEvo never imports or executes anything in the project to obtain this -- setup.py and conftest.py are read as text only. Call this before reasoning about any test, locator or run. Read-only, makes no assumption about folder layout, and always safe to repeat. If 'status' is 'partialSuccess' the scan hit a limit or could not read something, and 'not found' may mean 'not looked at'.

Inputs: no named parameters. Returns: data, error, runId, status, +9 more

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A4.3/5.0

    Scored across 2 tools

    Disambiguation5/5

    genxevo_agent_status reports on the agent/server itself, while genxevo_discover_project inspects the workspace project. Their purposes and targets are completely distinct, so an agent should never confuse them.

    Naming Consistency4/5

    Both tools share the genxevo_ prefix and use snake_case, which is good, but genxevo_agent_status is a noun-phrase while genxevo_discover_project is verb+noun. This is a minor stylistic inconsistency rather than a serious problem.

    Tool Count3/5

    Two tools is on the thin side and feels borderline, but both are substantial read-only capabilities that form a coherent project-reconnaissance pair. The count is not excessive, but it is minimal.

    Completeness2/5

    The descriptions repeatedly mention tests, locators, and runs, but no tool actually executes tests, inspects locators, or interacts with the Selenium project. After discovery, an agent has no way to act on the project, which is a significant gap for a Selenium-oriented server.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables coding agents to independently verify web changes by scanning pages, inspecting UI structure, generating Playwright reproductions, and executing tests with structured QA evidence.
      4
      85 npm
      4
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      Enables AI assistants to control a real browser via Selenium WebDriver for web automation, including navigation, element interaction, assertions, and recording sessions. It also generates production-ready test code in Java TestFly, Python pytest, or C# NUnit from those sessions.
      88
      Apache 2.0