{"id":"mozilla-firefox-devtools-mcp","name":"firefox-devtools-mcp","homepage":null,"repo_url":"https://github.com/mozilla/firefox-devtools-mcp","category":"devtools","subcategories":[],"tags":["mcp","mcp-server","browser-automation","firefox","webdriver-bidi","selenium","devtools","ai-agents"],"what_it_does":"Provides an MCP server that automates Mozilla Firefox via WebDriver BiDi using Selenium/WebDriver. Exposes MCP tools for navigating pages, interacting with elements by UID, capturing screenshots, handling network/console events, and optionally using privileged contexts (requires extra system access).","use_cases":["Browser automation and QA workflows controlled by an AI agent","Data collection from web pages (navigate, input, click, screenshot, inspect network/console)","Assistive testing of UI flows across sites using local Firefox automation","Agent-driven debugging by inspecting DOM snapshots, network requests, and console messages"],"not_for":["Running in serverless/cloud environments (requires local Firefox and cannot run on hosting like the glama.ai example)","Automating untrusted targets in high-security environments without sandboxing/browser isolation","Use cases that require fine-grained permissioning over what the agent can do inside the browser (e.g., disabling script execution entirely)"],"best_when":"You have a local machine with Firefox installed, want MCP-compatible browser control for agentic browsing/testing, and can accept running an automation browser session with optional privileged capabilities.","avoid_when":"You cannot run locally (no Firefox binary available), you need to avoid any form of JavaScript execution/privileged context access, or you require strict security governance over browser automation capabilities.","alternatives":["Playwright-based MCP/tools for browser automation (where available)","Selenium WebDriver directly with a custom agent integration","Other MCP browser automation servers that expose constrained toolsets","Manual WebDriver BiDi scripts without MCP"],"af_score":64.2,"security_score":43.2,"reliability_score":33.8,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T13:48:53.224811+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["None (local process transport via MCP client connection)","Environment-flag based capability enabling for privileged context/tools (e.g., MOZ_REMOTE_ALLOW_SYSTEM_ACCESS=1)"],"oauth":false,"scopes":false,"notes":"No user/auth scheme is documented. Instead, capability gating is done via command-line flags/env vars (not a permission model)."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Open-source (MIT) and intended for local execution; cost is primarily local compute and infrastructure for running Firefox/Selenium."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":64.2,"security_score":43.2,"reliability_score":33.8,"mcp_server_quality":85.0,"documentation_accuracy":78.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":95.0,"rate_limit_clarity":0.0,"tls_enforcement":60.0,"auth_strength":20.0,"scope_granularity":20.0,"dependency_hygiene":55.0,"secret_handling":70.0,"security_notes":"Runs locally and does not document transport security requirements (no explicit TLS/auth model). Privileged context and script-evaluation capabilities can materially increase attack surface; capability gating relies on environment variables/flags (not fine-grained permissions). Automation mode (Marionette/webdriver signals) can affect fingerprinting; README warns about bot detection. No explicit secrets handling guidance or rate limiting is documented.","uptime_documented":0.0,"version_stability":55.0,"breaking_changes_history":35.0,"error_recovery":45.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["UID-based element actions can become stale after navigation; README recommends taking a fresh snapshot (take_snapshot) before UID tools.","In connect-existing mode, BiDi-dependent features (console/network events) are not available.","Privileged context tools require MOZ_REMOTE_ALLOW_SYSTEM_ACCESS=1; enabling them increases risk and may fail if not set correctly.","Windows sometimes requires invoking npx via cmd / appropriate command wrapper due to connection-closed errors.","Marionette must be enabled for connect-existing automation; leaving it enabled can alter fingerprint signals (bot detection risk)."]}}