Skip to main content
Glama
124,190 servers. Updated
Browse by product

Matching MCP tools:

Matching MCP Connectors:

"Better Stack" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • A
    license
    A
    quality
    C
    maintenance
    A remote MCP server exposing 3 tools via Model Context Protocol: score_prompt (free, grades any LLM prompt A-F on 0-40 scale), optimize_prompt (returns optimized prompt + dimension breakdown, $0.025 USDC), and compare_models (Claude vs GPT-4o head-to-head, $1.25 USDC). Remote HTTP server at /api/mcp.
    2
    57 npm
    2
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Verificate combines 17 applications each designed to address a separate issue with AI Coding supported with a Frontier AI Model. This allows you to Vibe Code with confidence and even dropped down to a more basic model with a better outcome.
    4
    1
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    MCP server for verifying AI agent claims vs reality — single-transcript inline grounding-check that flags when an agent's response states facts not in the input context, when its code silently swallows exceptions and substitutes mock data, or when its multi-turn transcript contains contradictions or unverified completion claims. Sub-second, local, free, no API calls.
    4
    24 PyPI
    1
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Compacts noisy test, build, and cloud-log output before an AI agent reads it — dedupes repeats, collapses stack frames, folds Playwright retries, and renders CloudWatch/GCP JSON logs down to the signal. Typically 80–95% fewer tokens on failures. Tool: compact_output. Run: npx -y logslim logslim-mcp
    1
    18 npm
    5
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Drives a browser - or a native Expo/React Native app - and your dev server, putting both on one correlated timeline so a console error and the backend stack trace from the same moment line up. For Claude Code and AI agents.
    46
    144 npm
    2
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables Claude, Cursor, and other MCP clients to audit public sites across six areas, check and follow llms.txt links, compare rival sites side by side, and run sixteen content gates on local Markdown or MDX using only free public signals.
    4
    38 npm
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    MCP server with seven website-audit tools (incl. pay-transparency posting monitor) for AI agents: schema/AI-readiness, WCAG accessibility, tech stack, PageSpeed, AI-crawler access, page-change monitoring. Runs public Apify Actors on the user's own Apify account; MIT licensed.
    9
    351 npm
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables engineering leaders to query their AI assistant for quality KPIs — MTTR, MTTA, DORA metrics, defect escape rate and SLA breaches — computed from Jira bug, incident and deployment CSV exports already on hand. It delivers trends, period comparisons, hotspot findings and ready-to-share executive summaries and HTML dashboards without a BI stack or data warehouse.
    10
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Makes coding agents better at Godot 4 with 22 MCP tools: an offline Godot 4.7 API reference, a project map, a scored AAA review of GDScript that catches Godot 3 code and invented APIs, safe edits to scenes, settings and names, headless checks, unit tests, play-tests with input and screenshots, plus 3D models built, viewed and checked from code.
    43
    432 npm
    2
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Gives AI assistants structured access to a test automation stack so they can run suites, inspect failure details and captured output, look up test data, and file Jira bugs (or drafts) only for confirmed defects. It works with any framework that emits JUnit XML, letting assistants triage flaky, environment, and test-data issues alongside real product defects.
    6
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Gives Claude Code a live Node.js debugger over the V8 Inspector protocol, letting it launch or attach to a running process, set conditional breakpoints, step through execution, inspect scopes and stack frames, evaluate expressions in a frame, and read stdout/stderr — with no instrumentation added to the code.
    20
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Gives AI coding agents a ten-phase frontend design pipeline (audit, style direction, build, review, verify, perf, brand) with an exclusive style menu. Its verify_page tool loads a URL in a real Playwright browser at mobile and desktop viewports and returns screenshots, ARIA snapshots, console errors, failed requests, horizontal-overflow offenders, axe-core violations, and pointer type.
    3
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables AI assistants to query the Google Play Developer Reporting API for Android production stability data, including crash and ANR issue clusters, de-obfuscated stack traces, release track discovery, startup and crash metric trends, version-to-version comparisons, and anomaly alerts. It also provides guided prompts for incident triage, baseline profile verification, and weekly stability reporting with built-in token compression and caching.
    10
    MIT
  • A
    license
    B
    quality
    D
    maintenance
    Enables debugging of Python, JavaScript/TypeScript, Go, and Rust code using real debuggers with breakpoints, stepping, variable inspection, and stack trace navigation through the Debug Adapter Protocol.
    21
    2
    MIT
  • A
    license
    B
    quality
    D
    maintenance
    Enables coding agents to use a real debugger (Python via debugpy) for launching, attaching, setting breakpoints, stepping through code, inspecting stack frames, and evaluating expressions through MCP tools.
    12
    27
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    Enables converting Python tracebacks into root-cause analysis and runnable unittest/pytest suites, including edge-case generation and assertion auditing. It provides local MCP tools for decompiling stack traces, generating tests, and reviewing test coverage gaps.
    3
    1
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    Enables AI agents to run deterministic, fully local static security and compliance audits of code, configurations, and dependencies through 32 MCP tools covering 24 vulnerability categories. It also detects the project stack, generates risk reports and checklists, suggests stack-aware remediations, and re-validates fixes to confirm vulnerabilities were eliminated.
    32
    1
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    Enables AI assistants to debug PHP applications through Xdebug's DBGp protocol, providing full debugging control including breakpoints, variable inspection, stack traces, and advanced features like watch expressions and code coverage.
    46
    320 npm
    28
    MIT
  • F
    license
    B
    quality
    C
    maintenance
    Enables controlling and inspecting a running Dolphin emulator through its Debug Adapter Protocol, with persistent connections, task-oriented tools, and a raw request escape hatch for execution, breakpoints, stack/variables, memory, disassembly, sources, watches, scans, and code injection.
    16
    -
  • A
    license
    C
    quality
    D
    maintenance
    A server that converts Allure test reports into LLM-friendly formats, enabling AI models to better analyze test results and provide insights about test failures and potential fixes.
    1
    12
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI assistants to drive VS Code debugging over HTTP via MCP tools, including session control, stepping, breakpoints, stack and variable inspection, expression evaluation, and RTT I/O while keeping debug state visible in the VS Code UI.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Analyzes application crash dumps and extracts debug symbols, transforming Windows minidump files into readable stack traces and providing AI-powered crash analysis to help identify root causes and fix critical issues.
    8
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Wraps the Judge0 evaluation stack into a local algorithm-problem judging service that exposes seven tools to MCP clients, enabling models to browse problems, self-test against public samples, and submit solutions for full hidden-test grading. Judging parameters, submission limits, and hidden-data access are enforced server-side so models cannot bypass them.
    GPL 3.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables coding agents to deterministically audit markup and stylesheets for WCAG contrast failures, accessibility errors and design-token sprawl, and to compute contrast ratios and inventory hardcoded colors, sizes, radii and spacing before shipping UI code. Works across any web stack with Claude Code, Claude Desktop, Codex and Antigravity, and can also run as a CI check that exits non-zero on errors.
    195 npm
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Provides DevOps and testing tools for full-stack applications, including UI testing, security audits, CI/CD validation, and Rust/Tauri support.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Full-stack security for AI agents — static analysis + MCP runtime interception. 31 rules detect prompt injection, data exfiltration, backdoors, tool poisoning, and cross-file attack chains. Includes MCP proxy for real-time blocking, Python AST taint tracking, multi-language injection detection (8 languages), and AI-powered deep analysis. Free, offline, zero-config.
    49 npm
    17
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Provides debugging capabilities for Python, C, C++, Rust, Swift, and more through the Debug Adapter Protocol, enabling breakpoints, step-by-step evaluation, and stack traces.
    4
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Broccoli turns "the agent reads a stack trace and guesses" into "the agent drives the real debugger": it sets breakpoints, steps, inspects live variables over the Debug Adapter Protocol, and proposes a fix you approve in a diff — never applied silently.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables coding agents to load backend anti-slop rules and deterministically audit TypeScript/backend files for violations like SELECT *, SQL interpolation, N+1 calls, silent catches, stack leaks, type escapes, and TODOs, plus verify TypeScript compilation. Returns PASS/FAIL findings so agents can fix issues before shipping.
    82 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    A zero-dependency local MCP server and CLI that lets non-technical founders build and babysit AI-generated full-stack projects: it bootstraps runnable SQLite-backed app skeletons from a plain-language idea, traces front-end→API→database lineage, and audits for fake saves, swallowed errors, and exposed admin endpoints without spending LLM tokens. It also locks the blast radius of edits by Chinese button name and takes atomic snapshots/rewinds of both code and SQLite databases so a bad change can be rolled back in one step.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Bridges AI agents with VS Code's debugger, enabling breakpoint management, step execution, variable inspection, and stack tracing via CLI commands.
    25
    GPL 3.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    A stdio server that exposes 15 ios_* tools for iOS memory and diagnostic forensics: sampling simulator memory curves, drilling into allocation types on devices, querying unified logs, capturing hang stack samples, parsing pcap traffic, running pre-device preflight checks, and exporting/querying a linked event table. It also feeds a fixed six-section report and handoff workflow so measurements become comparable numbers and traceable records for developers.
    1
    MIT
  • F
    license
    Not graded
    quality
    Not graded
    maintenance
    A full-stack API automation testing server that parses OpenAPI/Swagger/Postman/HAR specs, generates comprehensive test scenarios and executable code, and provides AI-powered review and auto-fix.
    -