"Setting up services on a Linux virtual machine" matching MCP servers:

A validation layer for AI coding assistants that enforces explicit LLM evaluations on plans, code diffs, and tests to ensure safer and higher-quality code.

Enables AI assistants like Claude to navigate git repository history, providing insights into code evolution and helping understand legacy systems.

Governed development control plane for VedaOps projects, letting authorized agents inspect, search, patch, test, lint, and coordinate registered software without exposing a general shell.

Enables AI assistants to analyze project folders for dependencies and frameworks and fetch current documentation or datasheets from the web.

Codebase Q&A agent with git-history awareness. Explore a repo with list_files, read_file, and search, plus git log, blame, and diff and a repo map to answer "why did this change?" questions. Runs locally as an MCP server for Claude Code and other MCP clients.

A lean, local knowledge graph that joins a repo's code to its aSPARK delivery artifacts, enabling agents to trace user stories to code and assess impact of changes, served over MCP.

Enables executing arbitrary Joern/CPGQL queries against a loaded Code Property Graph, loading source code in multiple languages (PHP, Java, JavaScript, Python, C/C++) to build new CPGs, and inspecting loaded projects and the active workspace. It communicates with a running Joern server over its synchronous HTTP query endpoint, so no state polling is required.

Zero-dependency MCP server inspector for protocol conformance, tool annotations, and capability checks.

Helps AI assistants optimize Linux workloads on Arm64 by parsing perf report output, recommending NEON SIMD intrinsics for hot loops, and auditing Python dependency manifests for arm64 wheel availability — all offline and structured.

Local memory for coding agents that can refuse, not only recall. A rule carrying a machine-checkable proof blocks the matching command before it runs, while prose-only rules can warn but never block.

Structural memory for coding agents — 60% fewer tokens, refactor-safe, runs entirely on your machine.

A local-first MCP server that scores your codebase's Build Readiness by reading code and running tests on your machine, outputting a diligence-grade score and risk register without uploading your source.

Parses Unity text-serialized .prefab, .unity, and .asset files to output only Inspector-visible data in hierarchical YAML, reducing token usage by up to 96%.

Enables an AI assistant to debug ABAP code on a connected SAP system by setting breakpoints, running code, and capturing call stacks and variables, with one-shot or interactive stepping.

Wraps Claude Code's code-review skill so any MCP client can run reviews over a PR, branch, working directory, or last commit, with five parallel reviewer subagents, low-to-max effort levels, and optional fix mode that edits files in place. Also supports follow-up questions on a previous review session and a free environment self-check.

A local Git intelligence MCP server that provides deep repository analytics including hotspots, churn, knowledge maps, and risk scoring, all computed from commit history without data leaving your machine.

Enables AI assistants to analyze a local codebase and answer impact questions like 'what breaks if I change Y?' through local indexing, search, and reverse dependency analysis, with no code leaving the machine.

Lifts machine code to VTIL intermediate language and emits pseudo-C for VM handler characterization. Complements concrete execution tools with static IL analysis.

Enables semantic and keyword search over a local codebase by chunking source files along function and class boundaries, embedding them offline, and fusing vector and BM25 results. Runs entirely on your machine in a single SQLite file, so AI coding agents can find relevant code with no API keys, telemetry, or cloud calls.

A Model Context Protocol server that accelerates CodeIgniter-inspired PHP framework development by generating, validating, and maintaining idiomatic MVC plus Services/Repository code via 7 tools and 4 resources.

Godot 4 MCP server with: Test running (GUT/GdUnit4) with structured pass/fail results API docs search with 30+ Godot 3→4 migration mappings Script analysis detecting 10 common GDScript pitfalls Scene/resource file parsing with antipattern detection Viewport screenshot capture LSP diagnostics from Godot's language server TypeScript, cross-platform (macOS/Windows/Linux), published on npm

Enables AI agents to query Linux kernel source code, git history, LKML discussions, Patchwork patches, and documentation with evidence-ranked results, citations, and explicit assumptions or contradictions.

locidx

Enables agents to validate JSON, JSONC, YAML, and TOML configuration files against official SchemaStore schemas, pinpointing errors and likely key misspellings, and to look up schema-backed setting details.

Enables MCP-compatible AI clients to generate markdown documentation for single code files or batches of up to 20 files, using a Writulos Scribe API key.

Lets any MCP client call SWARM's live services — GitHub code-health scans, researched summaries and reports, and everyday utilities — paying per call in USDC on Base with no account or API key. Payments are metered by a spend cap and only settled after the work succeeds.

maven-mcp gives AI agents (Claude Code, Cursor, Codex, Grok Build and any MCP client) live knowledge about JVM dependencies. It looks up the latest versions on Maven Central, finds outdated dependencies in Maven, Gradle and version catalog files, checks known vulnerabilities via OSV.dev, pulls changelogs and licenses, and builds dependency graphs with deps.dev. It's a single-file Python 3.9+ serve

Enables AI coding assistants to look up KUKA system variables and KSS alarms, lint and diagnose KRL projects, perform industrial safety audits, and read live controller telemetry from KRC4/KRC5 or virtual controllers.

A local MCP server that audits software projects against the UK ICO Age Appropriate Design Code (Children's Code) entirely on the user's machine.

Analyzes codebases for cross-platform compatibility issues, detecting platform-specific APIs, file path problems, line ending inconsistencies, and shell command incompatibilities across Windows, macOS, and Linux.