MCP Servers

Keyless local MCP server bringing ISTQB / OWASP / IEEE / ISO / EU AI Act QA standards into your AI client: standards-grounded retrieval, deterministic QA effort estimation, and automated QA document quality review (0-100 rubric) plus JUnit/CSV test-results flakiness analysis. uvx qai-consultant-mcp

Scaffold modern npm packages, CLIs, services, and full-stack monorepos from your agent. Three tools: inspect the option schema, preview the generated file tree, and write the project to disk — optionally creating the GitHub repo and pushing to it, or merging into an existing clone without overwriting anything. Also available as a CLI and a web configurator. npx -y packkit-mcp

Affected-test selection for Kotlin/Android projects: returns only the unit tests impacted by the current working-tree changes, so agents skip full test runs while iterating. Function-level static analysis via Kotlin Analysis API — call graph over functions, properties (initializers, delegates, accessors), constructors and callable references — with automatic multi-module and Android variant source-set discovery. Verified on Now in Android (34 modules, ~4s per query). brew install mikhailhal/tap/

🎖️ - Guardrail that checks agent-written code against a repo's own git-history-learned patterns — flags foreign dependencies, reinvented functions, misplaced code, broken layering, and gamed tests. Exposes voicecontext (the repo's familiar imports/idioms for a file, so agents write in-voice before generating), check (score a generated hunk against the repo's patterns), and explain. 100% local, no LLM, single Rust binary. npm i -g @tmonier/argot

🎖️ - Reliable async execution for agent tool calls: schema-gate hallucinated payloads before they run, absorb rate limits and outages with retries/backoff/circuit breakers, idempotency keys, human approval gates, encrypted credentials, replay, and signed-webhook results. Errors come back with an llmhint the agent can self-correct from. Hosted remote (api.klanexai.com/mcp, free sandbox) or npx -y klanex-mcp.

Log-stream tools for on-call / SRE agent workflows — expose rlg (RustLogs) log files as MCP tools. Three tools: taillog (last N events, filtered by level/target), filterlog (JSON-path-style predicates), summarizeerrors (grouped error taxonomy). Speaks JSON-RPC 2.0 over stdio; near-lock-free structured logging engine underneath (65k-slot ring buffer, 14 output formats, oslog/journald sinks). Install cargo install rlg-mcp or docker run -i ghcr.io/sebastienrousseau/rlg-mcp. Dual-licensed MIT OR Apa

Audit the images on any web page: natural vs rendered dimensions, oversized-image detection, and format breakdown, so agents can check web-image performance. Calls the hosted imagedimensions.com API, so no local browser is required. npx -y imagedimensions-mcp

Operator leaderboard measuring users, not models — ranks AI coding operators by token cascade efficiency (Yield = Cache Reads × Output / Input²). 15 MCP tools: rank, pull, submit (ed25519-signed), diagnose, simulate. Privacy-first: only token counts leave the machine. npx sigrank

Semantic codebase search + persistent working memory for AI code editors. Hybrid dense + BM25 search over AST-aware chunks, a symbol graph for locate/trace, and typed notes that survive context compaction and session restarts. Local embeddings, zero config, no API key. pip install vectr

CI for ink interactive-fiction stories. Compiles, exhaustively playtests every branch, and finds runtime errors (with a repro path), unreachable knots, and every distinct ending — so an agent can verify the story it wrote. Writes no prose. claude mcp add inkcheck -- npx -y inkcheck mcp

Render and verify native Rust GUIs with no display or GPU: render to a typed accessibility tree, query/interact by semantic selector (never coordinates), check contrast/focus-order/hit-target-size, diff screenshots, and watch motion play as a captioned filmstrip. 13 tools. cargo install fenestra-mcp.

Structural code context server for AI agents — compressed symbol indexes, dependency graphs, and git diffs via TypeScript AST analysis. Zero external dependencies, no vector database or embedding API required.

Webhook & callback layer for AI agents: create a callback URL, then waitforcallback to block until the webhook lands — signature-verified and decrypted — instead of polling. Verify HMAC, list/replay callbacks. npx -y @hooksense/mcp

Audits a domain email deliverability: SPF, DKIM, DMARC, MX, mail provider, DNS blacklist, catch-all, and domain age, returning a 0-100 health score via an Apify actor.

Shorten links, read click analytics, generate branded QR codes, and manage links on opn.onl — the open-source, self-hostable URL shortener. Works with the hosted service or your own instance.

Routes an AI coding agent's code search through an official language-server index (clangd / Roslyn / tsserver / pyright) instead of grep, returning a token-capped file:line list with no source bodies — ~20× fewer tokens. Also symbol-level edit-by-name, a Bash-grep→indexed-query rewrite hook, and git/p4 output compaction. Local-only, no IDE. Claude Code plugin + vts CLI.

Capstone of the Grand Line MCP set: a "collect them all" server that unlocks once the other tools are installed. pip install laugh-tale-mcp

MCP server that lets AI agents create and manage public tunnels to local services (webhooks, dev servers, sharing) — six tools covering HTTP/TCP/UDP tunnels, custom subdomains, regions, and load-balanced pools. Pairs with the rustunnel CLI; managed cloud or self-hosted (AGPL).

Type-faithful calculator: evaluate expressions under fixed-point, IEEE-754 double, or exact rational arithmetic, with every answer labelled exact vs inexact. Tools: calculate, analyze, solver, help, info. Offline, no network. uvx mcp-abacus.

Semantic code graph MCP server for AI coding agents. Indexes your codebase into a typed graph (functions/types/modules as nodes; CALLS/IMPORTS/DATAFLOW/EFFECTS as typed edges) and exposes 40+ tools for call-chain tracing, data-flow analysis, semantic search, and invariant checking — so agents navigate code structure instead of reading files line by line. npm install -g grafema

Structural memory for coding agents. Indexes TypeScript/JavaScript repos and exposes callers, callees, blast-radius impact, and symbol locations over MCP — with file:line@sha evidence anchors and branch-aware differential impact — so agents answer "who calls X?" / "what breaks if I change X?" without re-reading files. Local-only, zero telemetry, Apache-2.0. npx @graphpilot-oss/graphpilot mcp

🎖️ - Built-in MCP server for Radar, a modern Kubernetes visibility tool. Lets AI agents query cluster topology, resources, events, logs, and Helm/GitOps state across multiple clusters. Single binary, no agents, no cloud dependency. Apache 2.0.

Read-only static scanner for MCP / agent-gateway production-readiness. The scangateway tool scores a repo across 7 security dimensions (RBAC, fail-closed, supply chain, observability, cost, secrets, prod-readiness). Never executes code or prints secret values.

MCP server for the VerifyAX platform. Enables agent evaluation, simulation testing, and functional/non-functional verification workflows through natural language.