MCP Servers

Local MCP voice coach with English pronunciation, grammar, fluency, phoneme-level feedback, practice drills, and learner-profile hints. Install via uvx mcp-server-pronunciation@0.3.0.

Local-first MCP server for Canvas LMS. Stdio transport, no third-party broker, token stays in ~/.canvas.env. Exposes courses, assignments, modules, announcements, grades, planner items, upcoming events, todo, and bulk file dump as MCP tools.

Agent-operable ML experiment contract (cq.yaml + JSON contracts) with a built-in MCP server exposing 14 tools (resolve/inspect/run/validate/describe/compare/lineage) for running, validating, and tracing experiments across any framework (PyTorch / HF Trainer / Lightning / sklearn / XGBoost). Apache-2.0.

Deterministic batch tools so LLM agents stop next-token-guessing dates and math. Rich now() snapshot (18 fields), calendar(ops) batch dispatcher (diff/until/since/add/weekday/businessdays, natural-language parsing), calc(expressions) Python eval with math+stats pre-loaded, and Pint-based unit conversion. One wiring for da

C++26 paper reference MCP (cpp26-ref) backing a Claude Code plugin: lookuppaper, fuzzy search, compilerstatus over a 216-paper ISO/IEC 14882:2026 corpus. The plugin's skill + reviewer subagent use these tools to bias Claude toward reflection, contracts, std::execution senders, #embed, expansion statements

Jaeger distributed tracing MCP. 5 tools: listservices, listoperations, searchtraces, gettrace, getdependencies. Any Jaeger instance (HTTP API v3); PyPI + MCP Registry.

CLI-first API testing tool with structured JSON failures (failurecategory, errorcode, hints) so AI agents can branch on the taxonomy without parsing stderr. MCP tools: tarnrun, tarnvalidate, tarnfixplan, tarninspect, tarnrerunfailed, and more. Tests are .tarn.yaml. Single static binary (musl), MIT.

Behavioral verification intelligence for autonomous coding agents. Builds a behavioral graph of any TS/JS repo, clusters into 25 semantic workflows (Auth, Payments, Webhooks, Caching, Queue, etc.), detects drift, generates concrete adversarial probes (idempotency, retry storm, cache stampede, replay), emits per-workflow risk + confidence. 1

Structural code intelligence MCP server for AI-assisted development. Navigate and edit code by symbol names instead of raw text — symbol lookup, dependency graphs, call chains, dead code detection, and structural diff. Replaces grep/cat with semantic tools: 87% token reduction on large codebases.

Zero-config MCP server that gives AI coding assistants a real-time diagnostic snapshot of your local dev environment. Detects framework, running services, recent errors, and git state in one call.

A lightweight MCP server for structured bug-fix analysis and project-local verified fix memory for AI agents.

Strict AI code reviewer powered by Groq. Finds bugs, vulnerabilities and SQL injections. Tools: analyzecode, comparecode, explaincode, generatetests, analyzefile, HTML reports.

9 MCP servers for React + TypeScript development automation — component scaffolding, dependency auditing, WCAG accessibility checking, test generation, TypeScript enforcement, and monorepo management. 134 tests, CI on Node 20+22.

AI 測試大師 — end-to-end QA loop over MCP. Drives pytest / Jest / Cypress / Go / Maestro from one surface; analyzes URLs (Web DOM) or live mobile screens (maestro hierarchy) to extract testable modules, generates runnable pytest or Maestro YAML with real selectors (not # TODO stubs), runs with auto-retry, then writes a

🎖️ - MCP server for Jungle Grid, an agentic GPU execution layer that lets AI agents estimate, submit, monitor, and fetch logs for inference, training, fine-tuning, and batch workloads.

Write-side MCP for Figma — complements Figma's official read-only MCP. 41 tools for building and editing Figma designs from Claude Code, Cursor, Cline: JSX-like tree creation, variables/tokens, components, cross-page navigation, and visual verification via screenshots. Install: npx -y genable-mcp.

The most complete API testing MCP — Postman inside your AI assistant. Per-project environment groups with {{variable}} interpolation, saved collections, multi-step flows with response extraction, assertions, load testing, and OpenAPI mock generation. 42 tools, zero cloud account needed.

iOS leak hunting and performance investigation. Reads .memgraph (leaks(1)) and .trace (xctrace) files, classifies retain cycles against a 34-pattern catalog (SwiftUI, Combine, Swift Concurrency, UIKit, Core Animation, Core Data, SwiftData, RxSwift, Realm), surfaces a Swift fixTemplate snippet for each

Local, read-only retrieval over official Python standard library docs with exact symbol lookup, section-level results, and version-aware context.

Companion Gallery for Codex: public read-only registry for Codex-compatible animated companion packs. Search, preview, install community pets, generate badges/embed cards, and discover the request flow via Streamable HTTP MCP.

MCP server for Atlassian Jira and Confluence with schema-validated Markdown↔ADF conversion. Catches content-model violations at conversion time rather than silently dropping ADF-only nodes like panels, mentions, and layouts.

An AST-aware structural repository graph engine and MCP server designed for AI agents. Understands Go struct embeds, public API surfaces, SQL queries, and error mapping to give agents instant codebase context without blindly grepping.

MCP server for interactive .NET / ASP.NET Core debugging via netcoredbg. 27 tools: breakpoints (line, function, exception, data), stepping, thread inspection, exception autopsy, hang/deadlock analysis, and request tracing.

Context engineering MCP server. Generates CLAUDE.md from git history and architectural file sampling, and maintains a concept-map snapshot of features/flows → files so agents can skip grep/glob on repeat queries.