Development MCP Servers

MCP server for analyzing API requirements, evaluating test coverage, and generating or maintaining Postman/Newman automation.

MCP server for analyzing performance requirements, generating and extending Apache JMeter test plans, evaluating JTL results, enforcing thresholds, and creating draft pull requests.

Reusable QA core for MCP servers, providing requirements analysis, traceability, coverage, change planning, secure patching, and GitHub integrations.

A feature-fich MCP server and CLI for Allure TestOps test management system

Lance is an agent that runs on its own cloud Mac and handles everything on the App Store Connect side of shipping an iOS app. It connects to coding agents like Claude Code and Codex through MCP and takes over the parts they can't do: creating apps on App Store Connect, setting up notifications / widgets, filling out listing metadata, uploading builds to TestFlight, submitting for review, and responding to App Review feedback. Because it has its own Mac, it can also build, run, and test users' apps and capture screenshots.

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Searchable library of 5,900+ agent skills — 10 MCP tools; free tier serves metadata, a free API key unlocks full skill content. Remote Streamable HTTP at mcp.skilldb.dev.

Runtime guardrails for AI agent MCP tools. Blocks dangerous tool calls at runtime with a default-deny policy proxy.

Decision tracking with prediction validation and outcome gates for AI agents

Free in-browser document scanner: photo → clean PDF. Crop, fix perspective, add an optional watermark or signature, and compress. No upload or sign-up.

AI-powered screenplay writing studio.

Ask Claude if any AI provider is down — a hosted MCP server with real-time status, incident history, and 30-day uptime for 75+ AI services, no auth.

Single MCP server that routes across multiple LLM providers for lower cost, fewer rate limits, and more available tokens.

Give scoped API access to Chatgpt or Claude to your repo via a docker container. isolated by default changes don't hit you repo unless you allow it

App screenshot generator for the App Store and Google Play

Human feedback for AI agents — read visual bug reports and review comments from staging previews, reply, and close them once fixed.

Charon gives AI clients scoped, auditable access to Lethe memory. connect to Chatgpt or Claude to store memories locally.

A free, local MCP server that syncs your Figma files to your machine so AI coding tools read the real design instead of guessing from a screenshot. Link (GitHub or docs)

Governed MCP gateway: approval gates, signed audit receipts, and cost control for agent tool calls.

The first MCP server governed by ICA. A remote streamable HTTP server at https://mcp.aleeth.com/mcp with 37 governed tools: every call is risk-checked by Rail Guard before it runs and sealed with a signed Ed25519 receipt on a hash-chained public ledger anchored to Bitcoin. Fails closed: no receipt, no response. OAuth 2.0 with RFC 9728 discovery; anonymous requests get 401. This repository is the public interface and provenance record: a generated tool manifest with per-tool annotations, an SBOM and vulnerability scan with digested provenance, and a TRUST.md of verify-it-yourself commands. The implementation is private by design. Independent probe grade A from mcp-spec-check, re-verified 2026-07-24.

An MCP server that gives AI agents full onchain access to Cookie Chain — trade, launch, LP, stake, and bridge to Solana.

Codebase memory for coding agents, with no embeddings and no API key. A deterministic AST index answers "which files are relevant to this task?" in milliseconds, and agents write durable notes about the repo that are content-hash checked — a note flags itself stale the moment the code it describes changes. Notes are markdown inside the repo, so they commit and review alongside your code.

Visual verification browser for coding agents: daemon-based headless WebKit with snapshot, click/type, console capture, screenshots, and pixel-diff scoring. One static binary, Linux/Wayland. MCP server via `hwatu mcp` (stdio).

Run a fleet of AI agents across your devices, your providers, your workflows.

AI localization from your editor — translate an app's string files into 46 languages with placeholder-safe, reproducible output.

MCP gateway adding per-tool RBAC, tenant isolation, audit export, and PII redaction to any server.

32+ instant developer tools (JSON/CSS/HTML/SQL/XML formatting, Base64/URL encoding, SHA-256/512 hashing, UUID generation, regex testing, JWT decoding) via REST API. MCP + OpenAPI ready. Free tier available. Built for AI agents.

AI-native repository intelligence, architectural governance, and living AST graph analysis tool.

Post-quantum cryptography readiness: scans code and dependencies for quantum-vulnerable RSA/ECDSA/ECDH, plans migration, and verifies fixes.

Independent governance and authorization layer for autonomous AI agent execution, with budgets, verification, recovery, evidence, and auditable receipts.