Development MCP Servers — Page 29

Hosted OAuth 2.1 + Dynamic Client Registration (RFC 7591) for MCP servers

Vendor-neutral gate between AI agents and production infrastructure. Deterministic policy engine, human-in-the-loop approval with diffs, JSONL audit log, graduated autonomy via empirical track record.

MCP server that lets Claude Code agents delegate tasks to agents in other project directories, with parallel dispatch, sessions, and async jobs.

Security-first MCP bridge between Claude Code and your Chrome, with HMAC pairing, a per-domain allowlist, and opt-in JS evaluation for driving and debugging live browser sessions.

App Store data, built for AI agents

Salesforce integration using OAuth2. Write operations disabled by default per integration. 700+ tools covering SOQL, SOSL, REST, and CRUD, individually selectable. Requires a DataGrout account.

Better agentic Rails development, runtime-level tools for your agent to talk to your running app.

Better agentic Phoenix development, runtime-level tools for your agent to talk to your running app.

Read-only MCP server exposing the Safer Agentic AI safety framework: 238 patterns + 14 operational heuristics via 12 query tools; Python stdio.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Let AI agents run your whole stack

Open-source MCP server connecting AI agents to the Godot Editor and runtime (Godot 4.x, C#).

Open-source MCP server connecting AI agents to Unreal Engine 5.7, editor and runtime (C++ plugin + .NET sidecar).

Read-only MCP server exposing turva.dev's agent-readiness scores, service catalog and security evidence.

Search thousands of community-vetted Claude Code skills, MCP servers and marketplaces and load_skill a real SKILL.md mid-task, ranked by installs and GitHub stars.

Upload DOCX, get embeddable HTML previews via MCP using Claude Code, Cursor, or Codex

Generate sprites, animations, tilesets, and game art with AI.

Objective-native planning board for agent-led development

Connect bugAgent to any MCP-compatible AI client. File, classify, and manage bugs, feature requests, and more directly from your AI coding assistant. No context switching, no copy-paste — just describe the issue and bugAgent handles the rest.

DataGrout - Discovery, governance, and orchestration layer for AI agents working across multiple MCP servers and integrations.

Search DevExpress documentation (300,000+ help topics) using natural language queries across Angular, Blazor, WPF, WinForms, ASP.NET Core, React, Vue, and more in the AI Coding Assistant and/or IDE of your choice. Receive instant code examples, implementation guidance, and step-by-step instructions. Built-in tools and prompts guide AI coding agents to help developers build better applications faster with DevExpress components.

Hosted Streamable HTTP MCP server for IP intelligence, fraud risk scoring, email validation, DNS, WHOIS, domain age, quota, and usage tools for AI agents.

Collection of agent skills that turn your AI coder into a SAST scanner

Local-first MCP tools for AI-assisted work receipts, source intake, workspace maps, routing ledgers, action receipts, and MATCH / DRIFT / UNVERIFIABLE verification.

Hub of 30+ developer & utility APIs as MCP tools: hashing, validation, DNS, currency, IP geolocation, IBAN, QR codes, GEO audits.

Search open SVG icon packs and fetch exact SVG markup from coding agents through MCP.

GPU infrastructure control plane + per-agent LLM FinOps. 74 tools. Deploy, scale, track cost per agent, enforce budgets. MIT license.

CLI tool that generates MCP servers from OpenAPI/Postman specs — pip install mcpgen-cli

Wrap your local MCP servers to check every tool call against policy and live state before it runs - allow, block, or request a refresh, with a reason the agent can act on.

Anchor is local repo and org memory for AI coding agents. It indexes GitHub PR history, current code, tests, regressions, architecture, and cross-repo impact locally, then exposes concise cited context through MCP and CLI workflows. Local-first. Read-only GitHub access. No CLI telemetry. No SaaS. No remote LLM calls.