Development MCP Servers
Discover Development MCP servers for AI agents. Browse, compare and install Model Context Protocol servers for Claude, Cursor, VS Code and more.
FeaturedAllOfficial πDevelopmentProductivityDatabaseSearchWeb ScrapingFile SystemVersion ControlCommunicationCloud ServiceCloud StorageMarketingFinanceDesignMemoryOther
Showing 1-30 of 4912 servers
Sort by:
OpenEye
Development
Give AI agents real computer vision: pull and run YOLO, RF-DETR, Grounding DINO, Depth Anything V2 and SAM 2 locally for object detection, depth and segmentation, returning structured JSON. Optional hosted detection API. Open source (MIT).
Formkove
Development
Set up website forms on Formkove from your AI assistant: create forms, get the form code for HTML, React, Next.js or Astro, check usage, and read submissions with a separate read-only key.
SkillMaxx
Development
Free directory of agent skills, plugins and MCP servers, re-installed nightly in clean sandboxes in Claude Code, Codex, Cursor, Grok Build and Pi, with the exact install command for each.
Importly
Development
Download, transcribe, and read metadata for any video or audio URL. Works from servers and agent sandboxes where downloads usually get blocked.
STATICA
Development
Suresoft STATIC static analysis from coding agents: analyze changed files, upload results, and manage rulesets, metrics and reports. Requires a local STATIC installation.
hodgeguard-mcp
Development
Guardrail MCP server (stdio) that detects and halts non-convergent coding agent loops.
COVERA
Development
MCP server for Suresoft COVER code coverage: run coverage builds for C/C++, C# and Java, look up module coverage on the COVER server, and recover toolchain errors from any MCP client.
QuickMatch
Development
Free, read-only MCP server to search and compare AI tools for making video games. No API key.
VideoDB
Development
VideoDB lets an AI agent watch, search and clip video. Works in Claude, ChatGPT, Claude Code, Cursor and any MCP client.
Rivtor
Development
Rivtor helps developers deploy full-stack applications using a CLI or an MCP-compatible AI coding agent.
tunnel
Development
Local HTTPS proxy + mock server for app tests: record, replay, mock and break API calls, and read back what the app called.
Ruling
Development
Look up and compare AI agents (coding agents first) from your editor: facts, pricing, licenses and community scores from ruling.so. Read-only, no API key. Tools: search_agents, get_agent, compare_agents. Endpoint: https://ruling.so/mcp
AI Compute Radar
Development
Which open models fit your GPU or Mac, measured: fit verdicts, GPU rental prices from eleven sources, model popularity and a weekly pick. Read-only, no key.
Dependency Risk Audit (Tidy Button)
Development
Check a lockfile for known vulnerabilities and risky licences, and get alerted when new ones appear.
ParallelSandbox
Development
Gives your coding agent a real Linux machine with Docker and a browser to build and test your project, then hands you the running version to try and continues from your feedback.
Wingbox
Development
Local code graph for coding agents: the files a change will break (blast radius), where a symbol is used, the architecture of each part of a repository. No model, no network.
prompt-to-store
Development
From one prompt to Google Play and the App Store inside your coding agent: plan, build, test and ship a Flutter app via Codemagic, with keys kept out of the chat.
Centralino
Development
Wires one MCP dispatcher into Claude Code, Claude Desktop, Codex, OpenCode, OpenClaw and Hermes in one command, merge-only, with a health check.
Nalvorn Checks
Development
Deterministic agent checks: manifests vs sha256, JSON Schema, payment receipts on Base, OpenAPI drift, DNS, TLS, headers. Free checks, paid per call in USDC via x402.
Phase Two Keycloak
Development
Set up passwordless login, SSO, organizations and clusters on Phase Two hosted Keycloak from Claude Code, Cursor or Codex. The companion skills also cover self-hosted Keycloak.
Image Upscaler 2x 3x 4x (Real-ESRGAN on CPU)
Development
Makes images 2x, 3x or 4x larger with the open Real-ESRGAN model on CPU and returns PNG, JPEG or WebP files, one row per image with a link to the file. It sharpens but does not invent detail, and it is not a face restoration tool. Images that could not be upscaled are not charged. It runs as an Apify Actor through Apify's hosted MCP server, so you need an Apify account and API token. Paid per image and per output megapixel, 0.0025 USD an image and 0.004 USD a megapixel on the Free plan plus a small start fee. Unofficial tool.
Lugh
Development
Write, check and dry-run AI agent programs in Lugh, a language where permissions, budgets and human approval are part of the code. Every action passes a policy gate in a sandbox, and each run ends with a policy log.
JiZhiMCP (ζζΊMCP)
Development
Cross-platform MCP gateway: host any HTTP API as standard MCP tools behind one streamable-HTTP endpoint, with unified auth, usage dashboard and a tamper-evident cross-agent settlement ledger.
omnigami
Development
Find omnigami skills: public catalogue search, install instructions and free-first recommendations.
Countersign (LLPRO)
Development
Remote MCP server. Independent signed check of AI work before you rely on it: math, quotes, sources, links, code. Free tier, no key, no sign-up; paid calls past the free daily limit. Endpoint: https://countersign.llpro.ai/mcp?via=mcpservers (streamable HTTP). Operated by LLPRO LLC.
Agent Record (LLPRO)
Development
Remote MCP server. Check an MCP tool or agent before you use it: daily census of which tools work, work record, signed receipts. Free tier, no key, no sign-up; paid calls past the free daily limit. Endpoint: https://agentrecord.llpro.ai/mcp?via=mcpservers (streamable HTTP). Operated by LLPRO LLC.
Hallway Test
Development
Order a usability test with a real person from Claude Code, Cursor or Codex. The recording, think-aloud transcript and friction points come back to your agent within 24 hours.
Trent AI
Development
Trent AI is the judgment layer for your security tools. It shows which findings are actually exploitable across your code, cloud and AI agents, then fixes them with your coding agent and verifies each fix.
Navego
Development
Drives your own signed-in browser from any MCP client over a loopback bridge and MV3 extension: 45 browser_* tools, consent-gated commits, machine-readable navego doctor --json. No cloud session.
PasteShield Secret Sanitizer
Development
Reversible zero-dependency local secret sanitizer & workspace leak scanner that scrubs API keys, JWTs, DB URIs, PEM keys & internal IPs into <CATEGORY_N> placeholders in RAM before cloud LLM prompts and restores replies in 1 call.