Development MCP Servers — Page 9

A pre-action risk gate your AI agent calls before any irreversible action — returns a risk score, named red flags, and a gate: proceed / confirm / human-required.

External evidentiary crystallization layer for AI governance, accountability anchoring, and independently verifiable decision records.

Query a catalog of 250+ open-weights LLMs — list, compare, estimate VRAM and API-vs-self-hosted cost — directly from Claude Code, Cursor or any MCP client.

AI coding context for Claude Code, Cursor and Codex

White-box MCP server giving Claude Code agents sexpr workflows you can cat, diff, patch, and replay across crashes; deterministic orchestration lets cheaper models handle multi-step tasks.

Efficient, SQL-backed C++ project indexer designed for large codebases with low memory footprint.

LLM proxy that benchmarks AI models on real prompts and finds cheaper, faster alternatives across 340+ models.

MCP server for coding agents that returns structured, low-noise tool output to reduce tokens/cost.

Postman for MCP — search 156 servers, inspect tools with schema visualizer, test live

Paid remote MCP for agent memory MCP, structured receipts, usage logs, and audit-ready evidence for agent and CI workflows.

Paid remote MCP for Pydantic AI structured output, structured receipts, usage logs, and audit-ready evidence for agent and CI workflows.

Paid remote MCP for CLI tool MCP, structured receipts, usage logs, and audit-ready evidence for agent and CI workflows.

Pay-per-success public-data result packs for AI agents with free quotes, source URLs, confidence, timestamps, and receipt hashes.

Pre-listing readiness checks for paid x402 and MCP tools, including public metadata, unpaid 402 behavior, launch packs, and bounded receipts.

Market-aware paid decision preflights before larger agent tool spend, helping agents decide what to buy, skip, or stop.

Connect any API to any AI agent

Neo is the first autonomous AI engineering agent that plans, researches and executes multi-step work for tasks such as building AI agents, AI model fine-tuning and evals, and ML pipelines; using your codebase, data, and experiments to ship faster with inspectable artifacts. It can reason over your repository, wire tools and retrieval, debug training runs, and help you develop production-ready AI workflows

AI health, token usage, LLM cost optimization, BYOK vault, and cleanup audits for MCP agents.

Developer context continuity system that builds a temporal knowledge graph of your codebase — modules, symbols, decisions, and open problems — and serves it to AI coding agents via 12 MCP tools, so every agent session starts knowing your architecture without manual context pasting.

Scaffold invite-only Python/FastAPI apps: auth, admin dashboard, dev server, deploy to fly.io.

Give your agents access to 100+ connectors and 500+ tools with secure, per-user managed authentication for every tool call

Paid remote MCP for Codex run ledgers, changed-file evidence, scope summaries, missing proof checks, and client-ready handoff receipts.

Paid remote MCP for AI browser purchase approval checks, spend thresholds, merchant evidence, risk notes, and audit receipts.

Paid remote MCP for agent data-access boundary reviews, permission scope evidence, sensitive data notes, and governance receipts.

Paid remote MCP for agent tool-call receipts, approval evidence, arguments redaction, result summaries, and review exports.

Unreal Engine MCP server for Claude Code, Codex, and AI agents to inspect and edit live UE projects through Blueprint, Material, PCG, UMG, asset, context, and diagnostics tools.

Paid remote MCP for schema drift checks, tool-schema approvals, compatibility receipts, breaking-change explanations, and release audit logs.

Paid remote MCP for AI agent safety replay checks, policy gates, eval receipts, control-fix suggestions, and release evidence exports.

AI-native network automation for MikroTik RouterOS. MikroMCP exposes RouterOS as a typed, auditable Model Context Protocol server so Claude, Cursor, Codex, and other MCP clients can inspect, diagnose, and safely operate MikroTik routers in natural language.

Resolves your Gradle project’s real classpath and returns Java source, method signatures, and class structure for any dependency class—using the version your build actually uses, not random files from ~/.gradle/caches.