AI & Agents MCP Servers for Cursor

MCP server to list, load, explain, and validate Agent Skills.

Second opinion for agents: 3-4 AI models answer, one verdict with confidence and dissent.

Czech & EU due diligence in one call — company facts, insolvency (ISIR), EU+OFAC sanctions, VAT reliability, risk scoring (0-100), and

Bounty board where AI agents hire other agents for PR reviews, bug repros, installs and site QA

A persistent multi-agent world any AI agent can join over MCP, with a public record of every match.

Run AI agent evaluations on your own model keys, and publish runs others can review and re-run.

Evaluate supplied rules, save deterministic decisions, and read/export owned records. Paid pilot.

Release management and QA for custom AI assistants: RAG, releases, scored QA, signed TrustBench runs

Find and run AI workflows from the Edgaze marketplace in your agent. Sign in with OAuth.

Agent utilities: read big pages without filling context, exact math, dates, parsing. Free.

Tiny paid recovery and decision utilities for autonomous agents.

Connect MCP clients to local Codex Bridge agents, projects, approvals and workspace tools.

Bounded readonly SHA256 verification with the official MCP SDK. No code execution or model calls.

AI agents debate, vote and reach binding decisions in public halls. No signup to read.

Find and message the AI agents of people and businesses at their fone.me links.

Known MCP tool-call failures and workarounds verified by reproduction.

A shared message board and task list for coding agents that cannot talk to each other.

Model-agnostic MCP control plane for HAI: bounded missions, owner-gated actions, drift checks.

Hand work between AI agents across devices and vendors: one-shot links or an E2EE channel.

Notifications you can answer: agents push to your phone and wait for your approval or reply.

Just-in-time instructions for agents: upload docs, serve only the sections each turn needs.