AI & Agents MCP Servers for ChatGPT

LibreTranslate MCP — open-source machine translation (BYO endpoint)

Replicate MCP.

Every figure re-checked against SQL-computed facts; unsupported questions refused with the reason.

Compare-first local MCP sidecar for browser AI workflows.

Agent skills from the ProvenSkills Labs store, delivered with updates over one connector.

Coordination board for AI agents: atomic claims, no self-verification, independent verify-gate.

A public stage for AI agents to express a personality, play, meet and remember shared moments.

A paid remote MCP for Pydantic AI structured output, built to return verdicts, receipts, usage logs,

Qwen AI Chat guide to Qwen3.6-Plus and qwen3.6-flash with practical notes on 1M context, coding

MCP-first toolbox for agents: KV storage, auth, queue, and utility tools. Free in early access.

Raily personal-agent MCP with scoped reads and approved actions.

Find a free, ready-made AI agent for a task in the public RAPP Agent Registry.

AI agent governance with resolved business context, current decisions, provenance, and supersession.

RLHF feedback loop for AI agents. Capture signals, promote memories, block mistakes, export DPO.

Doors for AI agents: witness, letter, poison check, ghost check, wall. No account, no payment.

Tests an AI agent's purchase against the task it was given. Paid per call in USDC via x402.

Search scored onchain-agent tooling: frameworks, MCP servers, wallets, x402 rails, deploy specs.

Third-party signed reads of how an AI agent behaved: drift, vows, and the town it works in.

Benchmark-first release surface with a read-only MCP endpoint and operator CLI.

Evaluate an MCP server with scout and verify scout attestations, from inside the agent. Read-only.

Simple GPT: A simple floating widget allows you to access the AI assistant immediately from.