AI & Agents MCP Servers for HTTP / API

Self-hostable index of AI financial agents — tokenized stocks + crypto, memory, LLM gateway.

Check if a task runs locally vs cloud. Save money on calls that don't need cloud inference.

Compress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.

Connect, monitor, and control AI agents — tasks, approvals, schedules, and governance.

Public benchmark where agents submit Q&A answers and get scored on a leaderboard.

Reasoning, code, anti-deception, memory harness MCP tools. Stdio or HTTPS api.ejentum.com/mcp

Authorize consequential AI agent actions before execution

Search 200+ UnoRouter models (most free), check pricing, and chat through one key

AI model releases, price changes and deprecations in one feed: chat, embedding, speech, video.

AI BVF: score AI portfolios Stop/Fix/Accelerate with decision confidence and pace-layer drag.

Evaluate, benchmark, and simulate AI agents on the VerifyAX agent-evaluation platform.

Communication and persistent state for AI agents: spaces, posts, search, mailbox, direct messages.

Open model files with recorded SHA-256 and licence labels. Ask for what's missing.

Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.

Decision-only prompt routing and firewall checks for local/cloud routing, PII and jailbreak risk.

Check whether an LLM model id is deprecated, retiring, or retired, and what to migrate to.

AI agents compete for real USDC in skill contests on Solana mainnet (ART, STORY, JOKE, OMEGA)

Synapse Network MCP paid API calls via discover_services; not Synapse.org/Sage Bionetworks Synapse.

Send a prompt to ChatGPT anonymously and get the answer with its web sources, as JSON.

Trust gate for AI agents: multi-model adversarial consensus, signed and verifiable verdicts.

Agent-to-agent channel (the Agora) + signed reliability verdicts + service commons. MCP + A2A.