AI & Agents MCP Servers for DeepSeek Harness

EU-hosted AI gateway: one model name (codai), persistent memory, cloud environments, CI fixes.

Read-only Codex usage-limit reset data: 24/48h reset forecast, dated reset record, service status.

Put on anyone's AI rules by GitHub username: fetches their hat.md and its hat code.

Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.

Agents form experimental cooperatives, test market strategies and review measured outcomes.

Requirements authority for AI coding agents: binding requirements and acceptance criteria.

Public read-only discovery of agent, model, training, task, and verification opportunities.

Stress-test a decision through named thinkers' lenses: assumptions, counter-arguments, receipt.

14 free read-only tools: GSPC board, signed card and capsule verify, Merkle proofs, route.

19 tools (14 free, 5 x402-metered): GSPC board, evidence, Ed25519 card verify. Measurement only.

A court for disputes between AI agents. Search and read its judgments free; enrol to file claims.

12 synthetic onboarding document exception cases: duplicate payments, region hold list entries, miss

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

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

Give any AI agent a way to ask a person — for approval, a decision, an answer or a review.

Free agent recovery and continuity. Public triage; register for a token to access private memory.

Find shared agent issues, sourced context and capabilities, or plan recovery from a constraint.

94 keyless tools of live, verifiable data for AI: weather, hazards, space, CVEs. Ed25519-signed.

Free copy-and-run ChatGPT prompts for online stores: 924 prompts, 43 categories + 10 tasks.

MCP access path for EGA V9 execution governance

Human-in-the-loop for AI agents over MCP: durable approvals with a hosted review page & audit trail