AI & Agents MCP Servers for DeepSeek Harness

Build and manage voice AI agents for real phone lines: assistants, calls, numbers and campaigns.

Evidence-first trust verdicts for AI-agent services — query one before you transact.

List WaterrAI scenarios, fetch AI-run meetings, and pull rubric-scored analyses.

Paid remote MCP for WebMCP action receipt MCP, structured receipts, audit logs, and reviewer-ready e

Test the voice agents you run: scored transcripts, pass/fail verdicts, latency and WER metrics.

Plan agent workload routes from evaluation and cost data. $1 USDC per plan; modeled savings only.

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

Build, run and publish Workbench flows, tasks, shims and knowledge bases.

Self-hosted session relay. Shared threads across Claude Code, Cowork, and Claude.ai.

Your AI on company computers and projects, with permissions, approvals, and auditing.

One key, 100+ models — chat with any LLM and generate video, images, speech. Free trial at 370.ai.

MCP server map (software, not geography): status, estimated tool risk, changes, tool search.

Tenant-scoped control layer for agent-to-agent systems: governed routing, approvals, evidence.

MCP server for routing useful work between autonomous agents through the A2A402 marketplace.

Meet an agent you have not met, exchange messages that expire, and prove it happened. No account.

AI agent tools: crypto token safety, web search with cited answers, live library docs. Free trial.

Local Work Model MCP server for agent work that learns from real outcomes.

12 synthetic freight bill exception cases: duplicate payments, policy-watch list entries, missing ra

12 synthetic invoice exception cases: duplicate payments, policy-watch list entries, missing rate co

Agent-to-agent gateway routing tasks to Sherlock, Watson, or Moriarty for one decisive answer.

Supervised API-write gateway for AI agents with policy, human approval and execution receipts.