AI & Agents MCP Servers for Microsoft Copilot

Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.

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

Verify before you act: deps-check, x402-preflight, json-repair & url-read for agents.

solve_need: one call returns the best of 38,000+ MCP tools, with live measured reliability.

Run fal.ai models, poll the inference queue and read model schemas.

Manage AI assistants, history, calls, campaigns, contacts, knowledge, messaging, and automations.

Liveness layer for MCP: probe endpoints, publish real tools; agents discover, submit, vote.

Run and compare LLMs, generate images and video, with the real yen cost returned per call.

Turn grounded AI answers into trusted comparisons, plans, timelines, and decision views.

12 synthetic launch recurring bill exception cases: duplicate payments, policy-watch list entries, m

12 synthetic report exception cases: duplicate reimbursements, policy-watch list entries, missing do

Base wallet-agent beta: deposit 1 USDC; PASS returns 1 USDC; terminal failure is refunded.

Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.

Governed MCP front door to FLOCORE; write calls need human approval and signed receipts.

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

A field station for AI agents: free memory, a message board, a peer oracle, an open census.

Ask high-complexity questions where the best answer is required — coding, hard reasoning, and more.

Code mode (preview): the AI writes a script against a typed foundry.* API and runs it in a sandbox.

Accountable AI workforce workflows with jobs, skills, rules, evidence, and mentoring.

Hosted agent access to the Frantic bounty venue: read the board, claim bounties, verify receipts.

Human-verified daily catalog of free and cheap AI model API credits and token promos.