AI & ML MCP 服務
LLM providers, agents, models, embeddings, inference, and machine learning workflows.
Agent Wallet Mcp
io.github.Rumblingb
Agent wallet and budget management for AI agents
Agent Audit Mcp
io.github.Rumblingb
Immutable audit trail for agent-to-agent interactions
Workloadtruth
io.github.RudrenduPaul
Classifies GPU workloads as inference or training from telemetry alone via MCP tools.
Truthroute
io.github.RudrenduPaul
Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP.
Toolgovern
io.github.RudrenduPaul
Wraps the toolgovern CLI as a single generic MCP tool for agent-tool policy validation.
Tokentrust
io.github.RudrenduPaul
Verifies token/cost savings claimed by AI context-reduction proxies via MCP tools.
Tenantguard
io.github.RudrenduPaul
Scans self-hosted multi-tenant AI-agent platforms for tenant-isolation gaps via an MCP tool.
Teamspend
io.github.RudrenduPaul
Compares AI coding tool spend before and after a migration via MCP tools.
Taskswarm
io.github.RudrenduPaul
Wraps the taskswarm CLI as a single generic MCP tool for multi-agent task coordination.
Swarmmesh
io.github.RudrenduPaul
Multi-agent context sharing, memory, and status coordination via MCP tools.
Swarm Rd Orchestrator
io.github.RudrenduPaul
Append-only event log for cross-agent context/memory sharing via 3 MCP tools.
Slop Eval
io.github.RudrenduPaul
Wraps the slop-eval CLI as a single generic MCP tool for genericness scoring of AI UI output.
Skillguard
io.github.RudrenduPaul
Security scanner for third-party AI agent-skill files (SKILL.md, hooks, scripts) via MCP.
Shimguard
io.github.RudrenduPaul
Wraps the ShimGuard CLI as a single generic MCP tool for agent-shim provenance checks.
Neuronscope
io.github.RudrenduPaul
Traces which neurons and attention heads drive a language model's output via MCP tools.
Memtrust
io.github.RudrenduPaul
Independent, reproducible benchmark harness for agent-memory backends.
Inferbench
io.github.RudrenduPaul
Benchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.
Haltproof
io.github.RudrenduPaul
Fail-closed deterministic checks and hash-chained receipts for AI agent outputs via MCP.
Evolveguard
io.github.RudrenduPaul
Wraps the evolveguard CLI as a single generic MCP tool for agent-skill file safety checks.
Electronics Rfq Agent
io.github.RudrenduPaul
AI quoting agent for electronics distributors. RFQ in, quote out via MCP tools.
Deskcert
io.github.RudrenduPaul
Evaluates whether an AI agent is safe to operate internal web apps via an MCP run_suite tool.
Agent Observability
io.github.RudrenduPaul
AI agent observability with deterministic record/replay for debugging agent failures.
Agent Eval
io.github.RudrenduPaul
Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
Agent Vending Factory
io.github.RubenTay
Pay-per-call MCP tools via x402 USDC: ZAR prices, data extraction, Python sandbox, SA flights.