MCP servers

AI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)

Model inventory and governance: trace deployed models and their dependencies as an append-only log

Enables AI agents to interact with ConfigCat, a feature flag service for teams.

Deterministic decision engine with receipts. Define rules in YAML, query a graph, get proof.

Bitemporal memory for AI agents with point-in-time recall and tamper-evident audit history.

Structural memory for coding agents: callers, callees, blast radius and symbols over MCP.

Local MCP server for reliable long-running AI coding workflows.

MCP as a Judge: a behavioral MCP that strengthens AI coding assistants via explicit LLM evaluations

Agent Room

rainyflash

Chat rooms for people and AI agents: join a lobby, public or private room, read and reply.

Persistent task context across TickTick, Notion, GitHub, Obsidian, Taskmaster and Beads

Event-sourced, auditable agent memory over MCP: cited checkout, replayable provenance.

The dependency bloodhound for AI coding agents. Zero API keys, zero config.

DeepSeek web vision model as an MCP server with browser auto-login.

Deterministic security scan of MCP servers, agent skills and npm/PyPI packages. Runs locally.

HKEx Filings

ascent-partners

Live HKEx (Hong Kong Stock Exchange) regulatory filings for AI agents.

Unblocked is the context layer for agentic software development.

Managed Playwright cloud browsers for scalable browser automation and AI agent workflows

Guidelines for UI components with a perfect UX, DX and AX, whether humans or AI agents write them.

Local multi-repo code graph over MCP. Blast radius, call graphs, and memory anchored to code.

Guard AI agents' PostgreSQL/MySQL access via MCP: SQL audit, auth, masking, write approval

Windows screenshots, OCR, and redacted screen recording for AI agents. No desktop app needed.

Smart hands for your AI agents - write-capable KVM+BMC+SSH MCP server: gated, verified, audited.

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

Project memory for coding agents whose memories carry code evidence, re-checked on every recall.

Credential isolation for AI agents. Inject secrets at the network boundary.

Lightweight MCP for infinite agent memory. Any agent, any session, anytime.

Hand a project over with the reasons attached. Local-first cross-agent memory MCP + drift detection.

Let AI agents build Blender scenes with four compact tools: discover, execute, inspect, capture.

Guardrailed fleet ops for AI agents: multi-cluster Kubernetes via OCM with policy, approval, audit.

Evidence-grounded agent memory with mandatory provenance, on local SQLite or Cloudflare D1

Cross-agent handoff: the next coding agent starts from the last one's facts, not a blank page.

Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.

Sato Hub: Build Onchain & Crypto Agents

satohub

Build any crypto agent: x402, ERC-8004, wallets. Does a server take your key? Hosted? Maintained?

A Model Context Protocol server for Wix AI tools

Open, Git-native memory protocol for MCP agents. Portable, versioned, human-editable.

Per-tenant bitemporal context graph built from domain events, shared by agents via five tools.

FAISS, call graph, AST, BM25 — 34 MCP tools for AI agents. 50-80% token reduction. Offline.

Self-hosted stealth browser for AI agents: Firefox engine + Rust MCP runtime.