AI & Agents MCP Servers for Devin Desktop

Read-only, tenant-scoped access to Tracelane agent traces and guardrail verdicts

Translation for AI agents — translate, detect, batch; Japanese keigo registers. OpenRouter.

AI governance MCP server — policy enforcement, skills, memory, multi-LLM consensus

Agent Commerce MCP — agent-native A2A storefront. Discovery, Stripe checkout, affiliate program.

Agent runtime full-stack interception: allow/deny tool calls, Ed25519 receipts, blocks RCE, theft, SSRF, injection, stdio.

Inspect AgentMark traces and drive AgentMark Cloud: apps, experiments, metrics, deployments.

Official Anam AI MCP server for managing AI personas

A powerful MCP server providing access to multiple AI models (Grok, Gemini, Kimi, Qwen, GLM) through OpenRouter. Perfect for Cursor, Claude

Runtime governance enforcement for AI agents. Zero token overhead.

Package intelligence MCP for AI agents — 22 tools, 19 ecosystems, AGPL SDK, free.

The open routing layer for AI tools: tool calls routed per policy, decision on every result.

Search 1,000+ battle-tested AI prompts from getprompts.org into Claude Code, Cursor, ChatGPT.

Local Fusion MCP: panel->judge->synthesis on the Claude CLI subscription, no OpenRouter.

MCP server that nudges better AI session behavior through token usage and efficiency analysis

Classifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it.

MCP server that advises LLM model routing & cost BEFORE the call — estimate_cost, recommend_model, should_offload_local. Pure logic, no API

Up-to-date LLM pricing + availability catalog with cited sources for AI agent routing.

logi Agent Approval Gate — human approval on the phone before high-risk agent actions.

MEOK AAIF Agent Card MCP — Linux Foundation AAIF agent identity bridge. Issues + verifies +

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

MCP server for Fabric AI patterns