-
Self-hosted Gmail broker for AI agents (formerly agentinbox): one place for credentials, MCP tools, real-time webhooks, guardrails, and a web console.
Version check not run yet
Email npm Local 2.6k a week MIT
-
Local multi-agent coding orchestrator with TDD, SonarQube, and code review pipeline
Version check not run yet
Developer tools npm Local 2.6k a week AGPL-3.0
-
Connect any AI agent to your Synchronex workspace — portable memory, decisions, and workers.
Version check not run yet
Model and agent tools Official MCP Registry · npm Local 24 a week APACHE-2.0
CR
Creedspace io.github.Creed-Space/creedspace-mcp-server Constitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication.
Version check not run yet
Model and agent tools Official MCP Registry · npm Local 24 a week MIT
FI
First io.github.XJTLUmedia/context-first-mcp 37-tool MCP server: context health, memory, reasoning, truthfulness & research pipeline.
Version check not run yet
DevOps and infrastructure Official MCP Registry · npm Local 24 a week MIT
DA
DarkMatter io.github.darkmatter-hub/verifiable-agent-audit-trail Tamper-evident records of AI agent decisions. Verify offline, or publish a proof link.
Version check not run yet
Model and agent tools Official MCP Registry · npm Local 24 a week APACHE-2.0
-
MCP server caching expensive LLM responses: HTTP-style freshness plus semantic recall.
Version check not run yet
Memory and context Official MCP Registry · npm Local 24 a week MIT
-
MCP server for Tessera's LLM cost-optimization layer: anchored spend, drift, recommendations.
Version check not run yet
Model and agent tools Official MCP Registry · npm Local 24 a week APACHE-2.0
VE
Verify io.github.tomjwxf/verify-mcp Offline Ed25519 verification of signed receipts, bundles, and trust artifacts.
Version check not run yet
Model and agent tools Official MCP Registry Local
-
Constitutional guardrails and loop detection for AI agents
Version check not run yet
Model and agent tools Official MCP Registry · npm Local 29 a week MIT
-
MCP Gateway for exposing VAT agents through Model Context Protocol
Not run: no command to start
Model and agent tools npm Local 2.5k a week MIT
LO
Logic ai.nocturnus/logic-server Agent reasoning, memory, and token-optimized context for AI applications.
Version check not run yet
Memory and context Official MCP Registry · npm Local 34 a week BUSL-1.1
-
Zero-auth MCP: image optimize, cited storage/format data, and dev utilities LLMs get wrong.
100% up · 30 days
Files and storage Official MCP Registry · npm Local Remote 23 a week MIT
-
Create editable Draw.io architecture diagrams from prompts and reference images.
Version check not run yet
Design and media Official MCP Registry · npm Local 23 a week MIT
-
Turns your Prisma schema into typed MCP tools, with destructive writes gated behind human approval
Version check not run yet
Databases Official MCP Registry · npm Local 22 a week MIT
-
Local read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.
Version check not run yet
Model and agent tools Official MCP Registry · npm Local 22 a week MIT
-
Generate and edit images and video via OpenRouter or any OpenAI-compatible API.
Version check not run yet
Design and media Official MCP Registry · npm Local 22 a week MIT
-
Live LLM pricing, context windows and model ids, read from each vendor's own page every 3 hours.
Version check not run yet
Model and agent tools Official MCP Registry · npm Local 22 a week MIT
SK
Skillfed io.github.skill-federation/skillfed-mcp Find vetted agent skills for your task — privacy-preserving skill discovery over MCP.
Version check not run yet
Project management Official MCP Registry · npm Local 22 a week MIT
-
Token counting & multi-model LLM cost estimates: GPT-4o, Claude, Gemini, 25+. No API key.
Version check not run yet
Model and agent tools Official MCP Registry · npm Local 22 a week MIT