MCP Servers 1,625

Connect AI agents to GlassFrog: roles, skills, notes, tensions, and governance.

Persistent memory shared across Claude, ChatGPT, Grok and other MCP clients.

Pay-per-call (x402/USDC-Base) web + crypto data tools for AI agents: audit, extract, crypto, DeFi.

Governed MCP gateway: approval gates, signed audit receipts, and cost control for agent tool calls.

Agent Almanac MCPNew

io.github.survivorforge/agentalmanac-mcp

B✓Verified

Search the Agent Almanac catalog of 9,000+ MCP servers from inside any MCP-aware agent.

Scientific compute for AI agents: symbolic, numerical, quantum, chemistry, ODE.

Agent ImmuneNew

io.github.denial-web/agent-immune

A✓Verified

AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening

A bounty board where AI agents do honest work for real money, sealed to a public ledger.

Inference AIopsNew

io.github.AIops-tools/inference-aiops

A✓Verified

Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 39 tools.

Agent CompanyNew

io.github.tcgtracker-boop/agent-company-mcp

B✓Verified

A legal home for AI agents: Wyoming $299 or Nevis LLC.

Free fan-convention data for AI agents: dates, registration windows & table costs, US & Canada

AI agent infrastructure: dedup, cost prediction, validation, governance, failure intelligence.

30 pay-per-call APIs for AI agents: compliance, trade, safety, web, data.

Luxembourg real estate for AI agents: property search, price estimates, market data, commutes.

Global shipping labels for AI agents via AfterShip with your own carrier accounts.

Privacy-first work tracking with summaries, reports, coaching, and AI-ready long-term memory.

Operate the AdCritter ads platform: campaigns, creatives, audiences, and reporting.

Collective MemoryNew

io.github.Hustada/collective-memory

B✓Verified

MCP server for persistent, semantic memory across AI sessions

A home for your agent's HTML artifacts - publish, pull, share and review them over MCP.

Deterministic gate for AI agents: ALLOW/DENY a step before it runs, sealed to a verifiable receipt.

Zero-storage MCP privacy proxy — PII tokenized before AI inference.

Agent GuardNew

io.github.ipezygj/agent-guard

A✓Verified

Safety checks an agent runs before it acts: package malware, destructive command, secret leak.

A business's marketing memory: campaigns, results, decisions, brand and audience knowledge.

Your team's shared, verified knowledge for AI agents: ask what's true, record what you learn.