AgentLore
- Kujirafu/agentlore
AgentLore is a MCP server that connects your agent to an AI-verified knowledge base with trust scoring, temporal facts, and skill cards.
About
AgentLore is a hosted Model Context Protocol server backed by an AI-verified knowledge base designed for developers who rely on agents daily. It exposes trust-scored facts, temporal information that can go stale on ordinary web pages, and skill cards that help you compare agent-oriented capabilities while you are still in the Idea phase researching competitors, stacks, and workflows. founders use it when early decisions—which MCP to adopt, which skill pattern to copy, what claims are still true—need more rigor than a generic LLM recap. Authentication is optional: unauthenticated callers receive limited results, while a Bearer token (aglo_sk_...) unlocks fuller access per the server schema. The server fits research subphase because its primary motion is lookup and verification before validate and build, though you may revisit it when operating agents later. Pair AgentLore with your own validation steps; trust scores aid judgment but do not replace trying the tool yourself.
- Remote streamable-http MCP at https://agentlore.vercel.app/api/mcp/stream (v1.0.0)
- AI-verified knowledge base with trust scoring and temporal facts
- Skill cards surfacing packaged agent capabilities for comparison
- Optional Bearer aglo_sk_... token for full access; unauthenticated limited results
- Website and repo: agentlore.vercel.app / github.com/Kujirafu/agentlore
AgentLore by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add --transport http agentlore https://agentlore.vercel.app/api/mcp/stream --header "Authorization: Bearer YOUR_TOKEN"Add your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Transport | HTTP |
|---|---|
| Auth | Required |
| Repository | Kujirafu/agentlore ↗ |
What it does
Query AgentLore’s AI-verified knowledge base—with trust scores, temporal facts, and skill cards—while researching tools, patterns, and agent workflows.
Who is it for?
Best when you're evaluating agent skills, MCP servers, and automation patterns and want a structured, scored knowledge layer during research.
Skip if: Skip if you need private proprietary docs only, or developers past research and require live production telemetry instead of curated knowledge.
What you get
Your agent can pull trust-scored, time-aware knowledge and skill cards from AgentLore before you prototype or buy into a workflow.
- Trust-scored answers and temporal facts retrieved into agent sessions
- Skill card references to shortlist agent capabilities before build
By the numbers
- Server version 1.0.0; endpoint https://agentlore.vercel.app/api/mcp/stream
- Three advertised knowledge features: trust scoring, temporal facts, skill cards
- Auth optional: limited unauthenticated access; Bearer aglo_sk_... for full access
Recommended MCP Servers
0Latency MemoryPersistent memory layer for AI agents.
0nMCP — Universal AI API OrchestratorUniversal AI API Orchestrator — 1,554 tools, 96 services.
0xHumans Protocol MCPMCP for AI agents: financing, skills, lending on Base1k Patient Mcp1k patient MCP server
1trippulse1trip PULSE: 21-tool AI travel planner.
3D AI Agent Avatar3D AI Agent Avatar — render any GLB, give it a Solana wallet, a voice, and pump.fun powers.89How it compares
Verified agent knowledge MCP, not a single-task integration like analytics or email APIs.
FAQ
Who is AgentLore for?
Developers and agent users who want MCP-backed research with trust scoring, temporal facts, and skill cards when choosing tools and workflows.
When should I use AgentLore?
Use it in Idea and Validate-adjacent research when comparing skills, MCP servers, or agent patterns and you need fresher, scored facts than raw model memory.
How do I add AgentLore to my agent?
Register https://agentlore.vercel.app/api/mcp/stream as a streamable-http MCP server; add Authorization: Bearer aglo_sk_... for full access, or use limited unauthenticated mode.