AgentLore
Query AgentLore’s AI-verified knowledge base—with trust scores, temporal facts, and skill cards—while researching tools, patterns, and agent workflows.
Overview
AgentLore is a MCP server for the Idea phase that connects your agent to an AI-verified knowledge base with trust scoring, temporal facts, and skill cards.
What is this MCP server?
- 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
- 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
What problem does it solve?
Early-stack research in chat mixes outdated facts and unverified claims about agents, skills, and MCP tools you cannot trust for a shipping decision.
Who is it for?
Solo builders evaluating agent skills, MCP servers, and automation patterns who want a structured, scored knowledge layer during research.
Skip if: Teams that need private proprietary docs only, or builders past research who require live production telemetry instead of curated knowledge.
What do I get? / Deliverables
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
Recommended MCP Servers
Journey fit
Idea is when you are still choosing what to build and need trustworthy, time-aware reference material instead of stale blog summaries. Research is the canonical shelf for verified knowledge retrieval, trust scoring, and skill-card discovery before you commit to a stack.
How it compares
Verified agent knowledge MCP, not a single-task integration like analytics or email APIs.
Common Questions / FAQ
Who is AgentLore for?
Indie 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.