AgentLore

io.github.KujirafuPublished by GitHub account Kujirafuv1.0.0Updated Oct 24, 2026

AI-verified knowledge base with trust scoring, temporal facts, and skill cards.

VerifiedStreamable HTTPWeb executableKnowledge & Memory

Overview

AI-generated overview

AgentLore is a remote MCP knowledge base with trust scoring, temporal facts and skill cards that an assistant can query for verified knowledge.

What you can do
Query an AI-verified knowledge base for facts and skill cards, with trust scores attached to results. Work with temporal facts, so answers can reflect how information changes over time. Access is tiered: unauthenticated callers get limited results, while a bearer token unlocks full access. The manifest lists no individual tools, so the exact operations are not documented here.
When to use it
Useful when an assistant needs to look up curated, trust-scored knowledge rather than raw web results, or when answers depend on time-sensitive facts and reusable skill cards.
Requirements
A remote streamable HTTP endpoint; no local runtime or package is needed. Optionally an Authorization header carrying a bearer token in the form aglo_sk_... for full access; without it, results are limited. Network access to the hosted endpoint is required.
Before you install
The Authorization bearer token is a secret granting full access; keep it out of logs and shared transcripts. Queries and any token are sent to a third-party hosted service, so avoid submitting sensitive data. The manifest lists no write tools, but the available operations are not documented.

Installation

In SourceWeft

  1. Open AgentLore in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.Kujirafu%2Fagentlore/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "agentlore": {
      "type": "http",
      "url": "https://agentlore.vercel.app/api/mcp/stream"
    }
  }
}

README

This repository has no README.

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

60% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.