session-knowledge — security grade SAFE, quality 73/100

Security audit verdict: SAFE · quality 73/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by nameforjt-afk · MCP Server · ★ 335

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is session-knowledge safe to install? View the security audit →

About session-knowledge

session-knowledge Claude Code's memory is scoped per project directory. Your history isn't. Every session you've ever run is already on disk in — every decision, every command that worked, every credential you pasted. But open a session in a different directory and none of it is reachable. You re-ask questions you already answered, and re-implement integrations you already wrote. This indexes all of it and hands Claude 13 MCP tools to search it. You just ask normally. What was the retry logic in that deploy script? Which DATABASEURL did I actually use for staging? Before I write the Stripe integration — has anyone here already done payment auth? Pure Python standard library. No third-party dependencies, no embeddings, no API calls, nothing leaves your machine. Restart Claude Code. Done. ⚠️ Read this before installing The index lives in and it contains plaintext credentials scraped from your sessions. That is the precondition for "which key did I

ai-agentsanthropicclaude-codedeveloper-toolsfull-text-searchknowledge-basellmlocal-firstmcpmcp-server

Quick Facts

Stars335
Forks12
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score72.8884376404412/100
Last Updated2026-09-30
Created2026-08-20
Platformsclaude-code, mcp, python
Est. Tokens~11k

session-knowledge alternative? Top 6 similar tools

Looking for a session-knowledge alternative? If you're comparing session-knowledge with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • docsagent by docsagent · ⭐ 623

    ⚡ DocsAgent — give your AI agents instant, private access to your personal knowledge base (Zotero, Obsidian, A

  • claude-emporium by Vvkmnn · ⭐ 82

    🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace

  • spool by paperboytm · ⭐ 591

    Your local AI session library. Browse, pin, and ⌘K-search every Claude Code, Codex, Gemini & OpenCode session

  • spool by spool-lab · ⭐ 532

    Your local AI session library. Collects sessions from Claude Code, Codex CLI, Gemini CLI (and more) — browsabl

  • roam-code by Cranot · ⭐ 517

    Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 comman

  • mcpproxy-go by smart-mcp-proxy · ⭐ 382

    Supercharge AI Agents, Safely

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is session-knowledge?

session-knowledge is Turn your Claude Code session history into a searchable local knowledge base — 13 MCP tools, pure stdlib, nothing leaves your machine. It is categorized as a MCP Server with 335 GitHub stars.

What programming language is session-knowledge written in?

session-knowledge is primarily written in Python. It covers topics such as ai-agents, anthropic, claude-code.

How do I install or use session-knowledge?

You can find installation instructions and usage details in the session-knowledge GitHub repository at github.com/nameforjt-afk/session-knowledge. The project has 335 stars and 12 forks, indicating an active community.

What license does session-knowledge use?

session-knowledge is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to session-knowledge?

The top alternatives to session-knowledge on Agent Skills Hub include docsagent, claude-emporium, spool. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools