Agentcairn vs Cortex Plugin — MCP Server Comparison | AllMCPs
Side-by-Side Model Context Protocol Comparison
Agentcairn vs Cortex Plugin
In-depth architectural comparison of the Agentcairn and Cortex Plugin MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Agentcairn
Knowledge & Memory · Local stdio
Quality: 47/100 (Fair) | Auth: No auth required
Cortex Plugin
Knowledge & Memory · Local stdio
Quality: 55/100 (Good) | Auth: No auth required
Verdict Summary: Choose Agentcairn if you need specialized Knowledge & Memory tools running via a local process. Choose Cortex Plugin if your workspace requires Knowledge & Memory integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Agentcairn when:
You need dedicated capabilities in the Knowledge & Memory domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Primary tools included: Plain Markdown Obsidian vault as canonical memory store, Rebuildable DuckDB index for hybrid BM25, vector, and graph recall, Non-lossy memory capture with supersession and secret redaction.
You need dedicated capabilities in the Knowledge & Memory domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
You have access to required keys: MEMEM_TELEMETRY_SOURCE.
Primary tools included: Event-triggered background miner extracting durable lessons from conversations, Stores memories as markdown files in a local Obsidian vault, Active Memory Slice assembling query-tailored context briefings.
Local-first agent memory: a plain-Markdown Obsidian vault is the source of truth, with a rebuildable DuckDB index for hybrid BM25 + vector + graph recall. Non-lossy capture with secret redaction; works across Claude Code, Codex, Cursor, and any MCP host. uvx agentcairn
Persistent, self-evolving memory plugin for Claude Code. Background miner extracts durable lessons (decisions, conventions, bug fixes) from completed sessions via Claude Haiku, stores them as human-readable markdown in an Obsidian vault, and assembles query-tailored context briefings at session start. Local-first, no cloud, no API keys. Self-healing install via uv bootstrap shim, /cortex-doctor preflight, graceful FTS-only degraded mode when claude CLI missing. MIT.
Category & Scope
Tools & Capabilities Breakdown
Agentcairn Tools (6)
Plain Markdown Obsidian vault as canonical memory store
Rebuildable DuckDB index for hybrid BM25, vector, and graph recall
Non-lossy memory capture with supersession and secret redaction
Cross-agent shared vault for consistent context
Memory provenance, currency, and importance metadata
Integration with Claude Code, Codex, Cursor, and MCP hosts
Cortex Plugin Tools (6)
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Agentcairn is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, Cortex Plugin belongs to Knowledge & Memory using local stdio subprocess. Select Agentcairn when you need capabilities focused on knowledge & memory and Cortex Plugin when you require tools for knowledge & memory.