MCP servers · alekseimarchenko

Central Intelligence: persistent memory MCP server for AI agents

An MCP server that gives AI agents persistent memory, so they can store, search and share knowledge across sessions.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

The server lets an agent store information with remember, retrieve it by semantic search with recall, load task-relevant memories with context, delete outdated ones with forget, and make them available to other agents with share. Facts are extracted for search, but the stored content is returned verbatim. Each memory has a scope of agent, user or org, which controls which agents can see it.

It suits agents that keep relearning preferences, architecture or past fixes each session, teams where several agents work on one project, and handoffs between agents or sessions. CI Local reads CLAUDE.md, Cursor and Windsurf rules, Codex and GitHub Copilot instruction files, and makes them searchable alongside stored memories. The publisher reports 52.2% on LifeBench and 75.0% on LongMemEval.

Setup means adding the server to the MCP configuration of Claude Code or Cursor, or pointing any MCP client to the central-intelligence-mcp npm package with a CI_API_KEY environment variable. A REST API is also offered, and every request must carry a bearer token. A local, cloud-free option is mentioned.

Limitations and requirements

Hosted use requires a CI_API_KEY, and every REST API request needs a bearer token. Do not store secrets, passwords, API keys, PII, large binary files or ephemeral scratch data. The benchmark figures are published by the author, who also maintains the Agent Memory Benchmark used for comparisons. Advanced retrieval features are described as a roadmap item for Enterprise, with commercial availability tied to pricing.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    io.github.AlekseiMarchenko/central-intelligence

    Persistent memory for AI agents. Store, recall, and share knowledge across sessions.

    v0.1.3
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
cloudflare

Cloudflare MCP servers

Cloudflare's hosted MCP servers for its products: documentation search, sandbox containers, browser rendering, Radar internet data, logs and analytics, Workers and more.

4.5K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
microsoft

Playwright MCP (browser automation)

Microsoft's MCP server that lets an AI assistant open web pages, click, type and read them through a real browser, using the page structure instead of screenshots.

39.6K GitHub starsTesting & QAWeb, search & browser
Updated 17 Nov 2026
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026