CogniCore — Claude Code MCP server: features and install
CogniCore gives agents persistent memory across sessions, reflects on failed attempts, and screens unsafe prompts. It works through an MCP connection.
claude mcp add --transport http cognicore-env https://mcp.cognicoree.tech/mcp/streamWhat CogniCore does
CogniCore lets an agent retain experience instead of starting each run from scratch. It stores past attempts, recalls related context, and surfaces lessons from repeated failures. Its safety layer can stop prompt injection and jailbreak attempts before they reach the agent.
The hosted MCP server connects to Claude Code, Codex, Cursor, and other compatible clients at https://mcp.cognicoree.tech/mcp/stream. A local Python setup needs Python 3.10+ and runs without a vector database or mandatory dependencies. Memory, reflection, and safety do not require an API key.
CogniCore also records decisions for replay and branching, and can export verified memory as a signed bundle. The hosted service uses GitHub sign-in; the local package runs in the Python process.
What it helps with
- retain agent experience across sessions
- bring earlier attempts into a new run
- turn repeated failures into lessons
- stop prompt injection and jailbreak attempts
- replay a decision and branch from it
Example prompts for the agent
- Save what we learned from this debugging session for the next run.
- Review earlier failed approaches to this bug before suggesting a fix.
- Record this decision so I can replay it and branch from a later step.
How to install CogniCore
Platform CLI: remote server
claude mcp add --transport http cognicore-env https://mcp.cognicoree.tech/mcp/streamPlatform CLI: remote server
codex mcp add cognicore --url https://mcp.cognicoree.tech/mcp/streamConfig file
{
"mcpServers": {
"cognicore": {
"url": "https://mcp.cognicoree.tech/mcp/stream"
}
}
}Config file
{
"servers": {
"cognicore": {
"type": "http",
"url": "https://mcp.cognicoree.tech/mcp/stream"
}
}
}Platform CLI: remote server
gemini mcp add -t http cognicore https://mcp.cognicoree.tech/mcp/streamStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about CogniCore
How do I install CogniCore in Claude Code?
Run claude mcp add --transport http cognicore-env https://mcp.cognicoree.tech/mcp/stream. CogniCore will then be available as an MCP server in Claude Code.
What does CogniCore do?
It keeps agent experience across sessions, recalls relevant past context, and extracts lessons from failures. The server also filters prompt injection and jailbreak attempts and supports replay with branching.
Does CogniCore need an API key?
Memory, reflection, and safety work without an API key. The hosted service uses GitHub sign-in, while the local package requires Python 3.10+.
