Cortex MCP server
Commit Sep 28, 2026Provides a semantic memory infrastructure for AI agents to save decisions, context, and sources with quality-gated writes and conflict tracking.
Also known as FilippoPilo/cortex-connector, cortex-connector
- Stars
- 2
- Tools
- โ
- Downloads, 30 days
- โ
- Latest version
- 1.1.0
- Last commit
- Sep 28, 2026
- License
- MIT
What is Cortex MCP?
Cortex provides a semantic memory infrastructure for AI agents to save decisions, context, and sources with quality-gated writes and conflict tracking.
Summary generated from the project's README
About Cortex MCP server
Cortex provides a semantic memory infrastructure designed to give AI agents a persistent external brain. It allows users to save decisions, context, and sources that remain accessible across different sessions. Unlike standard memory plugins that simply store text, this system uses a knowledge graph and a coherence metric to ensure information is reliable. It features a quality gate that checks for redundancy before writing and tracks contradictions between different claims.
Developers can connect Cortex to Claude via a remote MCP connector using a specific URL or through Claude Code. For clients that do not support remote connections natively, a stdio bridge using mcp-remote can be utilized. The service runs on distributed edge infrastructure located in the European Union. Users can manage their data through seven specific tools, including searching memories, fetching details with sources, and synthesizing information. The system also includes a background consolidation process called REM to turn episodic memories into long-term knowledge.
What you can do with it
- 1Maintain long-term project contextAsk the AI to remember specific project decisions or supplier choices for future reference.
- 2Verify information reliabilityRequest the specific sources used to support a particular claim made by the agent.
Written from the project's README. Every use case is checked against a quote from it.
How to install Cortex MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Cortex MCP in Claude Code
$ claude mcp add --transport http cortex-connector https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcpInstall Cortex MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"cortex-connector": {
"url": "https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcp"
}
}
}Install Cortex MCP in VS Code
.vscode/mcp.json
{
"servers": {
"cortex-connector": {
"type": "http",
"url": "https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcp"
}
}
}Install Cortex MCP in VS Code CLI
$ code --add-mcp '{"name":"cortex-connector","type":"http","url":"https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcp"}'Install Cortex MCP in Codex
$ codex mcp add cortex-connector --url https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcpInstall Cortex MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.cortex-connector] url = "https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcp"
Install Cortex MCP in Gemini CLI
$ gemini mcp add -s user --transport http cortex-connector https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcpInstall Cortex MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"cortex-connector": {
"url": "https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcp",
"type": "http"
}
}
}Configuration
CORTEX_ACCESS_TOKEN
Automated checks
Ran Nov 14, 2026Full report โNot verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work ยท What to fix for more points
- Source repository linked and reachablefilippopilo/cortex-connector is public and reachablegithub.com/filippopilo/cortex-connector โPass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html โPass
- Commit or release in the last yearLast commit or release 2026-09-28github.com/filippopilo/cortex-connector โPass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 88 msPass
README
View on GitHubCortex โ Semantic Memory for AI Agents
One external brain, model-agnostic, in production. Connect it to Claude in two minutes โ free trial, no credit card.
Cortex is a patent-pending semantic memory infrastructure developed by SKYNETLAB (Bergamo, Italy). Connected to your AI assistant as a remote MCP connector, it lets your conversations save decisions, context and sources โ and find them again in every later session. Your AI remembers, and can show why it remembers.
๐ Website: skynetlab-cortex.com ยท ๐ Patent ยท ๐ Benchmark ยท ๐ Paper ยท ๐ถ Pricing
๐ฎ๐น Versione italiana: README.it.md

Why Cortex is not "just another memory plugin"
Most memory tools for AI agents record what the agent did and retrieve similar text later. Cortex models what is true and how reliable it is:
| Capability | What it means |
|---|---|
| Quality Gate on write | Every memory passes a novelty/redundancy check before being stored. No junk accumulation. |
| Typed claims & conflict tracking | Facts are extracted as claims; contradictions between memories are detected and tracked, not silently overwritten. |
| Knowledge graph | Memories are linked by entities and typed relations, not just vector similarity. |
| Coherence metric (ฮจ_C) | Each memory carries a native coherence score โ the system knows how well a memory fits what it already knows. |
| Memory consolidation ("REM") | A continuous background cycle consolidates episodic memories into long-term knowledge. |
| Transparent evidence | Answers can cite the memories and sources they come from. |
Cortex runs on globally distributed edge infrastructure operated in the European Union. The memory engine is covered by Italian patent application UIBM 102026000014026 (filed 15 May 2026).
Quick start โ Claude (web / desktop / mobile)
Requirements: a Claude plan that supports custom connectors (the "Connectors" entry appears in Settings). No Cortex account needed beforehand โ it is created on first sign-in.
-
In Claude open Settings โ Connectors โ Add custom connector
-
Paste this URL and confirm:
https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcp -
Authorize access on the Cortex consent page (Google or email sign-in). Your personal memory space is created automatically, isolated from every other user.
That's it. Talk to Claude as usual: "Remember that we chose supplier X", "what did we decide about the budget?", "show me the sources for this claim". Claude picks the right tool on its own.
Quick start โ Claude Code
claude mcp add --transport http cortex https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcp
Then authenticate when prompted (/mcp shows connection status).
Quick start โ other MCP clients (stdio bridge)
For MCP clients that don't support remote connectors natively, use the mcp-remote bridge. Example configuration (see examples/):
{
"mcpServers": {
"cortex": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcp"]
}
}
}
Quick start โ this repository as a local stdio server
This repository also ships a small stdio MCP server (server/) that exposes the Cortex tools locally and forwards every call to the hosted service. It is meant for MCP clients, registries and evaluators that need a local process: it starts, lists its seven tools and answers introspection with no configuration at all; tool calls are forwarded when an access token is set.
git clone https://github.com/FilippoPilo/cortex-connector.git
cd cortex-connector
npm install
CORTEX_ACCESS_TOKEN=<your token> node server/index.js
Or with Docker:
docker build -t cortex-connector .
docker run -i --rm -e CORTEX_ACCESS_TOKEN=<your token> cortex-connector
| Variable | Meaning |
|---|---|
CORTEX_ACCESS_TOKEN |
Bearer token for the hosted connector (the OAuth access token issued at sign-in, for example the one mcp-remote stores). Optional: without it the server only lists tools. |
CORTEX_MCP_URL |
Remote endpoint, defaults to the hosted Cortex connector. |
npm test runs a self test (initialize, tools/list, one call without token).
The seven tools
| Tool | Type | Description |
|---|---|---|
| Search memories | read | Semantic search across your memories |
| Fetch memory | read | Full detail of one memory, with its sources |
| Recall & synthesize | read | Narrative synthesis of what Cortex knows about a topic |
| Show conflicts | read | Tracked contradictions between memories |
| Save memory | write | Stores a memory โ after a quality check against duplicates and redundancy |
| Write status | read | Outcome of a queued save: quality-gate verdict and any open conflicts |
| Forget memory | destructive | Deletes a memory โ always with explicit confirmation |
Data & privacy
Memories are personal: each user only sees their own. They are exportable and deletable on request, and the infrastructure operates in the European Union. Details: Privacy Policy.
To disconnect, simply remove the connector from your client's settings; your memories remain in your Cortex account until you request their deletion.
Is this open source?
The Cortex memory engine is a hosted, patent-pending service โ its source code is not published. This repository contains the public documentation, the client-side configuration examples and a small stdio bridge (server/) for connecting to it. Everything in this repository is released under the MIT License.
Support
๐ง info@skynetlab.net ยท Contact page
Cortex is a SKYNETLAB product โ independent research lab & deeptech studio, Bergamo, Italy. Founder: Filippo Pilotta (ORCID 0009-0000-5002-4199).
Some content and product outputs are generated or assisted by artificial intelligence, pursuant to Art. 50 of Reg. (EU) 2024/1689. AI transparency.
Cortex MCP questions
How do I add Cortex MCP to Claude Code?
Run claude mcp add --transport http cortex-connector https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Cortex MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How does Cortex ensure memory quality?
Cortex uses a quality gate on writes where every memory undergoes a novelty and redundancy check before being stored to prevent junk accumulation.
Can Cortex detect contradictions in information?
Yes, the system uses typed claims and conflict tracking to detect and track contradictions between memories instead of silently overwriting them.
Where is the data stored and how is privacy handled?
The infrastructure operates in the European Union and memories are personal, meaning each user only sees their own data.