MCP.Market

Cortex MCP server

by abbacusgroup·io.github.abbacusgroup/cortex·v0.2.2

Persistent knowledge system with OWL-RL reasoning and 22 MCP tools. Local-first.

C65/100grade C
What users say
No reviews yet
Be the first
Safety scan
C65/100

full report

Adoption
New

55 downloads/wk

Reviews

Write one

Nobody has reviewed Cortex yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Cortex tools (22, 3 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • cortex_capture

    Capture a knowledge object. When calling via MCP, YOU (Claude) are the classifier.

  • cortex_classify

    Classify or reclassify an existing knowledge object.

  • cortex_context

    Get a briefing (summaries only) for a topic. Token-efficient.

  • cortex_debug_memory

    Take tracemalloc memory snapshots for leak diagnosis.

  • cortex_debug_sessions

    Return MCP session table diagnostics (admin, localhost only).

  • cortex_deletewrite action

    Delete a knowledge object.

  • cortex_dossier

    Build an entity/topic-centric intelligence brief.

  • cortex_export

    Export a knowledge object.

  • cortex_feedback

    Provide explicit relevance feedback for an object.

  • cortex_graph

    Get the knowledge graph around an object or entity.

  • cortex_graph_data

    Return graph data in Cytoscape.js format for dashboard visualization.

  • cortex_linkwrite action

    Create a relationship between two knowledge objects.

  • cortex_list

    List knowledge objects with optional filters.

  • cortex_list_entities

    List entities in the knowledge graph, optionally filtered by type.

  • cortex_pipeline

    Re-run the intelligence pipeline on an existing object.

  • cortex_query_trail

    Return the most recent search query log entries.

  • cortex_read

    Read a knowledge object in full detail.

  • cortex_reasonwrite action

    Run advanced reasoning: contradictions, patterns, gaps, staleness.

  • cortex_safety_check

    Review a potentially destructive action before executing.

  • cortex_search

    Search knowledge objects with hybrid keyword + semantic + graph ranking.

  • cortex_status

    Get Cortex status, health metrics, and object counts.

  • cortex_synthesize

    Generate a synthesis of recent knowledge.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan48 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancerepository not readable: repo not found3/15
  • Maintainer identityno repository or website to verify2/10
Overall 65/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Cortex compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
65/100
higher than 20% of 48,255 servers
Tools
22
the typical server has 7
Tools that change things
14%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
55
more than 46% of 12,191 servers with a package

What its tools let an agent do: 19 read · 3 change

Install Cortex in Claude Code, Cursor or VS Code

claude mcp add cortex -- uvx abbacus-cortex
Add to Cursor

Cortex: common questions

Is Cortex MCP server safe?
With care: it is graded C, so read the findings first (65/100). Read the Cortex safety report
How do I install Cortex?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Cortex need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Cortex maintained?
The latest release is v0.2.2.
How does Cortex compare with other MCP servers?
safety score 65/100 (higher than 20% of 48,255 servers); tools 22 (the typical server has 7); tools that change things 14% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.