MCP.Market

Pulse8 AI Cortex Knowledge Vault MCP server

by synpulse8-opensource·io.github.synpulse8-opensource/pulse8-ai-cortex-knowledge-vault·v1.6.0·15 stars
No reviews yet

Agent-native knowledge OS on Markdown: typed graph, hybrid search, and compiler over MCP.

B77/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B77/100

full report

Adoption
Growing

15 stars27 downloads/wk

Reviews

Write one

Nobody has reviewed Pulse8 AI Cortex Knowledge Vault yet.

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

Pulse8 AI Cortex Knowledge Vault tools (14, 3 write)

write = sends, deletes, buys or posts

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

  • vault_compile

    Compile unprocessed raw sources into wiki articles via LLM.

  • vault_context

    Build a context window: search, graph BFS expansion, ranked subgraph with contradictions.

  • vault_explain

    Explain a note: summary, provenance, raw sources, and connections grouped by direction (links in / out, contradictions).

  • vault_feedbackwrite action

    Submit user feedback. Saved under feedback/ with tags and links to related notes. Optional outcome label (useful / dead-end / corrected) records whether the retrieved knowledge held up.

  • vault_impact

    Walk everything downstream of a note: all notes linking to it directly or transitively. Use for change-impact analysis.

  • vault_ingest

    Ingest a raw source. Accepts text via content or binary via content_base64.

  • vault_linkwrite action

    Create, query, or delete typed edges in the knowledge graph.

  • vault_list_feedbacks

    List feedback notes in the vault (metadata only: path, preview, tags, related_paths).

  • vault_path

    Find shortest paths between two notes over the typed graph. Every hop carries its edge type and lineage origin.

  • vault_read

    Read a note by path. Returns frontmatter, content, and graph edges.

  • vault_resource_read

    Read a server-stored resource by ID (fallback for MCP clients that do not expose the resources protocol natively). Accepts either the bare hex ID or the full ``cortex://resource/{id}`` URI.

  • vault_search

    Search the vault via QMD (keyword, semantic, or hybrid). Enriched with graph edges.

  • vault_trace

    Trace a note's lineage: provenance, raw sources, and every edge touching it labeled extracted / inferred / manual.

  • vault_writewrite action

    Create or update a note with provenance tracking. Updates graph and index.

Public scan report

scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it

no findings
  • Code scan72 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 qualitystatic API keys via environment variables6/15
  • Maintenancelast push 59 days ago12/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 77/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Pulse8 AI Cortex Knowledge Vault compares

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

Safety score
77/100
higher than 50% of 4,460 AI and agents servers
Tools
14
the typical AI and agents server has 6
Tools that change things
21%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
15
more than 87% of 2,711 AI and agents servers
Downloads a week
27
more than 13% of 1,538 AI and agents servers with a package

What its tools let an agent do: 11 read · 3 change

Install Pulse8 AI Cortex Knowledge Vault in Claude Code, Cursor or VS Code

claude mcp add pulse8-ai-cortex-knowledge-vault -- uvx pulse8-ai-cortex-knowledge-vault
Add to Cursor

What the publisher says

From the Pulse8 AI Cortex Knowledge Vault repository's README, as published. We do not edit it. Read it on GitHub

<!-- mcp-name: io.github.synpulse8-opensource/pulse8-ai-cortex-knowledge-vault -->

PULSE8.ai Cortex

The open-source knowledge layer for AI agents Knowledge that compounds.

PULSE8.ai Cortex is the open-source knowledge layer for AI agents: Git-native memory, a typed knowledge graph, and MCP-powered retrieval on top of plain Markdown — so agents can build, evolve, and reuse persistent knowledge instead of re-deriving it on every query.

Under the hood it's a unified vault for AI agents and humans, backed by a typed knowledge graph, full-text + hybrid search, and a MarkItDown-powered file compiler. Drop files in (PDF, DOCX, PPTX, XLSX, HTML, images, and more), let agents read, write, search, link, and compile knowledge — no database required.

Inspired by Andrej Karpathy's LLM Wiki pattern — a persistent, compounding knowledge base maintained by LLMs instead of re-derived on every query. Search powered by Tobi Lütke's QMD.

Why PULSE8.ai Cortex?

Most AI agents can access tools, but they cannot accumulate knowledge.

Traditional RAG systems retrieve documents. PULSE8.ai Cortex builds a persistent, evolving knowledge layer that grows over time and becomes more valuable the more agents and humans interact with it.

With PULSE8.ai Cortex, agents can:

  • Learn from interactions — every read, write, ingest, and compile event is logged and graph-linked
  • Build and traverse knowledge graphs — wikilinks, tags, and typed edges, maintained automatically
  • Store structured insights — Markdown notes with typed nodes (note, agent_def, session, daily, feedback)
  • Retrieve context across projects — vault_context builds a ranked subgraph from any seed query
  • Share knowledge through MCP — one vault, every MCP-compatible client
  • Maintain long-term memory — files survive sessions, deployments, and model upgrades
  • Version knowledge through Git — the vault is a plain directory of Markdown, diff-friendly out of the box

When to use PULSE8.ai Cortex

Ideal use cases

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Pulse8 AI Cortex Knowledge Vault: common questions

Is Pulse8 AI Cortex Knowledge Vault MCP server safe?
Mostly: it is graded B (77/100). Read the Pulse8 AI Cortex Knowledge Vault safety report
How do I install Pulse8 AI Cortex Knowledge Vault?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Pulse8 AI Cortex Knowledge Vault need an API key?
Yes. The registry entry asks for CORTEX_LLM_API_KEY.
Is Pulse8 AI Cortex Knowledge Vault maintained?
The last commit was 100 days ago (2026-07-27). The latest release is v1.6.0.
What can I use instead of Pulse8 AI Cortex Knowledge Vault?
Servers from other publishers that do the same job: Basic Memory MCP server, IWE (iwe.md) MCP server and PDF MCP server. Compare all Pulse8 AI Cortex Knowledge Vault alternatives.
How does Pulse8 AI Cortex Knowledge Vault compare with other AI and agents MCP servers?
safety score 77/100 (higher than 50% of 4,460 AI and agents servers); tools 14 (the typical AI and agents server has 6); tools that change things 21% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Pulse8 AI Cortex Knowledge Vault

Same job from other publishers: the closest match first, then the best rated.

All Pulse8 AI Cortex Knowledge Vault alternatives →
  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • IWE (iwe.md)
    Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
    A
  • PDF
    Agentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR.
    A
  • Total Agent Memory
    Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall
    A
  • agent-device
    Open source device layer for AI agents: control mobile, web, TV, and desktop apps over MCP
    A