Atlas / MCP servers / oliverxuzy-ai / Knowledge Vault

Knowledge VaultSAFE

mcp/oliverxuzy-ai/knowledge-vault

An intelligent knowledge management system connecting your local knowledge vault with Claude Desktop via MCP

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
7 5r · 1w · 1d
Transport
stdio
License
MIT
Stars
23
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://pypi.org/project/obsidian-in-a-vat-mcp/) [](https://pypi.org/project/obsidian-in-a-vat-mcp/) [](LICENSE) [](https://github.com/oliverxuzy-ai/knowledge-in-a-vat/actions/workflows/test.yml) [](https://github.com/oliverxuzy-ai/knowledge-in-a-vat/pkgs/container/obsidian-in-a-vat)

A personal knowledge vault MCP server for Claude Desktop — capture thoughts, connect ideas, and reflect on how your thinking is changing, all through natural conversation.

📖 English · 📖 中文

Showcase

A vault is more than a folder of notes — it's a mirror of how you think. vault_reflect turns that mirror into something you can look at.

📺 Watch the full demo (60s)

https://github.com/user-attachments/assets/0ef205a4-0ffc-4a24-a92a-b4acf66377fe

Why this exists

Most note-taking tools stop at storage. vault-mcp is built around a three-layer vision:

  • L1 · Capture — frictionless save from any conversation, with auto-tagging and slug generation.
  • L2 · Connect — promote raw captures into structured notes with auto-wikilinks, build a knowledge
Read from source at commit 3d1890310f03OBSERVED · 2026-10-09
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add obsidian-in-a-vat-mcp -- uvx obsidian-in-a-vat-mcp
claude-desktop
{
  "mcpServers": {
    "obsidian-in-a-vat-mcp": {
      "command": "uvx",
      "args": [
        "obsidian-in-a-vat-mcp"
      ]
    }
  }
}
03

Exposed tools (7)

5 read · 1 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

ToolRiskDescription
vault_analyzereadAnalyze vault knowledge graph.
vault_capturedestructiveCapture a refined insight into the vault, or delete an existing capture.
vault_initreadInitialize a new vault or migrate existing Obsidian notes to vault-mcp format.
vault_promotereadPromote one or more captures into a structured note.
vault_readreadRead and search vault content.
vault_reflectreadReflect on your knowledge vault — what you
vault_topicwriteManage topic lifecycle: prepare materials, create, or update.
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (4)

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59
vault_capture
Why it matters. 1 tool(s) can delete or overwrite
Fix. prefer a read-only mode or scoped tokens; the page states the blast radius
INFOInventory / provenance · inv.oversize · CWE-1104
docs/assets/reflect-snapshot-zh.png
docs/assets/reflect-snapshot-zh.png
Why it matters. 1374317 bytes not read
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README.md:82
curl -LsSf https://astral.sh/uv/install.sh | sh
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README.md:291
curl -LsSf https://astral.sh/uv/install.sh | sh

Gates applied: no_behavioural_pass.

Audited 2026-10-09 · audit v0.4.1 · source sha 3d1890310f03full audit observations/trust-audit/mcp-server/oliverxuzy-ai__knowledge-vault.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-093d1890310f03SAFEB89first audit
06

Questions

What is the Knowledge Vault MCP server?

An intelligent knowledge management system connecting your local knowledge vault with Claude Desktop via MCP

What tools does Knowledge Vault expose?

7 in total: 5 read-only, 1 that write, and 1 that can delete or overwrite (vault_capture). Every one is listed on this page with its risk.

Is Knowledge Vault safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does Knowledge Vault need?

No credential environment variables were found in its source, so it appears to need none.

How does Knowledge Vault run?

It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as obsidian-in-a-vat-mcp.

How current is this page?

The grade is for one exact copy of the source (3d1890310f03), read on 2026-10-09. The repository is watched and re-audited when it changes.

Advertisement