Skills/npm/obsidian-mcp-server

obsidian-mcp-server@3.9.0

VERIFIED· startup only

Publisher claims: "Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher cyanheads · publishing for 659 daysInstalls 26,530Last detonated 38 h ago
$claude mcp add obsidian-mcp-server -- npx -y obsidian-mcp-server
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials
Needs
OBSIDIAN_API_KEY — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
no credential variables read in the code; at startup it asked for OBSIDIAN_API_KEY
Where it talks to
no vendor host named in the code
What the honeypot saw
no credential files read · no network
What we could not test
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it under the guard. Startup only; authenticated tool behavior not tested. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- npx -y obsidian-mcp-server

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-12 and scored it 83/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed (it asks for OBSIDIAN_API_KEY); the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 60 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
19sprocessdependency install exit 0
39sprocessrelaunched with a decoy OBSIDIAN_API_KEY (tagged; nothing real)
59sclaimedstartup only: exited before answering, asking for OBSIDIAN_API_KEY (a decoy value was refused)
59sprocessscript backend runs setup only
59sprocessno install scripts to re-run

Static findings

HIGH
Destructive file system command detecteddist/mcp-server/tools/definitions/index.d.ts:872 · Destructive file system command detectedreadonly recovery: "Read the block with obsidian_get_note (format \"content\"), repair the YAML between the `---` fences, then retry the delete.";Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagepackage.json:38 · npx invocation of non-well-known package — may execute untrusted code"bundle": "bun run build && npx -y @anthropic-ai/mcpb pack . dist/obsidian-mcp-server.mcpb && bun run scripts/clean-mcpb.ts dist/obsidian-mcp-server.mcpb",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Refusal suppressionAGENTS.md:195 · Refusal suppression — attempting to prevent safety responses… no round can run), nothing needs a session and stateless HTTP starts. stdio is never refused — `MCP_SESSION_MODE` has no effect there. `tests/integration/delete-note-confi…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Destructive file system command detecteddist/mcp-server/tools/definitions/obsidian-manage-frontmatter.tool.d.ts:70 · Destructive file system command detectedreadonly recovery: "Read the block with obsidian_get_note (format \"content\"), repair the YAML between the `---` fences, then retry the delete.";Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST05
MEDIUM
npx invocation of non-well-known packageAGENTS.md:496 · npx invocation of non-well-known package — may execute untrusted code…uded. `mcp.json` holds one `"type": "stdio"` entry keyed by the unscoped name, `npx -y obsidian-mcp-server`, and the same fixed `env` as `.codex-plugin/mcp.json`. Nei…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Destructive file system command detecteddist/mcp-server/tools/definitions/obsidian-get-note.tool.d.ts:136 · Destructive file system command detectedreadonly recovery: "Call obsidian_get_note with format \"document-map\" to list available headings, blocks, and frontmatter fields, then retry with one of those locators.";Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandDockerfile:149 · File permission modification command — agent changes file ownership/permissionsRUN mkdir -p /var/log/obsidian-mcp-server && chown -R bun:bun /var/log/obsidian-mcp-serverFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Destructive file system command detecteddist/mcp-server/tools/definitions/index.d.ts:160 · Destructive file system command detectedreadonly recovery: "Call obsidian_get_note with format \"document-map\" to list available headings, blocks, and frontmatter fields, then retry with one of those locators.";Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Refusal suppressionCLAUDE.md:195 · Refusal suppression — attempting to prevent safety responses… no round can run), nothing needs a session and stateless HTTP starts. stdio is never refused — `MCP_SESSION_MODE` has no effect there. `tests/integration/delete-note-confi…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageCLAUDE.md:496 · npx invocation of non-well-known package — may execute untrusted code…uded. `mcp.json` holds one `"type": "stdio"` entry keyed by the unscoped name, `npx -y obsidian-mcp-server`, and the same fixed `env` as `.codex-plugin/mcp.json`. Nei…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commanddist/config/server-config.js:128 · Process kill command — agent can terminate processes.describe('Global kill switch. When true, denies every write regardless of OBSIDIAN_WRITE_PATHS, and suppresses the OBSIDIAN_ENABLE_COMMANDS pair (commands can mutate). Defaults to false.'),Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈24,079 tok
3 files · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for obsidian-mcp-server@3.9.0 as of 38 h ago. This is the package itself, not its dependencies.