AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Obsidian Mcp

skill-r007b34r-opencode-obsidian-knowledge-workflow-obsidian-mcp · by r007b34r

>

No reviews yet
0 installs
14 views
0.0% view→install

Install

$ agentstack add skill-r007b34r-opencode-obsidian-knowledge-workflow-obsidian-mcp

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-r007b34r-opencode-obsidian-knowledge-workflow-obsidian-mcp)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Obsidian Mcp? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

obsidian-mcp

Constraints

  • NO write without fresh read first
  • NO completion claims without readback verification
  • EVERY changed line must trace to user request
  • This skill owns vault operations ONLY; workflow decisions belong to companion skills

Host Constraints (version-locked — re-verify on upgrade)

These are based on obsidian-mcp-server@3.1.5. They may be stale.

To re-verify: call the forbidden API with a trivial test payload. If it returns -32602, constraint holds. If it succeeds, update this table and remove the ban.

| Operation | Status | Alternative | |-----------|--------|-------------| | obsidian_patch_note | Forbidden (last verified: 2026-05-10) | obsidian_replace_in_note | | obsidian_append_to_note | Forbidden (last verified: 2026-05-10) | obsidian_replace_in_note or obsidian_write_note overwrite:false for new files | | obsidian_write_note overwrite:true | Forbidden by default | Surgical replace for existing files | | obsidian_delete_note | Requires user confirmation | List path + risk first |

If you suspect a constraint is stale, test it. A successful call means the ban should be lifted.

Tool Selection

| Goal | Tool | |------|------| | Browse structure | obsidian_list_notes (depth 2-4) | | Search | obsidian_search_notes | | Read before edit | obsidian_get_note format:"document-map" then content/full | | Create note | obsidian_write_note overwrite:false → readback | | Edit existing | obsidian_replace_in_note → readback | | Frontmatter | obsidian_manage_frontmatter | | Tags | obsidian_manage_tags |

When selecting tools, read references/examples.md for operation patterns.

Workflow

  1. Locate: identify targets, read before writing
  2. Plan: minimum change only; report unrelated issues, don't fix them
  3. Write: use appropriate tool from table above
  4. Verify: readback every write; compare actual vs expected

When formatting completion reports, read references/templates.md.

Error Recovery

| Error | Response | |-------|----------| | -32602 schema error | Stop using that operation; switch to alternative | | note_missing | Search for candidates; ask user | | file_exists | Read existing; use surgical replace | | 3 repeated failures | Stop and report |

Trigger Boundary

Use when: any vault read/write/search/tag/edit/verify operation.

Do NOT use for: triage decisions, synthesis, relationship analysis, health diagnosis, promotion decisions — those belong to companion skills.

Boundaries

  • Owns: vault CRUD, frontmatter, tags, search, verification
  • Delegates to: all 6 workflow skills for decisions
  • Never absorbs: workflow decisions, knowledge interpretation

Continuations

| Condition | Next | |-----------|------| | Operation complete | Return to calling workflow skill | | Repeated MCP failures | vault-health-feedback | | 3 failures on same op | Escalate to human |

Gotchas

Gotcha 1: Using forbidden APIs "because they look right" Current host fails with -32602 regardless of intent. Use alternatives. But if you suspect the bug is fixed, test it first.

Gotcha 2: Trusting section reads as verification format:"section" has schema issues on long content. Verify with content/full.

Gotcha 3: Making workflow decisions This skill executes operations, not decides what to do. Defer to companion skills.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.