MCP Obsidian vs Pageindex MCP
A side-by-side look at the MCP Obsidian and Pageindex MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose MCP Obsidian for knowledge & memory work as a local process; choose Pageindex MCP for knowledge & memory as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose MCP Obsidian when
- You need dedicated capabilities in the Knowledge & Memory domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
read_note, write_note, patch_note.
Choose Pageindex MCP when
- You need dedicated capabilities in the Knowledge & Memory domain.
- You prefer a local stdio subprocess transport.
- You want tools like
process_document, browse_documents, search_documents.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Knowledge & Memory | Knowledge & Memory |
| Quality signal | 73/100 · Great | 65/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | Not declared |
| Pricing | Free | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 1,697 | 402 |
| Directory activity | 9 views 0 installs 0 upvotes | 3 views 0 installs 0 upvotes |
| Tools | 18 | 9 |
| Full listing | View MCP Obsidian | View Pageindex MCP |
Tools & capabilities
MCP Obsidian tools 18
read_noteRead a note from the Obsidian vaultwrite_noteWrite a note to the Obsidian vaultpatch_noteEfficiently update part of a note by replacing a specific string. This is more efficient than rewriting the entire note for small changes.list_directoryList files and directories in the vault (includes non-note filenames, while read/write tools remain note-only)delete_noteDelete a note from the Obsidian vault (requires confirmation). Supports permanent delete, vault trash, or system trash.search_notesSearch for notes in the vault by content or frontmattermove_noteMove or rename a note in the vaultmove_fileMove or rename any file in the vault (binary-safe, file-only, requires confirmation)read_multiple_notesRead multiple notes in a batch (max 10 files)update_frontmatterUpdate frontmatter of a note without changing contentget_notes_infoGet metadata for notes without reading full contentget_frontmatterExtract frontmatter from a note without reading the content- +6 more on the listing page
Pageindex MCP tools 9
process_documentUpload and process PDF documents from URLs or local files. Supports OCR processing, hierarchical content extraction, and intelligent document analysis. Returns a unique doc_id for subsequent operations. Processing typically takes 0-3 minutes depending on document size (estimate: 2 seconds per page). Supports files up to 100MB.browse_documentsPrimary document retrieval tool. After orienting with get_folder_structure() (when available), use this for all document-related questions. The bare call returns root-level sub-folders and documents; pass folder_id to drill into a sub-folder level by level. Use sort="relevance" + query for semantic ranking. Do NOT jump to search_documents() first — it is an escalation path, only after browse_documents(sort="relevance") has failed.search_documentsESCALATION tool — never the first step. Use only after `browse_documents(sort="relevance", query=...)` missed a document you strongly believe exists by precise term, acronym, or file-name fragment. Query must be keywords only — see the `query` schema describe. Each result has a `score` (6-10, higher is more relevant). On result: single best match → read it; several equally good → ask user; none → fall back to `browse_documents(sort="relevance")`.get_folder_structureOrientation step: show the folder hierarchy as a tree (like `tree -d`). **Call this before browse_documents()** to plan targeted retrieval — folder names reveal content domains (e.g. "Research", "Finance") and return folder IDs you pass to browse_documents(folder_id=…). Wait for this result before issuing browse_documents() or search_documents(). For folder_id="root" (default), returns the entire folder tree; for a specific folder_id, returns that subtree only.get_documentCheck a document's processing status and metadata. `status` is one of "pending", "queued", "processing", "completed", or "failed" — call this before `get_document_structure()` or `get_page_content()` to confirm the document is ready.get_document_structureExtract a document's hierarchical outline (headers, sections, page references). REQUIRED for documents over 20 pages — call this first to locate relevant sections, then pass their page numbers to `get_page_content()`. Use the `part` parameter to iterate large outlines until `pagination.has_more` is false.get_page_contentExtract page content from a processed document. Use tight, targeted page ranges — never the whole document at once. For documents over 20 pages, call `get_document_structure()` first to pick relevant sections. Embedded image paths in the response feed into `get_document_image()`.get_document_imageRetrieve an image from a document — pass an `image_path` from a `get_page_content()` response: either an embedded image (from a content block) or a full rendered page (from the `page_images` array, useful when a page is scanned or its meaning depends on visual layout). Returns the image as an MCP image content block (base64 data + MIME type). Do NOT repeat the raw base64 value in your text response.remove_documentPermanently delete documents and all associated data. Only invoke when the user explicitly names the documents AND confirms deletion. Returns `results` — one entry per requested document: `{ doc_name, status: "deleted" | "not_found" | "failed", error? }`. Inspect each entry for per-document failures. This action is irreversible.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
MCP Obsidian
{
"mcpServers": {
"bitbonsai-mcp-obsidian": {
"command": "npx",
"args": [
"-y",
"@bitbonsai/mcpvault@latest"
]
}
}
}
Pageindex MCP
{
"mcpServers": {
"pageindex-mcp": {
"command": "npx",
"args": [
"-y",
"@pageindex/mcp"
]
}
}
}
Frequently asked questions
MCP Obsidian is categorized under Knowledge & Memory and uses a local stdio subprocess. Pageindex MCP belongs to Knowledge & Memory and uses a local stdio subprocess. Pick MCP Obsidian for knowledge & memory work and Pageindex MCP for knowledge & memory.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
MCP Obsidian is listed as free. Auth: no auth required. Pageindex MCP has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add bitbonsai-mcp-obsidian and pageindex-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, MCP Obsidian has a quality signal of 73/100 (Great) with 9 views, 0 installs and 1,697 GitHub stars. Pageindex MCP has 65/100 (Great) with 3 views, 0 installs and 402 GitHub stars.