Obsidian MCP Pro vs Screenpipe
A side-by-side look at the Obsidian MCP Pro and Screenpipe MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Obsidian MCP Pro for knowledge & memory work as a local process; choose Screenpipe 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 Obsidian MCP Pro 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 have the keys it needs:
OBSIDIAN_VAULT_PATH, OBSIDIAN_READ_PATHS, OBSIDIAN_WRITE_PATHS. - You want tools like
search_notes, get_note, list_notes.
Choose Screenpipe 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
search-content, synced-devices, search-synced-content.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Knowledge & Memory | Knowledge & Memory |
| Quality signal | 67/100 · Great | 73/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | No auth required |
| Pricing | Free | Freemium |
| Required env vars | OBSIDIAN_VAULT_PATHOBSIDIAN_READ_PATHSOBSIDIAN_WRITE_PATHS | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 33 | 22,087 |
| Directory activity | 1 views 0 installs 0 upvotes | 8 views 0 installs 0 upvotes |
| Tools | 41 | 30 |
| Full listing | View Obsidian MCP Pro | View Screenpipe |
Tools & capabilities
Obsidian MCP Pro tools 41
search_notesFull-text search across all notes in the vault. Ranks literal matches with title/path focus and repeated-line dampening, then returns matching note paths grouped with the line numbers and query-centered snippet content of each matching line. Use to locate notes containing a phrase, keyword, or code fragment; pair with get_note to retrieve full bodies.get_noteRead a note in full or as a fragment. With no fragment options, returns parsed frontmatter (as a labeled header), a flat list of inline #tags, and the body. With `section`, returns just the body under that heading (path-form like 'Tasks/Today' is supported). With `block`, returns the paragraph or block tagged `^id`. With `lines`, returns the inclusive 1-indexed line range. Fragment modes skip the frontmatter/tag header and return raw text — use them to keep token usage tight on long notes.list_notesEnumerate every markdown note in the vault (or a single folder), returning a sorted list of relative paths along with the total count. Truncates output to `limit` entries but still reports the total. Use to browse vault structure, build a file picker, or enumerate targets for batch processing.get_daily_noteRead the daily note for today or for a specific date, resolved via the vault's configured daily-note folder and filename format. Returns the note path, parsed frontmatter (as a labeled header block), and body. Errors if no daily note exists for that date — use create_daily_note to create one.search_by_frontmatterFind notes whose YAML frontmatter contains a given property/value pair. Property names and values are matched case-insensitively; for array-valued properties, a match is declared if any element matches. Returns matching note paths with their full frontmatter. Use to filter notes by metadata like status, type, or tags stored in frontmatter.get_recent_notesList notes ordered by most-recently-modified first. Optional `since` filter accepts an ISO date (e.g. '2026-04-01') or a relative span ('7d', '24h', '2w'); only notes modified at or after that time are returned. Use to surface what you've been working on, build a 'what changed this week' digest, or pick targets for review.get_vault_statsReturn a quick health snapshot of the vault: note count, total bytes, total words, unique tag count, untagged-note count, and the most-recently-modified note. Useful for dashboards and 'is this vault healthy?' checks. Reads through the mtime cache so repeat calls are cheap.resolve_aliasFind every note whose frontmatter `aliases:` field contains the given name (case-insensitive). With `includeBasename: true`, also matches notes whose filename (without `.md`) equals the name — Obsidian's resolution fallback when no alias matches. Use to translate a human-friendly title like 'My Project' into the actual note path before calling get_note.create_noteCreate a new markdown note at the given path with body content and optional YAML frontmatter. Fails (does not overwrite) if a note already exists at that path — use append_to_note, prepend_to_note, or update_frontmatter for existing notes. Missing directories are created automatically, and a .md extension is appended if omitted.append_to_noteAppend text to the end of an existing note without altering prior content. By default, inserts a leading newline if the file does not already end in one, so appended content starts on its own line. Use for log entries, running lists, or adding new sections. Fails if the note does not exist — use create_note to make a new note first.prepend_to_noteInsert content at the top of an existing note's body, immediately after the YAML frontmatter block if one is present (so metadata stays at the top of the file). Use for adding new items to the front of a running list, pinning context, or inserting TL;DR sections. Fails if the note does not exist.update_frontmatterMerge new key-value pairs into a note's YAML frontmatter, preserving any keys not mentioned and leaving the body content untouched. Keys in the payload overwrite existing values. Creates a frontmatter block if the note has none. Returns a count of properties written. Use to set status fields, tags arrays, or other metadata without rewriting the body. Note: The YAML block is regenerated on each update — comments, custom quoting, multi-line scalar style, blank lines, and key ordering inside the block are normalized. Key *presence and values* are preserved; formatting is not.- +29 more on the listing page
Screenpipe tools 30
search-contentSearch screen text, audio transcriptions, input events, memories, and parsed app data. Returns timestamped results with app context. USE WHEN: you need the actual text/content of a moment — quotes, screen text, transcript lines, or compact parsed messages, emails, tasks, documents, and code review — or want to filter by speaker/window. DO NOT USE for: broad questions like 'what was I doing?' (use activity-summary, it pre-summarizes apps + windows + transcripts). Also DO NOT USE for: targeted UI controls (use search-elements). Start with limit=5, increase only if needed. Per-result text is auto-truncated to 1000 chars; pass max_content_length=0 to opt out, or a custom integer to override.synced-devicesList this signed-in user's Screenpipe devices that have uploaded Data Sync records, including each device name and last sync time. USE WHEN: the user asks what devices are available, names another device, or asks a cross-device question and you need the exact device_name filter. This never accepts an account or bucket identifier; the local app forwards the signed-in user's identity.search-synced-contentSearch Data Sync records from this signed-in user's devices. Results include device name, device ID, and timestamp for attribution. USE WHEN: the user asks about another/named device, asks across devices, or local search does not cover the requested machine. For the current machine only, use search-content. Start with a narrow time range and limit=10.list-meetingsList detected meetings (Zoom, Teams, Meet, etc.) with id, duration, app, attendees, and note status. Pass `q` to substring-match title, attendee names/emails, and notes — `q` searches ALL meeting history, so when looking for a meeting with a person or on a topic ('when did I last talk to Noah?'), pass `q` and OMIT start_time. Only constrain the time range when the question itself is time-bound. Results are newest-first; without `q`, old meetings only surface via time range or offset pagination. Follow up with get-meeting (id from results) for the full note and transcript.activity-summaryRich activity overview: authoritative active minutes, app/window time, edited document paths, key text, and audio transcriptions, with optional parsed task context when available. USE WHEN: any broad question about what the user did — 'what was I doing?', 'how long on X?', 'which apps?', 'recap my morning'. This is almost always the right first call for time-range questions — usually sufficient without follow-up searches. Use parsed/path evidence to identify tasks, but only active-minute fields for duration; frame and row counts are never time. DO NOT USE for: finding a specific keyword (use keyword-search) or a specific UI control (use search-elements).search-elementsSearch UI elements (buttons, links, text fields) from the accessibility tree, filterable by role. USE WHEN: you want a specific UI control or page-structure question — 'find every Submit button I saw', 'list the links in that page'. DO NOT USE for: general text/content (use search-content) or fast keyword lookup (use keyword-search).frame-contextGet full accessibility text, parsed tree nodes, and URLs for a specific frame ID. Use after search-content to get detailed context for a specific moment.export-videoExport an MP4 of screen recordings for a time range, with synced microphone audio. Frames are placed at their real timestamps, so the clip's duration matches the wall-clock span you requested (not a sped-up timelapse). Returns the file path. Can take a few minutes for long ranges.update-memoryCreate, update, or delete a persistent memory (facts, preferences, decisions the user wants to remember). To retrieve memories, use search-content with content_type='memory'. To create: provide content + tags. To update: provide id + fields to change. To delete: provide id + delete=true.get-feedbackSearch local user ratings and written comments attached to AI-produced notifications, chats, memories, blocks, artifacts, and other targets. Use before generating related work so you preserve what earned up ratings and correct what earned down ratings.send-notificationSend a notification to the screenpipe desktop UI. Use high priority only for time-sensitive failures or decisions needing human attention; routine findings and completed tasks should be normal or low.health-checkCheck if screenpipe is running and healthy. Returns recording status, frame/audio stats, timestamps.- +18 more on the listing page
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.
Obsidian MCP Pro
{
"mcpServers": {
"rps321321-obsidian-mcp-pro": {
"command": "npx",
"args": [
"-y",
"obsidian-mcp-pro"
],
"env": {
"OBSIDIAN_VAULT_PATH": "YOUR_OBSIDIAN_VAULT_PATH_HERE",
"OBSIDIAN_READ_PATHS": "YOUR_OBSIDIAN_READ_PATHS_HERE",
"OBSIDIAN_WRITE_PATHS": "YOUR_OBSIDIAN_WRITE_PATHS_HERE"
}
}
}
}
Screenpipe
{
"mcpServers": {
"screenpipe": {
"command": "npx",
"args": [
"-y",
"screenpipe-mcp@latest"
]
}
}
}
Frequently asked questions
Obsidian MCP Pro is categorized under Knowledge & Memory and uses a local stdio subprocess. Screenpipe belongs to Knowledge & Memory and uses a local stdio subprocess. Pick Obsidian MCP Pro for knowledge & memory work and Screenpipe 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.
Obsidian MCP Pro is listed as free. Auth: no auth required. Screenpipe is listed as freemium — a free tier with paid plans. Auth: no auth required. 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 rps321321-obsidian-mcp-pro and screenpipe as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Obsidian MCP Pro has a quality signal of 67/100 (Great) with 1 views, 0 installs and 33 GitHub stars. Screenpipe has 73/100 (Great) with 8 views, 0 installs and 22,087 GitHub stars.