MCP server for 0Latency — persistent memory layer for AI agents. Give Claude, Cursor, or any MCP client long-term memory.
Free
Nothing to run from here
Mindcache is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
Your Obsidian vault, connected to AI. MCP server for bridging personal knowledge with LLMs.
Quickstart
# 1 — run it from where its publisher ships it
npx -y @augmnt-sh/mindcache
# 2 — the plan is chosen at checkout, in the browser
# 3 — ask your agent something
> Your Obsidian vault, connected to AI. MCP server for bridging personal knowledge with LLMs.
Publishernot claimed
AUAll 2 servers
@augmnt-sh2 servers
2 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Mindcache as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. It is scanned, signed and pinned to the version you choose — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add mindcache-mcp -- npx -y @augmnt-sh/mindcacheReconnect, or start a new session, and the tools appear in the model’s tool list.
This is a paid listing, so the CLI has to be signed in and the licence has to be on your account — how the login works. Until then the install stops with the price rather than half-writing a config entry.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
29 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Add a [[wikilink]] to a note, connecting it to another note in the vault. Appends the link under a
Takes no parameters.
Example callreturns →
Analyze a note and suggest other notes that could be linked to it. Uses shared tags, mentions, and content similarity to find connections.
Takes no parameters.
Example callreturns →
Find broken links in the vault — [[wikilinks]] that point to notes that don\
Takes no parameters.
Example callreturns →
Find orphan notes — notes with no incoming or outgoing links. These are disconnected from the knowledge graph and might need connecting.
Takes no parameters.
Example callreturns →
Add one or more tags to a note. Tags are added to the YAML frontmatter. If the note has no frontmatter, it will be created.
Takes no parameters.
Example callreturns →
Update YAML frontmatter properties of a note. Can add new properties or modify existing ones.
Takes no parameters.
Example callreturns →
Rename a note by creating a copy at the new path and deleting the original. Note: Obsidian will update backlinks if the app is running.
Takes no parameters.
Example callreturns →
Move a note to a different folder in the vault. Preserves the filename.
Takes no parameters.
Example callreturns →
Read the full content of a note by its path. Returns the complete markdown including frontmatter.
Takes no parameters.
Example callreturns →
Read a specific section from a note, identified by its heading. Returns content from the heading to the next heading of the same or higher level.
Takes no parameters.
Example callreturns →
Get a note with its metadata: frontmatter properties, tags, wikilinks, and word count. Useful for understanding a note without reading it fully.
Takes no parameters.
Example callreturns →
Read only the YAML frontmatter properties of a note. Fast way to check metadata without reading the full content.
Takes no parameters.
Example callreturns →
Read today
Takes no parameters.
Example callreturns →
Read all daily notes from the current week (Monday to Sunday). Useful for getting a weekly overview of activity.
Takes no parameters.
Example callreturns →
Extract all links from a note — both [[wikilinks]] to other vault notes and external URLs. Useful for seeing what a note references.
Takes no parameters.
Example callreturns →
Quick capture — save a thought, note, or piece of information to the vault. Auto-saves to the inbox folder. Use this for quick, unstructured captures.
Takes no parameters.
Example callreturns →
Create a structured meeting note with attendees, agenda, notes, and action items. Uses the meeting template.
Takes no parameters.
Example callreturns →
Log a decision using the ADR (Architecture Decision Record) format. Captures the context, decision, consequences, and alternatives considered.
Takes no parameters.
Example callreturns →
Capture an idea with context on why it matters and potential next steps.
Takes no parameters.
Example callreturns →
Save something new you learned — a concept, technique, insight, or skill with examples and application notes.
Takes no parameters.
Example callreturns →
Create or update a note about a person — their role, organization, context, and interactions.
Takes no parameters.
Example callreturns →
Bookmark a URL or resource with a summary, tags, and personal notes. Great for saving articles, videos, tools, or documentation.
Takes no parameters.
Example callreturns →
Get an overview of your Obsidian vault: total notes, folder structure, tag distribution, and general statistics.
Takes no parameters.
Example callreturns →
List all tags used in the vault with their occurrence counts. Samples notes to build the tag list.
Takes no parameters.
Example callreturns →
Get the folder structure of the vault as a tree with note counts per folder. Useful for understanding vault organization.
Takes no parameters.
Example callreturns →
Create a new note in the vault. Supports optional templates, folder routing, and frontmatter. Will not overwrite existing notes unless explicitly requested.
Takes no parameters.
Example callreturns →
Append content to the end of an existing note. The note must already exist.
Takes no parameters.
Example callreturns →
Replace the content under a specific heading in a note. Useful for updating a section without modifying the rest of the note.
Takes no parameters.
Example callreturns →
Permanently delete a note from the vault. This cannot be undone.
Takes no parameters.
Example callreturns →
Standardmost installed
$19 / month
- 16,000 calls a month, included
- 192 calls a minute at peak
- Every tool the listing has
- Cancel any time — the unused days are credited
- Runs behind the gateway, so cancelling stops it
Pro
$69 / month
- 160,000 calls a month, included
- 1,920 calls a minute at peak
- Every tool the listing has
- Cancel any time — the unused days are credited
- Runs behind the gateway, so cancelling stops it
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
No call is billed on its own, and this plan carries no monthly call limit. $19 a month covers every tool at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: $8.42
$16.58 left
ATrust score 96 / 100
Release 0.3.1 · scanned 25 Aug 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest8b84f2a505f38fb055625deb9dd34b8251dead9ff6ee79cdc7e0158d81958550
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (44 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search | no tags | |
| ask | no tags | |
| find_related | no tags | |
| find_by_tag | no tags | |
| find_by_date | no tags | |
| find_recent | no tags | |
| find_mentions | no tags | |
| read_note | no tags | |
| read_section | no tags | |
| read_summary | no tags | |
| read_properties | untrusted-input | |
| read_today | no tags | |
| read_this_week | no tags | |
| extract_links | no tags | |
| remember | no tags | |
| remember_meeting | no tags | |
| remember_decision | no tags | |
| remember_idea | no tags | |
| remember_learning | no tags | |
| remember_person | no tags | |
| remember_reference | no tags | |
| log | no tags | |
| log_task | no tags | |
| reflect | no tags | |
| create_note | no tags | |
| append_to_note | no tags | |
| update_section | no tags | |
| delete_note | no tags | |
| add_link | no tags | |
| suggest_connections | no tags | |
| find_gaps | no tags | |
| find_orphans | no tags | |
| add_tag | no tags | |
| update_properties | no tags | |
| rename_note | no tags | |
| move_note | no tags | |
| vault_overview | no tags | |
| list_tags | no tags | |
| get_vault_structure | no tags | |
| find_tasks | no tags | |
| complete_task | no tags | |
| bulk_tag | no tags | |
| daily_notes | no tags | |
| export_note | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest8b84f2a505f38fb0
Scanned2026-08-25
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Pinned to 0.3.1 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
0.3.1
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Mindcache in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.