io.github.sandoreclegane/inkvault
PYPI · INKVAULT
Local-first AI memory: search your Claude Code, Codex, Claude desktop, Pieces and browser history.
Available components
Last scanned (4 hours ago)
Scores higher than 51% of PyPI servers
Category Memory and Knowledge
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 2 of 45 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 16 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability59
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 683 tokens (~170/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 31 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 27 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 26 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 19 Oct 26 50
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed pypi/inkvault@0.3.4
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 45 packages
| Packages resolved | 45 |
|---|---|
| Stale | 1 |
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
get_memory ~53
Full text of one memory (summary, event, chat, snippet, web page, or screen window) by id from search_memories or timeline.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
| max_chars | integer | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
memory_stats ~24
Overview of the vault: counts, date ranges, and most-captured apps.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
search_memories ~352
Search the user's memory: what was rescued from Pieces, plus Claude Code, Claude desktop and Codex sessions, and screen capture. query: what to look for. In "meaning" or "hybrid" mode, natural descriptions work ("that retry helper with exponential backoff"). In "keyword" mode all words must match; FTS5 syntax is accepted: "exact phrase", a OR b, prefix*. mode: "hybrid" (default: keyword + meaning, merged), "keyword" (exact words, names, ids), or "meaning" (related ideas even when wording differs). source: "summaries" (AI-written session summaries, best for 'what was I doing'), "events" (raw screen/document captures, and text read by screen capture; best for specific details), "screen" (the windows you had open, by app and title; keyword-only), "chats" (Pieces chats and Claude Code / Claude desktop / Codex sessions; the conversation name says which), "snippets" (saved code/text snippets), "web" (pages you opened, from your browsers' history; best for 'when did I look at…'), or "all". since/until: optional ISO dates ("2026-10-01") or UTC times ("2026-10-01T14:30"). Returns ranked hits with ids; use get_memory(id) for the full text.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| mode | string | – | – |
| query | string | yes | – |
| since | string | – | – |
| source | string | – | – |
| until | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
timeline ~139
Chronological view of a date range — answers 'what was I working on in/around <date>'. Lists Pieces' session summaries and, when `inkvault digest` has run, a one-paragraph digest per day, a line per day with browsing, and a Screen section: the windows you had open, from screen capture, live (including right now). since/until: ISO dates, e.g. since="2025-10-20", until="2025-10-27". Use get_memory(id) to read one.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| since | string | yes | – |
| until | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
How do I install the io.github.sandoreclegane/inkvault MCP server?
io.github.sandoreclegane/inkvault runs locally as a PyPI package, launched with uvx inkvault. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · inkvault
claude mcp add sandoreclegane-inkvault -- uvx inkvault
What is the io.github.sandoreclegane/inkvault MCP server?
io.github.sandoreclegane/inkvault is an MCP server listed in the public MCP registry as io.github.sandoreclegane/inkvault. Local-first AI memory: search your Claude Code, Codex, Claude desktop, Pieces and browser history. This page covers its PyPI package (inkvault).
Is the io.github.sandoreclegane/inkvault MCP server safe to use?
io.github.sandoreclegane/inkvault scores 50 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.sandoreclegane/inkvault MCP server expose?
io.github.sandoreclegane/inkvault exposes 4 tools: search_memories, get_memory, timeline, memory_stats. Their descriptions and schemas cost roughly 568 tokens of context every time the server is loaded.
Is the io.github.sandoreclegane/inkvault MCP server still maintained?
io.github.sandoreclegane/inkvault is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.sandoreclegane/inkvault MCP server under?
io.github.sandoreclegane/inkvault declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.