Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking
Nothing to run from here
CtxVault 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.
99/100
trust score
6
downloads a day
local
runs on your machine
119
downloads in 30d
What it does
Local memory for AI agents: semantic, skill and episodic vaults as plain folders on disk.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user ctxvault-mcp '--' uvx ctxvault mcp
# 2 — ask your agent for something these tools do
# warmup_status, query, write_doc and 14 more
CtxVault costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
FVAll 1 server
filippo-venturini1 server
1 category
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 CtxVault 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. Its scan result is on the Security tab — 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. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user ctxvault-mcp '--' uvx ctxvault mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
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
17 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Check if the embedding model has finished initializing. Use this to verify warmup status before attempting queries or writes.
Takes no parameters.
Search for relevant information in a CtxVault vault using semantic similarity. Use this when the user asks a question that might be answered by their personal knowledge base or documents. Returns the most relevant text chunks with their source files.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vault_name | string | yes | — |
| query | string | yes | — |
Save new information or agent-generated content to a semantic vault for future retrieval. Use this only with semantic vaults, to persist important context, summaries, or notes that should be remembered across sessions. Supports .txt, .md, and .docx formats.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vault_name | string | yes | — |
| file_path | string | yes | — |
| content | string | yes | — |
| generated_by | string | yes | — |
| overwrite | boolean | no | — |
List all available vaults. Use this before querying or writing to discover which vaults exist and choose the right one.
Takes no parameters.
List all indexed documents inside a specific vault. Use this to understand what knowledge is available before performing a search.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vault_name | string | yes | — |
Create and store a new skill in a skill vault. Use this to persist procedural knowledge, instructions, or how-to guides that agents can retrieve and execute later. The skill will be indexed by name and description for fast lookup. Use this only with skill vaults.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vault_name | string | yes | — |
| skill_name | string | yes | — |
| description | string | yes | — |
| instructions | string | yes | — |
| overwrite | boolean | no | — |
List all available skills inside a specific vault. Use this to understand what skills are available before trying to fetch one.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vault_name | string | yes | — |
Read one skill from a skill vault: its name, description and full instructions. Use this after list_skills, once you know which procedure fits the task, and follow the instructions it returns.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vault_name | string | yes | — |
| skill_name | string | yes | — |
Record something that happened or something the user stated, in an episodic vault. Use this for facts with a lifetime — situations, preferences, relationships, plans — rather than for documents. Give the entities it is about so it can be looked up later, and a salience between 0 and 1 for how much…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vault_name | string | yes | — |
| content | string | yes | — |
| entities | array | no | — |
| source | string | no | — |
| salience | number | no | — |
| confidence | number | no | — |
| occurred_at | string | no | — |
| valid_from | string | no | — |
Retrieve episodes from an episodic vault. By default only statements that still hold are returned. Filter by entity for 'everything about X', pass valid_at to ask what was true at a past moment, or known_at to ask what the vault had already learned by then. Query text is optional and ranks…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vault_name | string | yes | — |
| query | string | no | — |
| entities | array | no | — |
| valid_at | string | no | — |
| known_at | string | no | — |
| include_closed | boolean | no | — |
| order_by | string | no | — |
| limit | integer | no | — |
Mark an episode as no longer true, without deleting it. Use this when something ends and nothing replaces it. If a corrected version exists instead, use supersede_episode so the two stay linked.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vault_name | string | yes | — |
| episode_id | string | yes | — |
| valid_to | string | no | — |
| reason | string | no | — |
Replace an episode with a corrected or updated version. The old statement is closed exactly where the new one begins and the two are linked, so the history of what changed stays readable. Entities and salience carry over from the old episode unless you pass new ones. Use this whenever new…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vault_name | string | yes | — |
| episode_id | string | yes | — |
| content | string | yes | — |
| entities | array | no | — |
| source | string | no | — |
| salience | number | no | — |
Restate an episode more precisely, when the world did not change but you can now say it better ('lives in Padova' -> 'lives in Padova, in the Arcella'). The revision opens where the original did and inherits its attestations and open disputes; the original stays in the history but is no longer…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vault_name | string | yes | — |
| episode_id | string | yes | — |
| content | string | yes | — |
| entities | array | no | — |
| source | string | no | — |
| salience | number | no | — |
Record that a statement already in the vault was asserted again. Use this when you hear something the vault already holds, instead of writing it a second time: the episode stays as it is and gains one attestation, so a fact heard once can be told from one heard many times.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vault_name | string | yes | — |
| episode_id | string | yes | — |
| at | string | no | — |
| source | string | no | — |
Record that two open statements cannot both hold, when you cannot tell which one is wrong. Neither is closed: both keep coming back from queries, each flagged with the other in disputed_with, so you can ask instead of assert. The dispute ends by itself when one side is invalidated or superseded.…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vault_name | string | yes | — |
| episode_id | string | yes | — |
| other_id | string | yes | — |
| note | string | no | — |
Show every version of a statement, oldest first. Use this to explain why the vault believes something, or to see what an episode used to say before it was corrected.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vault_name | string | yes | — |
| episode_id | string | yes | — |
List the entities an episodic vault knows about, with how many episodes mention each one. This is the vault's vocabulary: use it to find out what subjects exist before querying for them, to spot the name a person or thing is recorded under, or to see what has gone quiet. Unlike query_episodes it…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vault_name | string | yes | — |
| include_closed | boolean | no | — |
| valid_at | string | no | — |
| min_episodes | integer | no | — |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install CtxVault or to call it, 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: —
ATrust score 99 / 100
Release 0.9.1 · scanned 11 Nov 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 score99
Findings1 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationrepo
Surface digest5a1b0124b87c6440513c8867cb0148cf43aa758f8e0e7335829dfc2e89cfbae9
Score vectorthreat 100 → client 99
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| 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 (17 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| warmup_status | no tags | |
| query | no tags | |
| write_doc | no tags | |
| list_vaults | no tags | |
| list_docs | no tags | |
| write_skill | no tags | |
| list_skills | untrusted-input | untrusted-input: keyword "fetch" |
| read_skill | no tags | |
| write_episode | no tags | |
| query_episodes | no tags | |
| invalidate_episode | no tags | |
| supersede_episode | no tags | |
| confirm_episode | no tags | |
| dispute_episodes | no tags | |
| episode_history | no tags | |
| list_entities | no tags | |
| revise_episode | 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 digest5a1b0124b87c6440
Scanned2026-11-11
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
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.9.1. Pin a release below and the command asks for exactly that one.
0.9.1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish CtxVault can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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 a signed-in account that does not publish it, and nothing else.