Local-first knowledge graph for token-efficient code review through MCP and CLI
Nothing to run from here
jsonloupe 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.
94/100
trust score
10
downloads a day
local
runs on your machine
976
downloads in 30d
What it does
Open huge JSON locally and give agents its shape, queries and exact values, never the whole blob.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user jsonloupe-mcp '--' npx -y jsonloupe mcp
# 2 — ask your agent for something these tools do
# load_doc, inspect, draft_spec and 12 more
jsonloupe costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
PRAll 1 server
priyanshuN1 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 jsonloupe 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 Node.js — the current LTS (24) is the safe choice; npx 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 jsonloupe-mcp '--' npx -y jsonloupe 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
15 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.
Open a JSON document and return its size and top-level shape. Accepts a file path or inline text,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | no | Absolute or relative path to a .json/.jsonl/.zst file. |
| text | string | no | Inline document text, or a compressed payload string. |
First step toward a spreadsheet: find the repeatable arrays and object maps in a loaded document that can
| Parameter | Type | Required | Notes |
|---|---|---|---|
| docId | string | yes | A docId returned by load_doc. |
Draft a reviewable converter spec for a loaded document, usually after inspect shows its tables. This does
| Parameter | Type | Required | Notes |
|---|---|---|---|
| docId | string | yes | A docId returned by load_doc. |
| outPath | string | no | Optional path for the drafted .json spec. |
| format | string | no | Desired output format (default xlsx). |
| baseDate | string | no | Optional yyyy-MM-dd or today for time-only columns. |
| overwrite | boolean | no | Replace outPath only when explicitly true. |
Write a loaded document out as linked tables — one .xlsx workbook, or a .zip of CSVs — by running a frozen
| Parameter | Type | Required | Notes |
|---|---|---|---|
| docId | string | yes | A docId returned by load_doc. |
| spec | object | no | Inline specVersion 1 converter spec. |
| specPath | string | no | Path to a converter spec; use either this or spec. |
| outPath | string | yes | Destination .xlsx or .zip path. |
| format | string | no | Optional output-format override. |
| overwrite | boolean | no | Replace outPath only when explicitly true. |
Field names and types of the document — never values. With no path, describes the whole document;
| Parameter | Type | Required | Notes |
|---|---|---|---|
| docId | string | no | A docId returned by load_doc. |
| filePath | string | no | File to open now instead of supplying docId. |
| path | string | no | Optional query selecting the subtree to describe, e.g. $.tasks[*]. |
Use this instead of ad-hoc Python for JSON counts, filtered exact sums/averages/min/max, composite groups,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| docId | string | no | A docId returned by load_doc. |
| filePath | string | no | File to open and query now instead of supplying docId. |
| query | string | yes | A query, e.g. $.tasks[?(@.status == 'FAILED')] | count; $.tasks[*] | group(@.region, @.status); $.tasks[*] | top(@.delay, @.id) |
| offset | integer | no | Detail rows to skip (default 0). |
| limit | integer | no | Maximum detail rows returned (default …, 0 for summary only, max …). |
Profile one or more fields across every selected record in one server-side scan; this replaces ad-hoc Python loops
| Parameter | Type | Required | Notes |
|---|---|---|---|
| docId | string | no | A docId returned by load_doc. |
| filePath | string | no | File to open and profile now instead of supplying docId. |
| query | string | yes | Path/predicate selecting records, e.g. $.tasks[*]. Do not append a pipe. |
| fields | array | no | Optional relative fields to profile together, e.g. ["status", "failureReason", "weightKg"]. |
| top | integer | no | Top values per field (default …, max …). |
Read n real values at a path, exactly as they were parsed (int64 and decimal digits intact). A path
| Parameter | Type | Required | Notes |
|---|---|---|---|
| docId | string | no | A docId returned by load_doc. |
| filePath | string | no | File to open and sample now instead of supplying docId. |
| path | string | yes | A query selecting what to sample, e.g. $.tasks or $.tasks[*].id |
| n | integer | no | How many values to return (default …, max …). |
Compare two documents opened with load_doc and return change counts plus the first 25 changes. There is
| Parameter | Type | Required | Notes |
|---|---|---|---|
| docIdA | string | yes | The baseline (older) document. |
| docIdB | string | yes | The current (newer) document. |
| keySpec | string | no | Comma-separated candidate identity keys for array alignment, e.g. "id,taskId". |
The CSV-only shortcut for export_result: run a query and write its complete table to a CSV file (RFC 4180,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| docId | string | no | A docId returned by load_doc. |
| filePath | string | no | Input file to open now instead of supplying docId. |
| query | string | yes | A query producing rows or groups. |
| outPath | string | yes | Where to write the CSV file. |
| overwrite | boolean | no | Replace an existing path atomically (default false). |
Write every query match to a local file without sending the data through the conversation. JSONL accepts
| Parameter | Type | Required | Notes |
|---|---|---|---|
| docId | string | no | A docId returned by load_doc. |
| filePath | string | no | Input file to open now instead of supplying docId. |
| query | string | yes | A path/predicate query, optionally with a table-producing pipe. |
| format | string | yes | Output format. |
| outPath | string | yes | Where to write the result file. |
| overwrite | boolean | no | Replace an existing path atomically (default false). |
Run deterministic checks — a query plus the count it expects — against a document; one verdict per check:
| Parameter | Type | Required | Notes |
|---|---|---|---|
| docId | string | no | A docId returned by load_doc. |
| filePath | string | no | File to open and check now instead of supplying docId. |
| playbookPath | string | no | A jsonloupe playbook (.json) whose checks to run. |
| checks | array | no | Inline checks; use either this or playbookPath. |
| maxEvidence | integer | no | Paths per failed/inconclusive check (default …). |
| allowRepair | boolean | no | Check a document that is not valid JSON after repairing it (default false: refused, as a gate should not pass a broken file). |
Scroll the user's tree view to a path and flash-highlight it. Use this to SHOW the human what you are
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | A query selecting the node to show, e.g. $.tasks[3] or $.meta.runId |
Filter the user's tree view down to the nodes a query matches, so they can see the whole answer set at once rather than one node at a time. Their expansion state is remembered; clear_highlights puts it back. A query that matches nothing is refused rather than emptying their screen.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | A path or predicate query, e.g. $.tasks[?(@.status == 'FAILED')] |
Undo highlight_matches: restore the user's tree to the document and the expansion state they had before it was filtered. Safe to call when nothing is filtered.
No parameter schema on file.
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 jsonloupe 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 94 / 100
Release 1.9.2 · scanned 28 Oct 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 score94
Findings4 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digestc439bf7d270d7684f8e59cb9864ba4e375e5e726ce987da488365b8ceea3874b
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| 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 surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
can send data / act on an external service
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 digestc439bf7d270d7684
Scanned2026-10-28
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 1.9.2. Pin a release below and the command asks for exactly that one.
1.9.2
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 jsonloupe 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.