Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
Nothing to run from here
Claudeleaf 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.
95/100
trust score
16
downloads a day
local
runs on your machine
389
downloads in 30d
What it does
Bring Claude (and any agent) into Overleaf: a reliable bridge that drives the Overleaf web editor in real time via an SDK, CLI, and MCP server.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user claudeleaf-mcp '--' npx -y claudeleaf
# 2 — ask your agent for something these tools do
# overleaf_list_projects, overleaf_project_info, overleaf_list_documents and 14 more
Claudeleaf costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CLAll 1 server
claudeleaf1 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 Claudeleaf 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 claudeleaf-mcp '--' npx -y claudeleafReconnect, 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.
List every Overleaf project the signed-in account can access (id, name, access).
No parameter schema on file.
Get metadata about a project (name, owner, members, compiler).
No parameter schema on file.
List the documents in a project. Set includeFiles=true to also list binary files.
No parameter schema on file.
Read the full text of a document, identified by its path (e.g.
No parameter schema on file.
Find every occurrence of a literal string in a document. Returns offset/line/column.
No parameter schema on file.
Insert text at a 0-based line and column. Collaborators see the edit live.
No parameter schema on file.
Append text to the end of a document (a newline is added if needed).
No parameter schema on file.
Replace literal occurrences of
No parameter schema on file.
Replace the text between character offsets [start, end) with
No parameter schema on file.
Delete the text between character offsets [start, end).
No parameter schema on file.
Delete 0-based lines startLine..endLine (inclusive).
No parameter schema on file.
Replace a document
No parameter schema on file.
Create a new document.
No parameter schema on file.
Delete a document or file from a project.
No parameter schema on file.
Rename a document or file.
No parameter schema on file.
List users currently connected to a project (name, email, cursor position).
No parameter schema on file.
Recompile a project
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 Claudeleaf 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 95 / 100
Release 0.2.0 · scanned 14 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 score95
Findings1 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationnone
Surface digestdde5623a8ce522fbdbaaa8bd110115843c2bc80953943aa430fdb9a4579ac27d
Score vectorthreat 100 → client 95
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | none | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read | −2 |
| 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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| overleaf_list_projects | no tags | |
| overleaf_project_info | no tags | |
| overleaf_list_documents | no tags | |
| overleaf_read_document | no tags | |
| overleaf_search | no tags | |
| overleaf_insert_text | state-write | state-write: declares readOnlyHint: false |
| overleaf_append_text | state-write | state-write: declares readOnlyHint: false |
| overleaf_replace_text | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| overleaf_replace_range | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| overleaf_delete_range | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| overleaf_delete_lines | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| overleaf_set_document | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| overleaf_create_document | state-write | state-write: declares readOnlyHint: false |
| overleaf_delete_document | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| overleaf_rename_document | state-write | state-write: declares readOnlyHint: false |
| overleaf_connected_users | no tags | |
| overleaf_compile | 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 digestdde5623a8ce522fb
Scanned2026-10-14
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 0.2.0. Pin a release below and the command asks for exactly that one.
0.2.0
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 Claudeleaf 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.