Skills/PyPI/overleaf-mcp-server

overleaf-mcp-server@0.4.1

VERIFIED· not started

Publisher claims: "A minimal, auditable MCP server for editing Overleaf projects via Git" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher amcheste · publishing for 203 daysInstalls 115Last detonated 4 h ago
$claude mcp add overleaf-mcp-server -- uvx overleaf-mcp-server
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
GIT_PASSWORDOVERLEAF_TOKENConfiguration, not credentials: OVERLEAF_MCP_CACHE, OVERLEAF_MCP_CONFIG, OVERLEAF_MCP_DEBUG
Where it talks to
overleaf.com (its own)
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard. It asks for GIT_PASSWORD, OVERLEAF_TOKEN and talks to overleaf.com. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --secrets GIT_PASSWORD=overleaf.com,OVERLEAF_TOKEN=overleaf.com -- uvx overleaf-mcp-server

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-14 and scored it 81/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

MEDIUM
Access to sensitive file pathstests/core/test_paths.py:24 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesvalidate_path(tmp_path, "/etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
URL with embedded credentialstests/test_real_overleaf.py:47 · URL with embedded credentials — may be phishing or credential leakingreturn f"https://git:{TOKEN}@git.overleaf.com/{PROJECT_ID}"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Access to sensitive file pathstests/tools/test_read_file.py:47 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesasyncio.run(read_file.handle({"file_path": "../etc/passwd"}))Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/core/test_git_client.py:14 · Python subprocess execution detectedreturn subprocess.run(["git", *args], **kwargs)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detected.github/workflows/tests.yml:140 · Python subprocess execution detectedsubprocess.run([str(cli)] + args, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL with embedded credentialstests/acceptance/conftest.py:47 · URL with embedded credentials — may be phishing or credential leakingreturn f"https://git:{TOKEN}@git.overleaf.com/{PROJECT_ID}"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Python subprocess execution detectedtests/test_real_overleaf.py:51 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/overleaf_mcp/core/git_client.py:42 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/overleaf_mcp/core/project.py:62 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandsrc/overleaf_mcp/core/project.py:81 · File permission modification command — agent changes file ownership/permissionsA throwaway shell helper script is written to a tempfile (chmod 700)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedsrc/overleaf_mcp/core/git_client.py:26 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/acceptance/conftest.py:51 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/overleaf_mcp/core/project.py:113 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/overleaf_mcp/core/paths.py:14 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Path.is_absolute() is platform-specific: on Windows '/etc/passwd' isFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandtests/core/test_project.py:104 · File permission modification command — agent changes file ownership/permissions"""The context manager owns the askpass tempfile lifecycle: chmod 700Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedtests/acceptance/conftest.py:56 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detected.github/workflows/tests.yml:127 · Python subprocess execution detectedsubprocess.run([str(pip), "install", str(wheels[0])], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/overleaf_mcp/core/project.py:140 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_real_overleaf.py:56 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈602 tok
2 files · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for overleaf-mcp-server@0.4.1 as of 4 h ago. This is the package itself, not its dependencies.